Garuda - Garba Rujukan Digital

Analisis Data Pada Jaringan Sensor Nirkabel Menggunakan Metode Support Vector Machine Layadi, Caroline; Fajar, Mohammad; Hasniati, Hasniati; Musdar, Izmy Alwiah
Jurnal RESISTOR (Rekayasa Sistem Komputer) Vol 1 No 1 (2018): Jurnal RESISTOR Edisi April 2018
Publisher : LPPM STMIK STIKOM Indonesia

The aims of this research are to implement Support Vector Machine for analyze abnormal data on sensor network and evaluate the implementation result. The data collection in the research were done through the searching of related libraries and software evaluate/testing. In this research, temperature, wind speed, and humidity tested using three kernels (linear, Gaussian, and polynomial). Evaluation result show that the implementation of Support Vector Machine can perform the best data validity analysis using Gaussian Kernel with the percentage of average accuracy, temperature 97.83%, humidity 94.5325%, and wind speed 96.93% for weather data 20-28 May and July 28-August 10, 2015. Meanwhile, for weather data June 5-6, 2017 obtained the percentage of average accuracy of temperature 92.855% and humidity 92.43%.

PEMANFAATAN GOOGLE FOR EDUCATION (GAFE) DI SMKN 10 JENEPONTO Musdar, Izmy Alwiah; Muriati, St.
KLASIKAL : JOURNAL OF EDUCATION, LANGUAGE TEACHING AND SCIENCE Vol 1 No 3 (2019): Klasikal: Journal of Education, Language Teaching and Science
Publisher : Fakultas Keguruan dan Ilmu Pendidikan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52208/klasikal.v1i3.44

SMK Negeri 10 Jeneponto is a Vocational School located in Sapaloe Tolo Timur Kelurahan, Kelara District, Jeneponto Regency. This school has facilities that support students and teachers to utilize IT in teaching and learning. The facilities are Computer Lab and internet connection. However, after conducting interviews with the principal of SMK Negeri 10 Jeneponto, those facilities are not yet utilized optimally. Therefore, it is proposed to do community service that applying GAFE to maximize those facilities. This Community service has some steps. They are website development, GAFE account creation, socialization of the school website, socialization of the GAFE for teachers and evaluation of community service activities. The results of this community service is the schools can manage the web pages themselves. The teachers stated that it is very necessary to implement GAFE to support learning activities in schools but it is still constrained on internet networks that are less stable and not all students have smartphones to support them using GAFE.

Rancang Bangun Sistem Cerdas Pemberian Nilai Otomatis Untuk Ujian Essai Menggunakan Algoritma Cosine Similarity Arfandy, Hamdan; Musdar, Izmy Alwiah
Inspiration: Jurnal Teknologi Informasi dan Komunikasi Vol 10, No 2 (2020): Jurnal Inspiration Volume 10 Issue 2
Publisher : STMIK AKBA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35585/inspir.v10i2.2580

Ujian merupakan salah satu cara evaluasi proses pembelajaran untuk mengetahui tingkat penguasaan peserta didik atas materi pengajaran yang diberikan. Secara garis besar terdapat dua jenis soal yang bisa digunakan yaitu soal objektif dan uraian. Pemberian nilai untuk jawaban soal uraian membutuhkan waktu yang lebih lama dibandingkan soal objektif karena harus diperiksa oleh orang yang benar-benar menguasai materi soal. Salah satu cara yang dapat digunakan untuk mempercepat pemeriksaan jawaban soal uraian adalah mengembangkan sebuah sistem cerdas Automated Essay Scoring (AES). Automated Essay Scoring merupakan sistem penilaian soal ujian uraian secara otomatis dengan membandingkan kunci jawaban dengan jawaban yang diberikan peserta didik melalui perhitungan nilai kedekatan jawaban menggunakan algoritma-algoritma sistem cerdas. Pada penelitian ini dikembangan sebuah sistem cerdas pemeriksaan jawaban soal uraian menggunakan algoritma cosine similarity. Penelitian dilakukan dalam 4 tahapan yaitu spesifikasi kebutuhan, perancangan sistem, implementasi dan pengujian sistem. Pada penelitian ini telah berhasil dirancangan dan diimplementasikan sebuah sistem penilaian otomatis dengan menerapkan preprocessing text dan menghitung bobot teks menggunakan Tf-Idf. Nilai Cosine Similarity untuk setiap jawaban berhasil ditampilkan dan berhasil dikonversi menjadi nilai hasil ujian. Nilai hasil ujian berhasil ditampilkan sesaat setelah ujian berhasil diselesaikan.

Sistem Penunjang Keputusan Pemilihan Peminatan Di Stmik Kharisma Menggunakan Metode Analytic Hierarchy Process Vivian Evania Liauren; Hasniati Hasniati; Izmy Alwiah Musdar
Jurnal INSYPRO (Information System and Processing) Vol 3 No 1 (2018)
Publisher : Prodi Sistem Informasi UIN Alauddin

Abstrak – Penelitian ini bertujuan untuk membangun dan mengimplementasikan sistem penunjang keputusan dalam pemilihan peminatan pada platform android. Aplikasi ini dibangun menggunakan android studio 2.0 dan basis data SQLite. Sistem penunjang keputusan merupakan sebuah sistem berbasis komputer yang membantu dalam proses pengambilan keputusan. Sistem ini berfungsi untuk memberikan keputusan apa yang tepat dan cocok untuk peminatan yang akan diambil dari setiap mahasiswa, sistem ini menggunakan metode Analytic Hierarchy Process. Penelitian ini telah menghasilkan sebuah sistem penunjang keputusan menggunakan metode AHP diimplementasikan pada Android. Akurasi keputusan yang diberikan oleh Sistem Penunjang Keputusan yang dikembangkan adalah 81,2% untuk Program Studi TI dan 50% untuk Program Studi SI.Kata Kunci: SPK, Analytic Hierarchy Process, Platform AndroidAbstract – This study aims to build and implement decision support system in choosing specialization on android platform. This application was built using android studio 2.0 and SQLite database. Decision support system is a computer-based system that helps in the decision-making process. This system serves to provide what decisions are appropriate and suitable for the specialization that will be taken from each student, this system uses the method of Analytic Hierarchy Process. This study has resulted in a decision support system using the AHP method implemented on Android. Accuracy of decision given by Decision Support System developed is 81,2% for IT Study Program and 50% for SI Study Program.Keywords: DSS, Analytic Hierarchy Process, Android Platform

Metode RCE-Kmeans untuk Clustering Data Izmy Alwiah Musdar; Azhari SN
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 9, No 2 (2015): July
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.7544

AbstrakTelah banyak metode yang dikembangkan untuk memecahkan berbagai masalah clustering. Salah satunya menggunakan metode-metode dari bidang kecerdasan kelompok seperti Particle Swarm Optimization (PSO). Metode Rapid Centroid Estimation (RCE) merupakan salah satu metode clustering yang berbasis PSO. RCE, seperti varian PSO clustering lainnya, memiliki kelebihan yaitu hasil clustering tidak tergantung pada inisialisasi pusat cluster awal. RCE juga memiliki waktu komputasi yang jauh lebih cepat dibandingkan dengan metode sebelumnya yaitu Particle Swarm Clustering (PSC) dan modified Particle Swarm Clustering (mPSC), tetapi metode RCE memiliki standar deviasi kualitas skema clustering yang lebih tinggi dibandingkan PSC dan mPSC dimana ini berpengaruh terhadap variansi hasil clustering. Hal ini terjadi karena equilibrium state, yaitu kondisi dimana posisi partikel tidak mengalami perubahan lagi, kurang tepat pada saat kriteria berhenti tercapai. Penelitian ini mengusulkan metode RCE-Kmeans yaitu metode yang mengaplikasikan K-means setelah equilibrium state metode RCE tercapai untuk memperbarui posisi partikel yang dihasilkan dari metode RCE. Hasil penelitian menunjukkan bahwa dari sepuluh dataset, metode RCE-Kmeans memiliki nilai kualitas skema clustering yang lebih baik pada 7 dataset dibandingkan K-means dan lebih baik pada 8 dataset dibandingkan dengan metode RCE. Penggunaan K-means pada metode RCE juga mampu menurunkan nilai standar deviasi dari metode RCE. Kata kunci—Clustering Data, Particle Swarm, K-means, Rapid Centroid Estimation. Abstract There have been many methods developed to solve the clustering problem. One of them is method in swarm intelligence field such as Particle Swarm Optimization (PSO). Rapid Centroid Estimation (RCE) is a method of clustering based Particle Swarm Optimization. RCE, like other variants of PSO clustering, does not depend on initial cluster centers. Moreover, RCE has faster computational time than the previous method like PSC and mPSC. However, RCE has higher standar deviation value than PSC and mPSC in which has impact in the variance of clustering result. It is happaned because of improper equilibrium state, a condition in which the position of the particle does not change anymore, when the stopping criteria is reached. This study proposes RCE-Kmeans which is a method applying K-means after the equilibrium state of RCE reached to update the particle's position which is generated from the RCE method. The results showed that RCE-Kmeans has better quality of the clustering scheme in 7 of 10 datasets compared to K-means and better in 8 of 10 dataset then RCE method. The use of K-means clustering on the RCE method is also able to reduce the standard deviation from RCE method. Keywords—Data Clustering, Particle Swarm, K-means, Rapid Centroid Estimation.

IMPLEMENTASI TEOREMA NAÃVE BAYES PADA SISTEM PENDUKUNG KEPUTUSAN UNTUK MENENTUKAN REKOMENDASI TEMPAT WISATA TERBAIK DISULAWESI SELATAN Rikardo Chandra; izmy alwiah musdar; Junaedy .
SINTECH (Science and Information Technology) Journal Vol. 2 No. 1 (2019): SINTECH Journal Edition April 2019
Publisher : LPPM STMIK STIKOM Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31598/sintechjournal.v2i1.316

This study aims to design and build web-based decision support system applications used to recommend the best tourist attractions in South Sulawesi to tourists. The expected benefit of this research is to help the user get the best tourist recommendation information available in South Sulawesi based on the conditions in input factors. The theorem or method used in this study, namely the theorem NaÃ¯ve Bayes. The design of the system isimplemented using PHP programming language and MYSQL database. Based on the results of the research, the authors have successfully built the application of decision support system to determine the recommendation of tourist attractions in South Sulawesi with 65% accuracy based on 20 tests conducted.

RANCANG BANGUN SISTEM INFORMASI PARIWISATA SULAWESI SELATAN BERBASIS ANDROID DENGAN MENGGUNAKAN METODE PROTOTYPING izmy alwiah musdar; Hamdan Arfandy
SINTECH (Science and Information Technology) Journal Vol. 3 No. 1 (2020): SINTECH Journal Edition April 2020
Publisher : LPPM STMIK STIKOM Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31598/sintechjournal.v3i1.542

Abstract Tourism is one of the sectors that has the opportunity to become the largest contributor to foreign exchange in Indonesia. Indonesia's tourism growth was recorded at 7.2 percent per year, higher than the average world tourism growth of 4.7 percent. The availability of information that is easy and fast to access can make people know about tourism in the Province of South Sulawesi so that it is expected to have an impact on increasing tourist arrivals. In this study, a tourism information system for mobile Sulawesi Province has been developed. The information system was developed by utilizing the prototyping model. The result of this research is a mobile-based tourism information system that is able to present tourism information such as tourist destinations, culinary tours, events, and photos of tourism objects. Tourism information system can be run on Android devices. The developed system can present tourism information which includes 110 destinations, 39 events, 45 culinaries, and photos of tourist attractions from 12 regions. The result of system testing was the features of the system can function properly and successfully show tourism information.

Implementasi Teori Naive Bayes dalam Klasifikasi Ujaran Kebencian di Facebook Willianto Willianto; Izmy Alwiah Musdar; Junaedy Junaedy; Husni Angriani
Jurnal Informatika Universitas Pamulang Vol 6, No 4 (2021): JURNAL INFORMATIKA UNIVERSITAS PAMULANG
Publisher : Teknik Informatika Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/informatika.v6i4.12593

Hate Speech can be orally or in writing which is expressed intentionally by someone for the purpose of spreading and leading to hatred between groups of people. The phenomenon of Hate Speech has become a hot topic. This is motivated by netizens who often express Hate Speech either in the comments column or in their personal status on social media. The impact of this phenomenon is the emergence of hatred in society which can lead to conflict. The purpose of this study is to implement the Naïve Bayes Theory in the classification of Hate Speech on Facebook. In this study Naïve Bayes is used as a Classfifier. Naïve Bayes method is applied to find the probability of words in documents would be categorized as hate speech or not hate speach. This Classfifier is implemented using Python programming language. In the Classfifier design stage, 500 data are collected randomly on Facebook. Data is divided by 80% - 20% , 400 text data for training and 100 text data for testing. The accuracy for hate speech classification in this study is 83%. These results are obtained from Classfifier evaluations using test data where the Classfifier correctly labels 83 out of 100 test data.

Analisis Data Pada Jaringan Sensor Nirkabel Menggunakan Metode Support Vector Machine Caroline Layadi; Mohammad Fajar; Hasniati Hasniati; Izmy Alwiah Musdar
Jurnal RESISTOR (Rekayasa Sistem Komputer) Vol. 1 No. 1 (2018): Jurnal RESISTOR Edisi April 2018
Publisher : LPPM STMIK STIKOM Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31598/jurnalresistor.v1i1.196

The aims of this research are to implement Support Vector Machine for analyze abnormal data on sensor network and evaluate the implementation result. The data collection in the research were done through the searching of related libraries and software evaluate/testing. In this research, temperature, wind speed, and humidity tested using three kernels (linear, Gaussian, and polynomial). Evaluation result show that the implementation of Support Vector Machine can perform the best data validity analysis using Gaussian Kernel with the percentage of average accuracy, temperature 97.83%, humidity 94.5325%, and wind speed 96.93% for weather data 20-28 May and July 28-August 10, 2015. Meanwhile, for weather data June 5-6, 2017 obtained the percentage of average accuracy of temperature 92.855% and humidity 92.43%.

PERBANDINGAN METODE FUZZY SUGENO DENGAN FUZZY TSUKAMOTO PADA SISTEM PREDIKSI HARGA SMARTPHONE BEKAS BERBASIS ANDROID DI WILAYAH MAKASSAR Samuel Pinontoan; Izmy Alwiah Musdar; Hasniati
KHARISMA Tech Vol 14 No 1 (2019): Jurnal KHARISMA Tech
Publisher : STMIK KHARISMA Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (282.196 KB)

This study aims to compare the Fuzzy Sugeno and Fuzzy Tsukamoto methods in the used android smartphone price prediction system based on Android in the Makassar region. The expected benefits of this research are as a service to get used Smartphone price information and pricing before the transaction. The theorems / methods used in this study are Fuzzy Sugeno and Fuzzy Tsukamoto. The research began by designing the Unified Modeling Language (UML). This program is tested using the Black Box Testing and testing method directly in the field. Based on the results of the study it can be concluded that the Fuzzy Sugeno method produces a better predictive value than the Fuzzy Tsukamoto method, with the MAPE value of 11.8% compared to 25.67%.

Title

Found 30 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 30 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 30 Documents
Search