Enggar Novianto
Unknown Affiliation

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

KEAMANAN INFORMASI (INFORMATION SECURITY) PADA APLIKASI SISTEM INFORMASI MANAJEMEN KEPEGAWAIAN DENGAN DEFENSE IN DEPTH Enggar Novianto; Erik Iman Heri Ujianto; Rianto Rianto
J-ICON : Jurnal Komputer dan Informatika Vol 11 No 1 (2023): Maret 2023
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v11i1.9139

Abstract

The rapid development of Information Technology (IT) has made IT the most important aspect to meet organizational needs. The existence of IT is believed to be able to provide solutions related to the organization's business processes, so that many organizations offer their resources to increase efficiency by relying on information technology support. Information system security is an internal organizational subsystem tasked with managing the risks associated with computerized information systems. Information system security is the application of international control principles, which are specifically used to trigger problems in information systems. Important information leads to protected information structures, more information is now available from the internet, so information management now includes computer and network technology. The goal of information security is to strengthen business operations and protect against falling business prices by minimizing the risks associated with internal security. The purpose of this study is to understand information security in the implementation of the Personnel Management Information System (SIMPEG) at Sebelas Maret University. The research method used is the application of Defense In Depth to analyze information security, including many layers of security to ensure information security. The results of the descriptive analysis explain that the design and development of SIMPEG pays attention to the principles and aspects of data and information security. However, information security vulnerabilities can occur at the server protection layer, network protection layer, and physical protection layer.
User Analysis of Info BMKG Application in The Perspective of Human Computer Interaction Using Support Vector Machine Algorithm Ilham Fannani; Enggar Novianto; Alfin Syarifuddin Syahab
Inspiration: Jurnal Teknologi Informasi dan Komunikasi Vol. 13 No. 1 (2023): Inspiration: Jurnal Teknologi Informasi dan Komunikasi
Publisher : Pusat Penelitian dan Pengabdian Pada Masyarakat Sekolah Tinggi Manajemen Informatika dan Komputer AKBA Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35585/inspir.v13i1.42

Abstract

On the Google Play Store, users often read other users' app reviews and reputations, before downloading an app. This makes the analysis of user reviews very interesting for app owners to make future decisions. This study aims to analyze user reviews of the Info BMKG application on the Google Play Store, using sentiment analysis. This user review analysis uses the Support Vector Machine (SVM) method. The evaluation proposal was made from more than 3,000 user reviews collected from the INFOBMKG application on the Google Play Store. The results of the analysis using the Support Vector Machine produce an accuracy of 85.54 % and the most frequently reviewed positive review results are "Good", while the most frequently reviewed negative reviews are "Error". Which indicates a complaint against INFOBMKG users, and from the negative words that appear most often, there are two combinations of the two words that appear most often together, namely the word "very helpful" and the word "less accurate", which indicates that user often complain about problems related to application performance. The results of the sentiment analysis process of testing 3000 review data using the fold = 5 test value in the Support Vector Machine (SVM) method obtained an accuracy of 85.54 % which produces predictions on data testing, namely 1500 positive reviews and 1500 negative reviews 1500 reviews.
PERBANDINGAN METODE KLASIFIKASI RANDOM FOREST DAN SUPPORT VECTOR MACHINE DALAM MEMPREDIKSI CAPAIAN STUDI MAHASISWA Enggar Novianto; Suhirman Suhirman; Damar Prasetyo
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 9, No 4 (2024)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v9i4.5423

Abstract

Keberhasilan Universitas, swasta dan negeri bergantung pada mahasiswa dan untuk mengurangi tingkat kegagalan akademik, diperlukan sistem yang dapat memprediksi mahasiswa berdasarkan data akademik serta membuat penilaian untuk memprediksi seberapa baik capaian studi mahasiswa. Data program studi dapat diolah dengan cepat dan akurat, dan data mining adalah proses penambangan data untuk membuat prediksi capaian studi berdasarkan data tentang mahasiswa. Kebaharuan dari penelitian ini adalah menggunakan proses untuk mengoptimalkan model RF dan SVM serta menghasilkan atribut yang berpengaruh terhadap akurasi dalam memprediksi capaian studi mahasiswa program studi S1 Ilmu Hukum Fakultas Hukum Universitas Sebelas Maret dengan seleksi fitur menggunakan Forward Selection. Pemodelan menggunakan RF sebelum dilakukan seleksi fitur mendapatkan hasil akurasi sebesar 97,67%, sedangkan pemodelan menggunakan SVM mendapatkan hasil akurasi sebesar 91,47% dengan menggunakan data mahasiswa angkatan tahun 2021 sejumlah 433 data dengan pembagian 70% data latih dan 30% data uji. Penggunaan seleksi fitur menggunakan metode Forward Selection tidak dapat meningkatkan hasil akurasi pada algoritma RF serta menghasilkan empat atribut yang berpengaruh pada klasifikasi prediksi capaian studi mahasiswa. Pada pemodelan SVM, seleksi fitur dapat meningkatkan nilai akurasi sebesar 6,2%, sehingga hasil akurasi SVM setelah dilakukan seleksi fitur adalah sebesar 97,67% dengan menghasilkan satu atribut yang berpengaruh pada klasifikasi prediksi capain studi mahasiswa. Perbandingan metode klasifikasi RF dan SVM setelah dilakukan seleksi fitur mendapatkan akurasi yang sama yaitu 97,67%, oleh karena itu, hasil penelitian ini termasuk dalam kategori model yang cukup. Hasil penelitian dapat menjadi acuan bagi pengelola program studi dalam memberikan perlakuan khusus kepada mahasiswa yang diprediksi tidak tercapai pembelajarannya. The success of universities, private and public depends on students and to reduce the rate of academic failure, a system is needed that can predict students based on academic data and make assessments to predict how well students will achieve in their studies. Study program data can be processed quickly and accurately, and data mining is a data mining process to make predictions about study outcomes based on data about students. The novelty of this research is that it uses a process to optimize the RF and SVM models and produces attributes that influence accuracy in predicting study outcomes for undergraduate students in the Legal Sciences study program, Faculty of Law, Sebelas Maret University by selecting features using Forward Selection. Modeling using RF before feature selection got an accuracy result of 97.67%, while modeling using SVM got an accuracy result of 91.47% using 433 student data from the class of 2021 with a division of 70% training data and 30% test data. The use of feature selection using the Forward Selection method cannot improve the accuracy results of the RF algorithm and produces four attributes that influence the classification of student study achievement predictions. In SVM modeling, feature selection can increase the accuracy value by 6.2%, so that the SVM accuracy result after feature selection is 97.67% by producing one attribute that influences the prediction classification of student study achievement. Comparison of the RF and SVM classification methods after feature selection obtained the same accuracy, namely 97.67%, therefore, the results of this study are included in the adequate model category. The results of the research can be a reference for study program managers in providing special treatment to students whose learning is predicted to fail.