Garuda - Garba Rujukan Digital

PENGEMBANGAN SISTEM PENJADWALAN KULIAH MENGGUNAKAN ALGORITMA GENETIK (STUDI KASUS : PASCASARJANA UNIVERSITAS JAMBI) Afrizal Nehemia Toscany; Rusdianto Roestam
Jurnal Manajemen Sistem Informasi Vol 2 No 2 (2017): Jurnal Manajemen Sistem Informasi
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar

Current scheduling classes at Jambi University graduate there are still some constraints such as thecreation of a relatively long schedules, conflicting schedules and schedule that does not correspond to thetime availability of the lecturers. Therefore, the author provides a solution in the form of lecturescheduling system using genetic algorithm with programming language PHP and the MySQL DBMS. Forsystem development method that is used is the waterfall. Lecture Schedule result generated by a systemthat has been built is becoming more precision with the allocated hours of teaching, classroom andprofessors. From the test results can also be concluded that the implementation of genetic algorithms is incompliance with the need to support the process of scheduling, so that scheduling can be done morequickly

Analisa Dan Perancangan Website Tes Psikologi (Study Kasus Fakultas Kedokteran Dan Ilmu Kesehatan Universitas Negeri Jambi) Dodi Setiawan; Rusdianto Roestam
Jurnal Manajemen Sistem Informasi Vol 2 No 1 (2017): Jurnal Manajemen Sistem Informasi
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar

Unja ( Universitas Negeri Jambi ) is one of the universities that there dijambi which has a psychologydepartment is one of the educational institutions that have applied information technology both learningmaterials in the field of information technology to the process of academic information systems. AtUniversity has a department of psychology and for the acceptance of new students majoring inpsychology test conducted at this time there are still some shortcomings in terms of slow overallassessment and obtain reports test results that take a lot of time. To overcome all these problems, theresearchers conducted an analysis system Psychological test are ongoing. The object of research focusingon the system Psychological test that have been run and the scope and phases of the systems developmentlife cycle is the purpose of this study is limited to the analysis and design to the prototype. In designingthe system of psychological test online using web-based programming by using PHP and MySQL. Thepurpose of this research is to study and analyze the existing problems in the system of psychological testthat are running test admissions psychology at University as well as designing web-based system ofpsychological test new. Analysis and design of web-based system of psychological test developed will beexpected to overcome the existing problems to the admission process of psychological test can bemanaged online.

Defending Your Mobile Fortress: An In-Depth Look at on-Device Trojan Detection in Machine Learning: Systematic Literature Review Lila Setiyani; Koo Tito Novelianto; Rusdianto Roestam; Sella Monica; Ayu Nur Indahsari; Amadeuz Ezrafel; Alinda Endang Poerwati; Yuliarman Saragih
Jurnal Penelitian Pendidikan IPA Vol 9 No 7 (2023): July
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v9i7.4209

Mobile app trojans are becoming an increasingly serious threat to personal information security. They can cause severe damage by exposing sensitive and personally-identifying information to malicious actors. This paperâ€™s contribution is a comprehensive review of the attack vectors for trojan attacks, and ways to eliminate the risks posed by attack vectors and generate settlement automatically. As such, such attacks must be prevented. In this study, we explore to find how to detect the trojan attack in detail, and the way that we know in machine learning. A review is conducted on the state-of-the-art methods using the preferred reporting items for reviews and meta-analyses (PRISMA) guidelines. We review literature from several publications and analyze the use of machine learning for on-device trojan detection. This review provides evidence for the effectiveness of machine learning in detecting such threats. The current trend shows that signature-based analysis using various metadata, such as permission, intent, API and system calls, and network analysis, are capable of detecting trojan attacks before and after the initial infection

DETEKSI EMAIL SPAM DENGAN CONTINUOUS BAG-OF-WORDS DAN RANDOM FOREST Michiavelly Rustam; Agung Brotokuncoro; Rusdianto Roestam
Scientica: Jurnal Ilmiah Sains dan Teknologi Vol. 2 No. 4 (2024): Scientica: Jurnal Ilmiah Sains dan Teknologi
Publisher : Komunitas Menulis dan Meneliti (Kolibi)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.572349/scientica.v2i4.1260

Email Spam merupakan ancaman dunia maya yang signifikan, karena penipu menggunakan berbagai taktik untuk mengelabuhi individu agar membocorkan informasi sensitif atau mengunduh konten berbahaya. Misalnya, pada bulan Juni 2023, Indonesia menghadapi sekitar 6,51 ribu serangan Spam, yang menunjukkan luasnya permasalahan ini. Serangan-serangan ini sering kali melibatkan strategi penipuan, seperti peniruan identitas atau janji hadiah palsu, untuk menjerat korban yang tidak menaruh curiga. Mengalah pada Spam dapat mengakibatkan kerugian finansial dan dampak buruk lainnya. Untuk mengatasi masalah ini, Penelitian ini mengatasi masalah mendesak ini dengan berfokus pada klasifikasi konten email untuk mendeteksi upaya Phishing. Solusi yang diusulkan memanfaatkan platform runtime seperti Google Colab dan menggunakan analisis Continuous Bag of Words (CBOW) dan metode Random Forest. CBOW dipilih karena efektivitasnya dalam menangkap hubungan semantik antar kata, sehingga memungkinkan model mengekstrak fitur bermakna dari konten email. Random Forest, di sisi lain, dipilih karena kemampuannya menangani kumpulan data tidak seimbang yang biasa ditemui dalam tugas klasifikasi email, memastikan representasi yang adil dari email Spam dan Ham selama pelatihan model. Dengan menggabungkan kedua teknik ini, kami bertujuan untuk mengembangkan model klasifikasi yang kuat yang mampu membedakan secara akurat antara email Phishing (Spam) dan email sah (Ham), sehingga meningkatkan langkah keamanan email. Melalui pendekatan kami, kami bertujuan untuk mengklasifikasikan kumpulan data SpamAssassin ke dalam kategori Ham atau Spam, dengan tingkat presisi yang diharapkan sebesar 0,98, yang menunjukkan efektivitas model dalam mengidentifikasi email Phishing secara akurat.

THE INFLUENCER PRICING PROGNOSTICATION ON SOCIAL MEDIA DYNAMICS AN ADVANCED EXAMINATION OF LINEAR REGRESSION 2 POLY DEGREE ALGORITHM & NEURAL NETWORK: AN ADVANCED EXAMINATION OF LINEAR REGRESSION 2 POLY DEGREE ALGORITHM & NEURAL NETWORK Canesta, Felicia; Rusdianto Roestam
MUST: Journal of Mathematics Education, Science and Technology Vol 9 No 2 (2024): Desember
Publisher : Universitas Muhammadiyah Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30651/must.v9i2.21040

The pervasive influence of social media has spawned the influencer profession, a potent force shaping audience interest in promoted products and services. Unlike traditional media, the impact of influencer promotion is quantifiable, with rates typically determined by factors such as follower count, engagement, and reach. However, the absence of a standardized reference for rate determination poses a potential risk of losses for both influencers and clients. This study seeks to address this challenge through the development of an advanced machine learning-based deep learning predictive model, incorporating Linear Regression with a second-degree polynomial algorithm and a neural network to enhance accuracy. This research underscores the potential of machine learning, including advanced regression algorithms and neural networks, in providing a robust framework for predicting influencer rates. The developed model serves as a significant step toward minimizing adverse effects on both influencers and clients by offering a more nuanced and accurate reference for rate determination in the dynamic landscape of social media promotion The Model Evaluation based on Mean Absolute Error (MAE) metrics reveals that the Keras Neural Network outperformed both Simple Linear Regression (10.612) and Linear Regression with a 2nd-degree polynomial (10.089) in predicting influencer rates. With a substantially lower MAE of 7.952, the neural network demonstrated superior accuracy, leveraging its capacity to capture intricate data relationships and learn non-linear patterns. In conclusion, the Keras Neural Network emerges as the most effective model for influencer rate prediction.

Improvement of Face Recognition Algorithm in Smart Home Security System Ghofir, Abdul; Rusdianto Roestam; Insidini Fawwaz
Journal of Data Science, Technology, and Artificial Intelligence Vol. 1 No. 1 (2024): July 2024
Publisher : CV. ADMITECH SOLUTIONS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63703/ditech.v1i1.21

At present, human intervention is still needed in most security systems to control their functions. The implementation of machine learning plays an important role in smart home security systems for better control functions. The system will have the ability to learn user behaviour, which then represents it in the form of control of the system. One of the important capabilities possessed by a security system is to recognize the face of everyone who accesses a secured place. This paper introduces a face recognition algorithm which is enhanced through a filtration of its controlled Euclidean Distance. The Success Rate Formula is also added and applied for more convincing results. All required system functions are identified and registered as the first system development step. The type of sensor for each function is determined as input data for machine learning processing. Designing and coding the system is carried out on Arduino as its core physical control system before testing and evaluating the system.

Powerpoint Controller using Speech Recognition Christina Christina; Rosalina Rosalina; Raden Bagus Wahyu; Rusdianto Roestam
Jurnal Teknik Informatika dan Sistem Informasi Vol 3 No 2 (2017): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v3i2.670

During presentation, it is hard to maintain the slide because we need to stand in front of the room and often not able to touch the computer. The presenters need to take attention at both their voice, and body language such eye contact, facial expression, posture, gesture, and body orientation. Microsoft PowerPoint is a simple but very useful tool to create digital presentation. Even though it is simple to use, but this application required the presenter to take control while using it, such as to star the slide show or moving it to the next slide. The purpose of this research is to minimize physical contact between user and the computer during the presentation by controlling the move of the slide using voice. This research will implement the Hidden Markov Model algorithm and Sphinx-4 library.

PELATIHAN MENGOLAH LIMBAH MENJADI RUPIAH Rusdianto Roestam
Lentera Jurnal Pengabdian Masyarakat Vol. 1 No. 1 (2023): Lentera Jurnal Pengabdian Masyarakat
Publisher : Lentera Ilmu Madani

Show Abstract | Download Original | Original Source | Check in Google Scholar

Limbah semakin hari semakin meresahkan dan mengancam kelangsungan hidup manusia yang tinggal berdekatan dengan lokasi limbah, jika limbah tidak diolah dengan baik hal ini akan mengakibatkan penurunan angka harapan hidup manusia yang dipengaruhi oleh lingkungan. Tujuan pengabdian untuk memberikan edukasi kepada masyarakat bagaimana mengolah limbah menjadi rupiah. Metode pengabdian dilakukan secara webinar yang memberikan ilmu dasar untuk mengolah limbah baik itu limbah pabrik maupun limbah rumah tangga, serta dari kegiatan acara webinar ini kami harap masyarakat memahami dan mulai mengolah limbah agar lingkungan lebih terjaga. Hasil pengabdian, dimana masyarakat sadar selama ini limbah yang mereka hasilkan pada dasarnya dapat menghasilkan rupiah bila dikelola dengan baik. Kesimpulannya mengolah limbah disisi lain dapat menjaga lingkungan yang bersih dan sehat tetapi disisi lain juga dapat mengasilkan rupiah bilamana dikelola dengana baik.

THE INFLUENCER PRICING PROGNOSTICATION ON SOCIAL MEDIA DYNAMICS AN ADVANCED EXAMINATION OF LINEAR REGRESSION 2 POLY DEGREE ALGORITHM & NEURAL NETWORK: AN ADVANCED EXAMINATION OF LINEAR REGRESSION 2 POLY DEGREE ALGORITHM & NEURAL NETWORK Canesta, Felicia; Rusdianto Roestam
MUST: Journal of Mathematics Education, Science and Technology Vol 9 No 2 (2024): Desember
Publisher : Universitas Muhammadiyah Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30651/must.v9i2.21040

The pervasive influence of social media has spawned the influencer profession, a potent force shaping audience interest in promoted products and services. Unlike traditional media, the impact of influencer promotion is quantifiable, with rates typically determined by factors such as follower count, engagement, and reach. However, the absence of a standardized reference for rate determination poses a potential risk of losses for both influencers and clients. This study seeks to address this challenge through the development of an advanced machine learning-based deep learning predictive model, incorporating Linear Regression with a second-degree polynomial algorithm and a neural network to enhance accuracy. This research underscores the potential of machine learning, including advanced regression algorithms and neural networks, in providing a robust framework for predicting influencer rates. The developed model serves as a significant step toward minimizing adverse effects on both influencers and clients by offering a more nuanced and accurate reference for rate determination in the dynamic landscape of social media promotion The Model Evaluation based on Mean Absolute Error (MAE) metrics reveals that the Keras Neural Network outperformed both Simple Linear Regression (10.612) and Linear Regression with a 2nd-degree polynomial (10.089) in predicting influencer rates. With a substantially lower MAE of 7.952, the neural network demonstrated superior accuracy, leveraging its capacity to capture intricate data relationships and learn non-linear patterns. In conclusion, the Keras Neural Network emerges as the most effective model for influencer rate prediction.

Title

Found 19 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 19 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 19 Documents
Search