Article Per Year (5 Year)
p-Index From 2021 - 2026
2.679
P-Index
This Author published in this journals
All Journal Jurnal Pengabdian UntukMu NegeRI Digital Zone: Jurnal Teknologi Informasi dan Komunikasi Innovation in Research of Informatics (INNOVATICS) Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) Jurnal Computer Science and Information Technology (CoSciTech) Jurnal Aplikasi Teknologi Informasi dan Manajemen (JATIM) Journal of Software Engineering and Information System (SEIS)
Mualfah, Desti
Unknown Affiliation
Religion Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Law, Crime, Criminology & Criminal Justice Social Sciences

Published : 18 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search
Journal : Jurnal Computer Science and Information Technology (CoSciTech)

 1 
Analisis Digital Forensik Keaslian Video Rekaman CCTV Menggunakan Metode Localization Tampering Mualfah, Desti; Rizki, Yoze; Gea, Meiriladiwis
Computer Science and Information Technology Vol 3 No 1 (2022): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v3i1.3697

Abstract

Video is one the valid evidence if the handling process is in accordance with digital forensic procedures. Closed circuit television is a video sourse that is often used as authentic evidence in court. The authenticity of the video is something that is often doubted by certain parties. For this reason, this discusses how to detect the authenticity of video as digital evidence by comparing the original video files and tampering video files resulting from attack frame addition and attack frame delection. The media info tool is used to analyze the metadata and the localization tampering method is used to detect the frame where manipulation occurs. Localization tampering analyzes frame by frame, calculates as histogram and displays a histogram graph. Based on the results of the metadata analysis of the original video file and the video file tampering, it displays different information, which means that the video has been manipulated. Next, analyze the video with the localization tampering method to display the location on the video frame where manipulation has occurred. From the analysis results provide different information both from the calculation of the RGB value and the histogram graph.
Teknik SMOTE untuk Mengatasi Imbalance Data pada Deteksi Penyakit Stroke Menggunakan Algoritma Random Forest Mualfah, Desti; Fadila, Wahyu; Firdaus, Rahmad
Computer Science and Information Technology Vol 3 No 2 (2022): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v3i2.3912

Abstract

Stroke merupakan penyakit yang berpotensi menyebabkan kelumpuhan bahkan kematian. Pada tahun 2022, stroke terdapat 12,2 juta kasus stroke baru yang menambah jumlah total penderita stroke sebesar 101,4 juta. Dari perolehan data maka diperlukan sebuah teknik yang mampu melakukan deteksi pada penyakit tersebut untuk membantu dalam mendeteksi penyakit stroke, dalam hal ini pendekatan machine learning sebagai salah satu solusi yang dapat digunakan untuk melakukan deteksi pada penyakit stroke. Namun sayangnya data yang diperoleh dalam mendeteki penyakit stroke ditemukan adanya imbalance class dalam menangani tidak imbangnya class sehingga dapat mempengaruhi hasil nilai akurasi dalam mendekteksi penyakit stroke, untuk itu dibutuhkan sebuah algoritma random forest dan metode SMOTE dalam menangani imbalance class. Output yang dihasilkan ialah berupa nilai akurasi, presisi, recall, dan f1-score pada algoritma random forest tanpa SMOTE sebesar 0.98, 0.69, 0.51, dan 0.51. Sedangkan algoritma random forest dengan SMOTE mendapatkan masing-masing sebesar 0.91, 0.92, 0.91, 0.91. Terjadi kenaikan signifikan pada presisi, recall, dan f1-score.
Analisis perbandingan tools mobile forensic menggunakan metode national institute of justice (NIJ) Mualfah, Desti; Muhammad Iqbal Syam; Baidarus
Computer Science and Information Technology Vol 4 No 1 (2023): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v4i1.4767

Abstract

Media sosial sebagai salah satu aplikasi pesan singkat berbasis online dan sangat populer dikalangan masyarakat khususnya di Indonesia. Salah satu aplikasi media sosial terpopuler adalah Signal Messenger. Kepopuleran penggunaan aplikasi ini dipengaruhi karena kekhawatiran dan kepedulian dalam menjaga informasi pribadi masing-masing penggunanya. Aplikasi pesan instan seringkali disalahgunakan pada momen kejahatan dunia maya atau dikenal dengan istilah cybercrime. Pada penelitian telah dilakukan perbandingan kinerja dari dua forensic tools yaitu Oxygen Forensic Detectivedan Belkasoft Evidence Center, yang digunakan untuk mengembalikan data yang telah dihapus, dan barang bukti digital lainnya pada skenario kasus transaksi jual beli narkoba. Metode investigasi dalam penelitian mobile forensic ini menggunakan National Institute of Justice (NIJ), yang terdiri atas lima tahapan antara lain identification, collection, examination, analysis, dan reporting. Dari hasil analisis pada pencarian 6 bukti digital pada file physical image ‘mmcblk0’, menggunakan tool mobile forensic Oxygen Forensic Detective, didapatkan sebanyak 5 dari 6 total bukti digital dengan pencapaian nilai 83.33%. Sedangkan tool mobile forensic Belkasoft Evidence Center, mendapatkan sebanyak 4 dari 6 total bukti digital dengan pencapaian nilai 66.67%. Penggunaan kedua tools tersebut telah berhasil mendapatkan bukti digital, yang digunakan pada skenario kasus transaksi jual beli narkoba, pada barang bukti perangkat smartphone android Samsung Galaxy J2 Prime.
Analisis dan perancangan user interface dan user experience untuk sistem asuransi karyawan berbasis web menggunakan metode design thinking Mualfah, Desti; Rajif, Iqbal
Computer Science and Information Technology Vol 4 No 3 (2023): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v4i3.6233

Abstract

In developing a software application design, it is often done without first observing the user. So the result often causes many problems. Inappropriate design of the interface and user experience will cause problems in the application after it is created. User interface and user experience are two things that are very important and cannot be separated. How easy or difficult it is to use a product will of course also have a big influence on the user's experience when they use the product. Using design thinking in creating a product can have a big influence on the UI/UX process. In designing the WorkerLife website, the author used the design thinking method as a solution to solve problems faced by users and carried out usability testing and assessment using SUS (System Usability Scale). When testing website designs. A score of 77.58 was obtained with a good rating so that the design has been successfully created and users do not experience confusion or difficulties when running the website design prototype.
Sistem Prediksi Penjualan Pupuk Kelapa Sawit PT. Agro Subur Anugrah Menggunakan Metode Single Exponential Smoothing: Sistem Prediksi Penjualan Pupuk Kelapa Sawit PT. Agro Subur Anugrah Menggunakan Metode Single Exponential Smoothing Sunanto, Sunanto; Mualfah, Desti; Ronaldo, Aditya
Computer Science and Information Technology Vol 5 No 1 (2024): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v5i1.6976

Abstract

A factory is an industrial facility where raw materials or components are processed or processed into finished products. The production process in a factory can involve a wide range of activities, including manufacturing, processing, assembly, and energy production. PT. Agro Subur Anugrah is the owner of the Ultra Agrotan organic fertilizer factory which is made from empty palm oil bunches. The Ultra Agrotan fertilizer factory started production in 2017 with a production capacity of 15 tons per day. Due to the increase in the price of chemical fertilizers, demand for Ultra Agrotan fertilizer increased, so production was increased to 50 tons per day. Fertilizer sales are greatly influenced by various factors, namely weather conditions, soil quality, soil type, age of oil palm plants, and cultivation practices carried out by farmers or plantation companies which are not fixed every year, so that fertilizer sales are not smooth due to these conditions. Large unsold fertilizer stocks will harden, this can be detrimental to the company. In this case, a system is applied that can predict the amount of fertilizer production every day, week, month and year based on fertilizer demand data in the previous year, namely fertilizer sales data for 2017, 2018, 2019, 2020, 2021 and 2022. The application is presented using a web-based The single exponential smoothing method is expected to help calculate the amount of production, stock and consumer demand for Ultra Agrotan fertilizer.
Perancangan ulang dan analisis desain UI/UX aplikasi identitas kependudukan digital (IKD) menggunakan metode design thinking Mualfah, Desti; Mardiah, Adilla
Computer Science and Information Technology Vol 5 No 3 (2024): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

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

Abstract

This research aims to increase user satisfaction of the Digital Population Identity (IKD) application by redesigning the user interface (UI/UX). The design features of the IKD application lack intuitiveness and have limited features, thus hindering people's interest in using the application. For this reason, a solution is needed to redesign the user interface (UI/UX) using the Design Thinking method and apply five design stages in the form of Design Thinking (Empathize, Define, Ideate, Prototype, and Testing), then this research produces a prototype of the IKD application. easier to use with test results using the System Usability Scale (SUS) showing that the prototype produced a score of 78, which is in the "GOOD" category, and shows that the redesigned IKD application meets user expectations in terms of ease of use and better experience
Klasifikasi serangan DDoS dengan metode random forest dan teknik class weight pada dataset CICDDoS2019 Mualfah, Desti; Ardiansyah, Rudi; Gunawan, Rahmad
Computer Science and Information Technology Vol 6 No 3 (2025): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v6i3.10731

Abstract

The rapid advancement of information technology has significantly influenced various aspects of life, including an increasing reliance on network-based services. However, this dependence has also led to the emergence of more complex cybersecurity threats, one of the most prominent being Distributed Denial of Service (DDoS) attacks. These attacks can disrupt service availability by overwhelming target systems with excessive traffic. A major challenge in detecting DDoS attacks lies in the wide variety of attack patterns and the class imbalance that commonly occurs in network traffic datasets. To address these issues, a machine learning–based approach capable of handling complex attack behaviors while compensating for imbalanced data distribution is required. One potential solution is the use of the Random Forest algorithm with class-weight techniques, applied to the CICDDoS2019 dataset. The research procedure includes data collection and exploration, preprocessing steps such as handling missing and infinite values, encoding categorical attributes, and feature normalization. The dataset is then divided into training and testing subsets before being processed by the Random Forest model. Model evaluation is conducted using a confusion matrix along with accuracy, precision, recall, and F1-score metrics. Experimental results show that incorporating class weight significantly improves model performance, achieving an accuracy of 99.98%, precision of 99.98%, recall of 99.97%, and an F1-score of 99.97%. These findings demonstrate that the proposed approach is highly effective for accurately detecting and classifying DDoS attacks.
Co-Authors Admojo, Fadhila Tangguh Aminuyati Amran, Hasanatul Fu’adah Baidarus Evans Fuad Fadila, Wahyu Gea, Meiriladiwis Gunawan, Rahmad Gunawan, Sulka Israndi, Febri Januar Al Amin Kamal Saputra, Taufiq Mahesa, Pandu Majid, Sidratul Salsabila Malindo, Qori Mardiah, Adilla Muhammad Innuddin Muhammad Iqbal Syam Novia5, Sherlin Okta Prihatin, Ananda Putra, Gope Mandala Rahmad Firdaus Rahmad Firdaus Rahmadeli, Safitri Rajif, Iqbal Ramadhan, Rizdqi Akbar Rivaldi, Hardi Rizki, Yoze Ronaldo, Aditya Rudi Ardiansyah Sandi, Ganesa Heru Slamet Risnanto Sunanto Viransa, Afdel Windiawati, Ai Wulan Zacki, Moh Soulthan