Article Per Year (5 Year)
p-Index From 2021 - 2026
4.638
P-Index
This Author published in this journals
All Journal Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Jurnal Elektronika Listrik dan Teknologi Informasi Terapan bit-Tech Jurnal Computer Science and Information Technology (CoSciTech) Journal of Computer Scine and Information Technology Jurnal Pustaka AI : Pusat Akses Kajian Teknologi Artificial Intelligence Jurnal Komtekinfo RJOCS (Riau Journal of Computer Science) CSRID
Yuhandri
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Energy Engineering Materials Science & Nanotechnology Mathematics

Published : 37 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 37 Documents
Search

 1   2   3   4 
METODE MULTIFACTOR EVALUATION PROCESS UNTUK MENENTUKAN STRATEGI PROMOSI KAMPUS (STUDI KASUS DI UNIVERSITAS MUHAMMADIYAH MUARA BUNGO) Aal, Defrizal; Yuhandri; Sumijan
RJOCS (Riau Journal of Computer Science) Vol. 9 No. 2 (2023): RJOCS (Riau Journal of Computer Science)
Publisher : Fakultas Ilmu Komputer, Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjocs.v9i2.1784

Abstract

Setiap tahun ajaran baru kampus selalu saling bersaing untuk mendapatkan daya tarik calon mahasiswa baru dalam memilih Perguruan Tinggi tertentu, dan keunikan tersebut sekaligus dapat dijadikan sebagai keunggulan kompetitif. Oleh karena itu perlu adanya strategi promosi dari masing-masing kampus, khususnya di Universitas Muhammadiyah Muara Bungo (UMMUBA). Dalam penelitian ini strategi promosi kampusnya di analisa dengan menggunakan Metode Multifactor Evaluation Process (MFEP) dimana Nilai faktor atau kriteria didapatkan dari kuesioner yang dibuat secara sistem dan selanjutnya dibuatkan sub kriteria yang diidentifikasi dari nilai bobot sub kriteria tersebut. Berdasarkan kriteria promosi kampus itu, maka akan diimplementasikan beberapa alternatif alat atau media promosi kampus yang akan diterapkan dari setiap kriteria nilai bobot faktor tersebut menjadi nilai evaluasi bobot faktor dan akan dilakukan perhitungan nilai bobot evaluasi dari masing-masing alternatif alat atau media strategi promosi kampus tersebut. Berdasarkan bobot evaluasi tiap faktor dari alternatif alat atau media promosi kampus didapatkan maka dapat dicari nilai Total Weight Evaluation per Alternatif alat atau media promosi yang akan diuji, selanjutnya dilakukan perangkingan dan dibuat keputusan, mana yang terbaik dan baik. Dalam penelitian ini, didapatkan kesimpulan apabila nilai total weight evaluation dari alternatif alat atau media promosi itu nilainya besar atau sama dengan 10 (≥10) maka alternatif atau alat media promosi tersebut dikatakan sebagai prediket TERBAIK dan sebaliknya jika total weight evaluation itu lebih kecil dari 10 (≤10) maka nilai total weight evaluation seperti ini dikatakan sebagai prediket BAIK.
PENERAPAN METODE MOORA UNTUK REKOMENDASI PENGHARGAAN DOSEN BERDASARKAN KINERJA PENELITIAN DAN PENGABDIAN MASYARAKAT (STUDI KASUS DI STMIK ROYAL KISARAN) Eriyanto, Joko; Sumijan; Yuhandri
RJOCS (Riau Journal of Computer Science) Vol. 9 No. 2 (2023): RJOCS (Riau Journal of Computer Science)
Publisher : Fakultas Ilmu Komputer, Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjocs.v9i2.2053

Abstract

Pemberian penghargaan merupakan salah satu bentuk pengakuan dan motivasi bagi seseorang yang telah melakukan prestasi atau kinerja yang luar biasa. Di dalam dunia akademik, penghargaan diberikan kepada dosen yang memiliki kinerja yang baik dalam bidang penelitian dan pengabdian masyarakat. Namun, dalam pengambilan keputusan pemberian penghargaan tersebut, seringkali terjadi ketidakjelasan dalam kriteria penilaian dan pengambilan keputusan yang subjektif. Oleh karena itu, perlu dilakukan sebuah penelitian untuk mengembangkan sistem rekomendasi dalam pengambilan keputusan pemberian penghargaan dosen yang objektif dan efisien. Metode Moora (Multi-Objective Optimization by Ratio Analysis) merupakan salah satu metode yang dapat digunakan untuk menghasilkan rekomendasi pemberian penghargaan yang akurat dan konsisten. Penelitian ini bertujuan untuk mengembangkan sebuah sistem rekomendasi pemberian penghargaan dosen berdasarkan kinerja penelitian dan pengabdian masyarakat menggunakan Metode Moora. Dalam penelitian ini, data kinerja penelitian dan pengabdian masyarakat dari dosen-dosen yang bersangkutan dikumpulkan dan diolah menggunakan Metode Moora. Selanjutnya, sistem rekomendasi tersebut diuji coba dengan menggunakan data aktual dari LPPM STMIK Royal Kisaran. Kemudian didapatkan hasil akhir dimana alternatif A1 sebagai nilai tertinggi 0.33983832
Audit Keamanan Website Menggunakan Acunetix Web Vulnerability (Studi Kasus Di SMK Muhammadiyah 3 Terpadu Pekanbaru) Supriyanto, Boby; Sumijan; Yuhandri
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.v5i1.6705

Abstract

Perkembangan teknologi informasi berkembang pesat seiring dengan pertumbuhan penggunanya. Contoh dari perkembangan teknologi adalah penggunaan website untuk mendukung kegiatan pembelajaran. Website merupakan kumpulan halaman web yang dapat diakses secara publik. Website dapat terdiri dari teks, gambar, video, dan media suara lainnya. Namun dengan berkembangnya suatu teknologi, maka perkembangan kerentanan atau serangan terhadap teknologi tersebut juga bertambah. Berdasarkan laporan tahunan monitoring keamanan siber tahun 2021 oleh Badan Siber dan Sandi Negara (BSSN), terdapat lebih dari 1,6 miliar serangan siber yang telah terjadi di Indonesia. Penelitian ini akan menggunakan Acunetix Web Vulnerability Scanner (WVS) untuk mengaudit keamanan website SMK Muhammadiyah 2 Terpadu Pekanbaru (SMK MUTI). Penelitian ini akan mengkaji kelemahan keamanan website SMK MUTI dan membahas bagaimana Acunetix Web Vulnerability dapat membantu dalam meningkatkan tingkat keamanan website tersebut. Metode Vulnerability Assessment (VA) yang digunakan adalah analisis deskriptif, yaitu data yang diperoleh disajikan dalam bentuk tabel, sehingga memungkinkan untuk memperjelas hasil analisis yang dilakukan dalam meng-audit. Berdasarkan data yang diperoleh dari hasil scanning iterasi 1 yang dilakukan, website SMK MUTI berada pada level ancaman 3 tergolong tinggi dengan ditemukan 192 peringatan atau kerentanan, dimana 2 diantaranya berada pada level tinggi dan 11 berada pada level sedang. Berdasarkan audit, dilakukan perbaikan dan pengujian pada penelitian di situs SMK MUTI ini, hasil yang telah dilakukan tingkat ancaman yang dicapai berada pada level 1, dimana pada level tinggi, jumlah kerentanan menjadi 0 dan tingkat dukungan juga menjadi 0, sehingga dapat disimpulkan bahwa situs SMK MUTI saat ini dengan status level 1 dapat bebas dari kerentanan keamanan.
Vision Transformer untuk Identifikasi 15 Variasi Citra Ikan Koi Uthama, Rayhan; Yuhandri; Billy Hendrik
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.v5i1.6711

Abstract

This research aims to classify various types of koi fish using Vision Transformer (ViT). There is previous research [1] using Support Vector Machine (SVM) as a classifier to identify 15 types of koi fish with training and testing datasets respectively of 1200 and 300 images. This research was continued by research [2] which implemented a Convolutional Neural Network (CNN) as a classifier to identify 15 types of koi fish with the same amount dataset. As a result, the research achieved a classification accuracy rate of 84%. Although the accuracy obtained from using CNN is quite high, there is still room for improvement in classification accuracy. Overcoming obstacles such as limitations in classification accuracy in previous studies and further exploration of the use of new algorithms and techniques, this study proposes a ViT architecture to improve accuracy in Koi fish classification. ViT is a deep learning algorithm adopted from the Transformer algorithm which works by relying on self-attention mechanism tasks. Because the power of data representation is better than other deep learning algorithms including CNN, researchers have applied this Transformer task in the field of computer vision, one of the results of this application is ViT. This study was designed using class and number datasets retained from two previous studies. Meanwhile, the koi fish image dataset used in this research was collected from the internet and has been validated. The implementation of ViT as a classifier in koi classification in this research resulted in an accuracy level that reached an average of 89% in all classes of test data.
Penerapan Convolutional Neural Network pada Klasifikasi Citra Pola Kain Tenun Melayu Mukhlis Santoso; Sarjon Defit; Yuhandri
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.v5i1.6713

Abstract

The use of electronic computerized media is growing along with advances in hardware and software as an analytical tool with various algorithms and methods for classifying and measuring objects in various contexts. This progress aims to overcome the weaknesses that exist in conventional methods used in the identification process. The identification process can be applied to various objects, one of which is an image object. An image is a visual representation of an object formed through a combination of RGB (red, green, blue) colors. RGB color components or features have a range of values from 0 to 255 in an image. Weaving is a type of fabric that is specially made with distinctive motifs. Malay weaving motifs have a lot of diversity, this diversity makes it difficult to distinguish the motifs of these fabrics.This study aims to recognize and distinguish the pattern of Malay woven fabric. The method used in this research is Convolutional Neural Network (CNN). The CNN method has several stages, namely Convolution Layer, Pooling Layer, Rectifed Linear Unit (ReLU) Function, Fully-Connected Layer, Transfer Learning, Optimizer and Accuracy. The dataset used in this research is sourced from Tenun Putri Mas Bengkalis. The dataset used consists of 1000 images of weaving motifs which are divided into 80% training data and 20% testing data, from the existing dataset divided into three categories of weaving motifs namely pucuk rebung, elbow clouds and elbow keluang. The results in this study are considered good because they produce accuracy with a result of 95% with an epoch value of 15. From the results of good enough accuracy, it is hoped that it can help the community in recognizing Malay weaving motifs.
Decision Support System for Selecting Casual Daily Workers to Become Permanent Employees Using the Profile Matching Method Edwar, Eggy Febyanti; Yuhandri; Arlis, Syafri
Journal of Computer Scine and Information Technology Volume 10 Issue 4 (2024): JCSITech
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/jcsitech.v10i4.109

Abstract

Information is the result of processing data from one or more sources, which is then processed to provide value, meaning and benefits. In modern times, the use of technology plays a very important role as a means of information and promotion, especially in the field of websites in delivering information. Technological advances in the field of computers are very helpful in the current decision-making process. One method of decision support systems is profile matching. This method is used to determine the assessment in selecting daily employees to become employees. Profile matching is broadly a process of comparing individual competition in job competition so that the difference in competition (also called gap) can be known, the smaller the gap produced, the greater the weight of the value which means that there is a greater chance for employees to occupy the position. After the calculation using the Profile Matching method, the ranking value that meets the requirements is in the alternative with the name of the worker, namely Bakhtiar with a score of 4.535 and is recommended to become a permanent employee. By applying this method, it is very helpful in determining the selection of casual laborers to become permanent employees.
Eksplorasi Algoritma Decision Tree untuk Penentuan Siswa Berprestasi Ramadhan, Prestian; Yuhandri; Veri, Jhon
bit-Tech Vol. 7 No. 3 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v7i3.2210

Abstract

Kemajuan teknologi informasi telah membawa perubahan signifikan dalam berbagai aspek kehidupan, termasuk pendidikan. Salah satu tantangan utama dalam meningkatkan kualitas pembelajaran adalah identifikasi siswa berprestasi secara akurat dan objektif. Penelitian ini bertujuan untuk menerapkan algoritma Decision Tree C4.5 dalam menentukan siswa berprestasi di SMPN 1 Kerinci, dengan mempertimbangkan faktor akademik dan non-akademik seperti nilai disiplin, nilai tahfidz, nilai akhlak, dan nilai ujian. Metode penelitian mencakup pengumpulan data siswa, preprocessing data untuk mengatasi ketidakseimbangan data, analisis faktor-faktor yang berpengaruh, serta pembangunan model klasifikasi menggunakan perangkat lunak RapidMiner 9.0. Hasil penelitian menunjukkan bahwa algoritma Decision Tree C4.5 mampu mengklasifikasikan siswa dengan tingkat akurasi sebesar 91,67%, precision 93,33% untuk kelas "Tidak" dan 88,89% untuk kelas "Layak", serta recall masing-masing 93,33% dan 88,89%. Berdasarkan analisis gain ratio, nilai akhlak memiliki pengaruh terbesar dalam klasifikasi siswa, dengan nilai 0,5961, diikuti oleh nilai tahfidz dan nilai disiplin. Model klasifikasi ini dapat membantu sekolah dalam mengidentifikasi siswa secara lebih objektif, sehingga memungkinkan pengambilan keputusan berbasis data dalam memberikan intervensi pendidikan yang lebih tepat sasaran. Selain itu, hasil penelitian ini membuka peluang untuk pengembangan lebih lanjut, seperti penggunaan teknik ensemble learning atau optimasi model menggunakan metode boosting guna meningkatkan performa klasifikasi. Dengan demikian, sistem berbasis data mining ini dapat menjadi solusi inovatif dalam meningkatkan mutu pendidikan, mendukung kebijakan akademik yang lebih adaptif, serta mengarah pada pembelajaran yang lebih personalisasi dan efektif.
Analisis Data Forensik Pada Rekaman CCTV Menggunakan Metode National Institute Of Standard Techology (NIST) Ilham Asy'ari; Yuhandri; Sumijan
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 | DOI: 10.37859/coscitech.v5i3.7779

Abstract

CCTV (Closed-Circuit Television) recordings have become one of the important instruments in monitoring and securing various places such as companies, commercial buildings, public institutions, and households. CCTV recordings are often vital evidence in investigating crimes, accidents, or other incidents. However, in addition to the visual content stored in CCTV recordings, metadata also plays an essential role in forensic analysis and event reconstruction. The NIST method has developed several techniques and guidelines for forensic metadata analysis on CCTV recordings. This research aims to explore and apply the forensic metadata analysis methods recommended by NIST (National Institute of Standards and Technology) in the context of CCTV recordings. By involving forensic data analysis techniques and information security principles, this study will delve into the potential of metadata analysis in supporting criminal investigations, event reconstructions, and meeting the security standards established by NIST. This research is crucial in the context of digital security and modern forensic investigations. The outcome of applying the NIST methods in forensic data analysis of CCTV recordings is the preparation of an official report derived from the stages outlined in the NIST method, so that the report can serve as a reference in court, and the authenticity of the digital evidence can be validated. By applying the NIST method in forensic data analysis of CCTV recordings, the case handling process becomes structured and adheres to procedures, with a valid report ensuring the integrity of the digital evidence.
Improved Backpropagation Using Genetic Algorithm for Prediction of Anomalies and Data Unavailability Widi Nurcahyo, Gunadi; Akbari Wafridh; Yuhandri
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 8 No 4 (2024): August 2024
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v8i4.5507

Abstract

Anomalies and data unavailability are significant challenges in conducting surveys, affecting the validity, reliability, and accuracy of analysis results. Various methods address these issues, including the Backpropagation Neural Network (BPNN) for data prediction. However, BPNN can get stuck in local minima, resulting in suboptimal error values. To enhance BPNN's effectiveness, this study integrates Genetic Algorithm (GA) optimization, forming the BPGA method. GA is effective in finding optimal parameter solutions and improving prediction accuracy. This research uses data from the 2022 National Socio-Economic Survey (Susenas) in Solok District to compare the prediction performance of BPNN, Multiple Imputation (MI), and BPGA methods. The comparison involves training the models with a subset of the data and testing their predictions on a separate subset. The BPGA method demonstrates superior accuracy, with the lowest mean squared error (MSE) and highest average accuracy, outperforming both BPNN and MI methods.
Identification of Skin Diseases in Toddlers Using Convolutional Neural Networks Maharani, Dian; Yuhandri; Very, Jhon
Jurnal KomtekInfo Vol. 12 No. 3 (2025): Komtekinfo
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/komtekinfo.v12i3.665

Abstract

The development of Artificial Intelligence (AI) technology, particularly in the field of computer vision, has made a significant contribution to medical image analysis. Skin disease in toddlers is a common health problem, especially in developing countries. Toddlers' skin is highly susceptible to various infections and dermatological conditions, ranging from bacterial and viral infections to allergies. Some skin diseases frequently found in toddlers include eczema, dermatitis, impetigo, and fungal infections. This study aims to develop a skin disease classification system in toddlers using the Convolutional Neural Network (CNN) method that can be implemented in applications. The Convolutional Neural Network (CNN) method and the U-Net architecture are used to identify skin diseases in toddlers, requiring a fast and accurate diagnosis, but limited medical personnel and examination time are challenges. A deep learning-based system is proposed to assist the automatic identification process. The research dataset consists of 100 toddler skin images obtained from Siti Rahmah Islamic Hospital, covering various types of common skin diseases. The preprocessing process includes cropping, resizing to 128x128 pixels, normalization, and data augmentation to increase the diversity of the dataset. The CNN architecture is used in the feature extraction stage through convolution and pooling layers, while the U-Net is applied in the segmentation stage to separate the wound area from healthy skin with high precision through the encoder-decoder mechanism and skip connection. The model is trained using the Adam optimization algorithm with the Binary Cross-Entropy loss function and the accuracy evaluation metric and Mean Intersection over Union (IoU). The results show that the system is able to segment the wound area with 95.7% accuracy on the test data, and produces fast and efficient detection. The application of the CNN and U-Net methods in this study proves its effectiveness in supporting the medical diagnosis process, especially in cases of toddler skin diseases, as well as can be a reference in contributing to improving the quality of health services, especially in the diagnosis of skin diseases in toddlers and the development of computer vision-based decision support systems in the health sector.
Co-Authors Aal, Defrizal Ade Dwi Dayani Akbari Wafridh Arlis , Syafri Auriga, Wira Billy Hendrik Dian Maharani, Dian Edwar, Eggy Febyanti Eriyanto, Joko Fernando Ramadhan Fikri, Dzaki Al Gunadi Widi Nurcahyo Gunadi Widi Nurcahyo, Gunadi Hardianto, Romi Harkamsyah Andrianof Hendrik, Billy Idir Fitriyanto Idir Ilham Asy'ari Indah Dwi Putri Karseno, Doni Mardison Meiditra, Irzon Mey Yuki Lestari Mukhlis Santoso Pulungan, Akhiruddin Rahmansyah, Rizky Ramadhan, Prestian Ramadhanu, Agung Resnawita Riati, Itin Ridho, Ridho Afwan Rita Sari Rita Sari Rusydi, Rezki Sahri, Alfi Sajida, Mayang Saputra, Randy Sari, Fitri P. Sarjon Defit Siregar, Diffri Soeheri Soeheri Sonia Indhira Sovia, Rini Sumijan Supriyanto, Boby Syafri Arlis Syaputra, Eka B. Tri Agusti Farma Uthama, Rayhan Veri, Jhon Very, Jhon Wahyu Saptha Negoro Wahyu Saptha Negoro Yanti, Salma Nofri Yuda, Fitra Yuda