cover
Contact Name
Hafiz Irsyad
Contact Email
hafizirsyad@mdp.ac.id
Phone
+6281373740969
Journal Mail Official
hafizirsyad@mdp.ac.id
Editorial Address
Universitas Multi Data Palembang, Kampus Rajawali. Jl. Rajawali no 14 Palembang
Location
Kota palembang,
Sumatera selatan
INDONESIA
Algoritme Jurnal Mahasiswa Teknik Informatika
ISSN : -     EISSN : 27758796     DOI : https://doi.org/10.35957/algoritme.v2i2
Core Subject : Science,
Jurnal Algoritme menjadi sarana publikasi artikel hasil temuan Penelitian orisinal atau artikel analisis. Bahasa yang digunakan jurnal adalah bahasa Inggris atau bahasa Indonesia. Ruang lingkup tulisan harus relevan dengan disiplin ilmu seperti: - Machine Learning - Computer Vision, - Artificial Inteledence, - Internet Of Things, - Natural Language Processing, - Image Processing, - Cyber Security, - Data Mining, - Game Development, - Digital Forensic, - Pattern Recognization, - Virtual & AUmented Reality,. - Cloud Computing, - Game Development, - Mobile Application, dan - Topik kajian lainnya yang relevan dengan ilmu teknik informatika.
Articles 104 Documents
Penerapan Model U-Net untuk Segmentasi Gigi pada Citra Radiografi Panoramik Orang Dewasa Sonia, Sonia; Yohannes, Yohannes
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 5 No 2 (2025): April 2025 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v5i2.10965

Abstract

Dental and oral health play a crucial role in maintaining overall bodily health. Panoramic radiography serves as a primary diagnostic tool for analyzing dental and oral conditions; however, the complexity of its images often complicates manual analysis. This study aims to implement a Convolutional Neural Network (CNN) architecture for segmenting panoramic radiographic images, utilizing U-Net as the chosen model. The dataset used consists of panoramic radiographic images. The test results indicate that the implemented model achieved an IoU score of 0.8335 and a dice coefficient of 0.9092, demonstrating strong segmentation capability. These findings suggest that the proposed method can serve as a supportive tool for diagnosis and treatment planning in dental and oral healthcare.
Energy Harvesting Berbasis Panel Surya untuk Keberlanjutan Daya Sensor IoT Prayitna, Adiyuda; Buwono, Robby Cokro
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 5 No 2 (2025): April 2025 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v5i2.10976

Abstract

The utilization of the Internet of Things (IoT) in the fields of environmental monitoring or precision agriculture is often constrained by power supply issues for wireless sensors. This study explores solar energy harvesting solutions as a standalone power source for IoT data logging systems. Through the analysis of solar energy production datasets, this study measures the conversion efficiency of solar panels, predicts daily energy availability, and tests their feasibility to meet the needs of energy-efficient wireless communication-based sensors.The results show that the conversion efficiency of solar panels is relatively stable despite being affected by external factors such as weather. The ARIMA model proved superior in predicting energy production with an MAE accuracy of 792,878.69 kWh, beating the linear regression approach. Simulation of the power demand of the IoT sensor (0.024 kWh/day) also confirmed that the energy produced by the solar panel (millions of kWh/day) far exceeds the operational demand. These findings prove that solar energy harvesting systems are feasible for IoT applications in remote locations, while opening up optimization opportunities through adaptive power management.
Understanding the Determinants of Continuance Intention for Banking Chatbots: A TCT Study Wirapraditya Ramdhani, Angga; Fangdinata, Felicia; Mandoyo, Joko
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 5 No 2 (2025): April 2025 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v5i2.11383

Abstract

The banking industry has witnessed tremendous changes in its structure within a short time frame due to scientific strides and the AI sector took it one step further, chatbots became an innovative trend. This research is to investigate the factors which may help determine continuance intention for banking chatbots in Indonesia using Technology Continuance Theory (TCT). The goal of this research is to close the knowledge gap regarding what motivates customers in continuous utilization after an initial adoption. This study carries out a survey of 153 bank customers and employs the Structural Equation Modeling (SEM) with the Partial Least Squares (PLS) technique to examine relationships among perceived usefulness, perceived ease of use, service quality, satisfactions, trust, confirmation of expectations on continuance intention. The findings reveal that these factors significantly influence the continuance intention of customers, providing valuable insights for banks to enhance their chatbot services and ensure sustained user engagement.
Restorasi Citra Wajah Terdegradasi Menggunakan Model GAN dan Fungsi Loss Wijaya, Beni; Haqiqi, Mokh. Mirza Etnisa; Satyawan, Arief Suryadi; Susilawati, Helfy
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 5 No 2 (2025): April 2025 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v5i2.11487

Abstract

This study develops a Generative Adversarial Network (GAN)-based model to restore partially degraded facial images by reconstructing missing regions while preserving the structural integrity of the face. The model adopts an encoder-decoder architecture enhanced with skip connections and residual blocks to improve restoration accuracy. The training process utilizes 1,000 paired images, comprising 500 original and 500 occluded facial images, with 200 images allocated for testing. The model was trained over 50 epochs, resulting in a consistent reduction of generator loss from 0.80 to 0.67 and stabilization of discriminator loss at 0.70. Qualitative evaluation indicates the model’s capability to reconstruct facial features such as eyes, nose, and mouth with high visual fidelity, although minor artifacts remain in areas with complex textures. These findings demonstrate the effectiveness of GAN-based approaches in facial image restoration and suggest potential improvements through the exploration of alternative network architectures and more diverse training datasets. The proposed model shows promise for applications in digital forensics and historical image recovery.
Optimisation of Erythrocyte Abnormality Classification using Watershed Segmentation Parahita, Syavina Octavia; Fitri, Zilvanhisna Emka; Imron, Arizal Mujibtamala Nanda
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 6 No 1 (2025): Oktober 2025 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v6i1.9580

Abstract

According to the World Health Organization (WHO), Polycythemia vera (PV) belongs to one of the main categories of Myeloproliferative Neoplasm (MPN). The results of laboratory diagnosis of PV are characterized by an increase in the number of erythrocytes, hemoglobin, leukocytes and platelets. Generally, blood examination uses automatic full blood count (FBC), but this method cannot detect abnormalities in the shape of erythrocytes, so further processing is needed from microscopic examination by creating a system that is able to detect and identify red blood cell abnormalities automatically. The system is a combination of digital image processing methods and intelligent systems methods commonly known as computer vision. The watershed segmentation method is used to separate closely packed cells, while the backpropagation method is an intelligent system capable of classifying erythrocyte shape abnormalities. The amount of data used is 340 training data and 50 test data, while the most optimal learning rate is 0.6 with a maximum epoh of 100 so that the system accuracy is 88%, specificity is 0.056 and sensitivity is 0.714.
Pengelompokkan Data Nilai Mahasiswa Menggunakan Metode K-Means Kusuma Putra, Rafli Danu; Palupi, Kinanthi Sekar; Wakhidah, Nur
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 6 No 1 (2025): Oktober 2025 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v6i1.10038

Abstract

Efficient and organized determination of student grades can help improve the quality of academic evaluation. In this research, the K-Means algorithm is used to cluster students based on academic grades. The K-Means algorithm is an unsupervised learning method often used to group data based on certain data The use of K-Means on student grade data aims to identify into several clusters based on similar characteristics so that students who have achievements can be identified. The implementation process involves the stages of data collection, data pre-processing, and data processing with Google Collaboratory platform using Python. The result showed that data grouping resulted in three clusters, namely students with low,medium, and high performance. The elbow method is used to determine the ideal number of clusters, and cluster quality is assessed by the silhouette coefficient. The best result showed a silhouette coefficient value of 0.458, indicating that the clusters formed were accurate. Thus, the K-Means algorithm is reliable for identifying students' academic performance.
Transfer Learning dengan MobileNetV2 untuk Klasifikasi Motif Jumputan Palembang Sahpira, Mulia; Yohannes, Yohannes
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 6 No 1 (2025): Oktober 2025 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v6i1.10998

Abstract

Palembang jumputan fabric is one of Indonesia's cultural heritages that is unique in its motifs and manufacturing techniques. However, the lack of public understanding of the meaning of motifs and competition with other traditional fabrics are challenges in its preservation. This research aims to develop a classification model of Palembang jumputan fabric motifs using the Convolutional Neural Network method with MobileNetV2 architecture and transfer learning approach. The dataset used consists of 800 images of four types of motifs, namely Bintik Tujuh, Pola, Tabur, and Terong. The data is divided into 80% training, 10% validation, and 10% testing. The model was trained using four types of optimisers, namely AdamW, Adagrad, Nadam, and SGD, with training parameters of 100 epochs, batch size 32, and learning rate 0.001. The test results showed that AdamW gave the highest accuracy of 97%, followed by Nadam 96%, Adagrad 95%, and SGD 90%. The model recognised the motifs well, especially the Bintik Tujuh and Tabur motifs which achieved 100% accuracy. With these results, artificial intelligence can be utilised to support the preservation of Palembang jumputan fabrics through motif recognition technology.
Klasifikasi Spesies Jamur Menggunakan Convolutional Neural Network dengan Arsitektur MobileNetV2 Hakiki, Muhammad Anugrah; Rachmat, Nur
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 6 No 1 (2025): Oktober 2025 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v6i1.11077

Abstract

Indonesia has a high biodiversity of fungi, including edible and toxic species. Manual identification is often challenging due to morphological similarities between safe and poisonous species. Therefore, this study evaluates the use of deep learning-based Convolutional Neural Network (CNN) with the MobileNetV2 architecture for mushroom classification. The research method includes collecting a dataset of 1,500 images from 10 mushroom species (5 edible and 5 toxic), preprocessing data by normalizing image size and applying augmentation techniques, and training the model using the Adam optimizer with dropout and early stopping to prevent overfitting. Hyperparameter tuning was performed using grid search on batch size (64, 128, 256), epochs (20, 50, 100), and learning rate (0.1, 0.01, 0.001). The test results show that a combination of batch size 64, epoch 50, and learning rate 0.1 achieved 98% validation accuracy. The final model was tested and achieved 95.33% accuracy, with an average precision, recall, and f1-score of 95%. These results confirm that MobileNetV2 is effective in classifying mushroom species and can assist in more accurately identifying edible and toxic fungi.
Analisis Implementasi Algoritma Genetika pada Penjadwalan Mata Kuliah Nasution, Mukhtada Billah; Utomo, Pradita Eko Prasetyo; Iftita, Hasanatul
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 6 No 1 (2025): Oktober 2025 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v6i1.11139

Abstract

Scheduling university courses is a complex challenge involving multiple variables, such as time allocation, room assignment, lecturer availability, and student requirements. This study explores the implementation of a genetic algorithm as a solution for generating optimal and efficient schedules. The genetic algorithm operates through the principles of selection, crossover, and mutation to progressively explore the solution space. Experiments were conducted using parameters of 50 individuals and 40 chromosomes, yielding an optimal schedule at the 124th iteration with a maximum fitness value (fitness = 1). The results indicate that the fitness value of individuals increases as generations progress, affirming the genetic algorithm's capability to achieve optimization iteratively. However, the stochastic nature of the algorithm leads to variations in the number of generations required to reach optimal results, influenced by the problem's complexity and the number of chromosomes. This study demonstrates that genetic algorithms are highly effective in solving complex scheduling problems with significant efficiency, producing solutions that meet constraints and support more structured operations. The algorithm contributes substantially to the development of automated scheduling systems in educational institutions and other sectors.
Analisis Keamanan Website J&T Cargo Kebumen Terhadap Serangan Brute force Menggunakan ISSAF Anam, Khoerul; Fachri, Fahmi
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 6 No 1 (2025): Oktober 2025 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v6i1.11148

Abstract

Keamanan siber menjadi aspek penting dalam pengelolaan Website, terutama dalam menghadapi ancaman serangan brute force. Website J&T Cargo Kebumen dipilih sebagai objek penelitian karena perannya dalam layanan logistik serta pentingnya menjaga integritas dan kerahasiaan data pengguna. Tujuan Penelitian ini untuk menganalisis potensi kerentanan Website terhadap serangan brute force. Penelitian ini menggunakan metode ISSAF (Information Systems Security Assessment Framework) mencakup tahapan Information Gathering, Network Mapping, Vulnerability Identification, dan Penetration Testing untuk mengidentifikasi kelemahan serta mengevaluasi efektivitas perlindungan yang ada. Hasil penelitian menunjukkan bahwa Website memiliki celah keamanan berupa tidak adanya mekanisme pembatasan percobaan login, autentikasi dua faktor (2FA), serta kebijakan kata sandi yang kuat. Simulasi serangan brute force yang dilakukan berhasil menemukan kombinasi kredensial yang valid, membuktikan adanya risiko akses tidak sah ke dalam sistem. Oleh karena itu, penelitian ini merekomendasikan penerapan langkah-langkah mitigasi seperti pembatasan percobaan login, peningkatan enkripsi data, serta implementasi kebijakan keamanan yang lebih ketat untuk meningkatkan ketahanan Website terhadap ancaman siber.

Page 9 of 11 | Total Record : 104