cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Syahroni Hidayat
Contact Email
jtim.sekawan@gmail.com
Phone
-
Journal Mail Official
jtim.sekawan@gmail.com
Editorial Address
Jl. Bandeng No.25, Bintaro, Kec. Ampenan, Kota Mataram, Nusa Tenggara Bar. 83511
Location
Kota mataram,
Nusa tenggara barat
INDONESIA
Jurnal Teknologi Informasi dan Multimedia
Published by Puslitbang Sekawan Institute Nusa Tenggara
ISSN : 27152529     EISSN : 26849151     DOI : https://doi.org/10.35746/jtim.v2i1
Core Subject : Science,
Computer Science & IT
Cakupan dan ruang lingkup JTIM terdiri dari Databases System, Data Mining/Web Mining, Datawarehouse, Artificial Integelence, Business Integelence, Cloud & Grid Computing, Decision Support System, Human Computer & Interaction, Mobile Computing & Application, E-System, Machine Learning, Deep Learning, Information Retrievel (IR), Computer Network & Security, Multimedia System, Sistem Informasi, Sistem Informasi Geografis (GIS), Sistem Informasi Akuntansi, Database Security, Network Security, Fuzzy Logic, Expert System, Image Processing, Computer Graphic, Computer Vision, Semantic Web, Animation dan lainnya yang serumpun dengan Teknologi Informasi dan Multimedia.
Arjuna Subject : -
Articles 275 Documents
 24   25   26   27   28 
Deteksi Malware pada Perangkat Android Menggunakan Ensemble Learning Muhamad Azwar; Lilik Widyawati; Raisul Azhar; Kartarina Kartarina; Tanwir Tanwir; Andi Sofyan Anas
Jurnal Teknologi Informasi dan Multimedia Vol. 7 No. 3 (2025): August
Publisher : Sekawan Institut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v7i3.573

Abstract

The increasing use of permission-based applications on mobile platforms has raised concerns regarding privacy and security. Android, being one of the most widely used operating systems for interacting with mobile applications, is particularly susceptible to various security risks that must be promptly addressed. Low digital literacy and a lack of user awareness about security risks—especially when installing applications from unofficial sources or without paying attention to access permissions—make users vulnerable to malware attacks. Uninformed users can easily become victims of malware insertion by irresponsible parties, turning them into targets for data manipulation and even data theft, which may then be sold on illegal forums. Attackers exploit the permission system, allowing them to freely access the target smartphone. This lack of awareness among users increases their vulnerability to malware injection and subsequent threats such as data manipulation and the theft of personal information, which can be traded on underground markets. One approach to detecting malicious behavior in mobile applications is the use of machine learning techniques. These techniques can analyze application patterns and behaviors based on features such as requested permissions. Popular algorithms for malware detection include Support Vector Machine (SVM) and Random Forest (RF), both of which have demonstrated strong performance in various studies. However, to further improve accuracy and reduce classification errors, ensemble learning approaches such as Adaptive Boosting (AdaBoost) are increasingly being adopted. Ensemble learning combines multiple predictive models to produce more reliable classification results compared to single models. This study evaluates the performance of several classification algorithms in detecting malicious Android applications. The results show that AdaBoost achieved a high accuracy rate of 91.65% and an AUC value of 95%, effectively distinguishing between safe applications and malware. Therefore, the use of machine learning algorithms—particularly ensemble methods like AdaBoost—can serve as a promising solution to enhance the security and privacy of Android-based mobile application users.
Smart Traffic untuk Menghitung Volume Kendaraan dan Klasifikasi Kondisi Lalu Lintas Menggunakan Model YOLOv7 Kurniadin Abd Latif; Putri Tanisa Utami; Apriani Apriani; Fatimatuzzahra Fatimatuzzahra; Ria Rismayati
Jurnal Teknologi Informasi dan Multimedia Vol. 7 No. 2 (2025): May
Publisher : Sekawan Institut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v7i2.667

Abstract

One of the most complex challenges in urban management, particularly in developing countries, is traffic control. Traffic congestion has become a global issue, significantly affecting mobility, economic productivity, and quality of life. To address this problem, smart traffic systems are increasingly being adopted as adaptive and efficient solutions. This study aims to implement the You Only Look Once version 7 (YOLOv7) object detection model within a smart traffic system to calculate vehicle volume and monitor traffic conditions in real time. YOLOv7 is chosen for its high object detection accuracy, even in dynamic and complex environments where objects are fast-moving or overlapping in dense backgrounds. The methodology involves processing a 2-minute-30-second CCTV video recording taken from a street in New York City. Vehicle detection is conducted by applying bounding boxes over specific areas within the video frames, which serve as virtual counters for vehicles passing through. The experimental results demonstrate that the system effectively counts vehicles per second and identifies traffic conditions, which in this case remained smooth throughout the observation period. These findings highlight the potential of implementing YOLOv7 in smart traffic systems to support data-driven, automated, and real-time traffic management.
Media Pembelajaran Peralatan Servis Sepeda Motor dengan Menerapkan Teknologi Augmented Reality Miftahul Madani; Melati Rosanensi
Jurnal Teknologi Informasi dan Multimedia Vol. 7 No. 2 (2025): May
Publisher : Sekawan Institut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v7i2.682

Abstract

Learning media is one of the key components in the educational process. Teachers need to pay special attention to the use of learning media during teaching and learning activities. However, a lack of variety and suboptimal utilization of learning media often causes students to lose interest in learning. In fact, learning media aim to serve as tools to enhance the effectiveness of the learning process. Learning media are available in various forms, one of which is printed media or verbal explanation-based methods that are widely used in schools. This type of media is chosen for its practicality, adaptability to students' abilities, and ease of distribution. However, printed media have limitations, such as the inability to present elements like sound, animation, or three-dimensional objects. This study employs the Multimedia Development Life Cycle (MDLC) method, which consists of six stages: Concept, Design, Material Collection, Assembly, Testing, and Distribution. The final product of this research is an application in ".apk" format that can be installed on Android devices. Augmented reality is a term used to describe various types of display technology that can add or integrate information in the form of text, symbols or graphics into the user's view of the real world, this application utilizes Augmented Reality technology to introduce motorcycle service tools, helping vocational high school (SMK) students acquire basic skills and access information via their smartphones. User testing using the Likert Scale resulted in a score of 33.46, which falls into the "Strongly Agree" category.
Studi Pemodelan dan Prediksi Aktivitas Antibakteri Biopo-limer Kitosan Menggunakan Response Surface Methodology (RSM) Halil Akhyar; Selvira Anandia Intan Maulidya; Muhammad Mukaddam Alaydrus; Maz Isa Ansyori; Mohammad Zaenuddin Hamidi; I Gede Pasek Suta Wijaya; Ramaditia Dwiyansaputra; Pahrul Irfan
Jurnal Teknologi Informasi dan Multimedia Vol. 7 No. 2 (2025): May
Publisher : Sekawan Institut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v7i2.713

Abstract

Infections occured in the human are mostly caused by uncontrolled growth of Staphylococcus aureus bacteria. A strategy to inhibit bacterial growth can use antibacterial agents such as chitosan. The mechanism of the effectiveness of chitosan as an antibacterial is quite complex, even the data on its antibacterial activity is quite fluctuating so that it is difficult to analyze accurately and efficiently. Therefore, the purpose of the study was to predict the inhibition zone of s.aureus bacteria through laboratory experiments combined with modeling using the Central Composite Design (CCD) approach. The research was carried out with two main stages, including chitosan isolation and calculation of bacterial inhibition zones. The production of chitosan leverages the microwave isolation and FTIR to examine for the degree of deacetylation and its functional group using. Furthermore, the antibacterial activity of chitosan biopolymer was tested using the diffusion method combined with modeling using the RSM CCD approach. The results showed that chitosam from oyster shell was obtained by DD of 83.29% and the emergence of typical chitosan groups, such as amine (NH2) and hydroxyl (OH). Chitosan can hamper the growth of s. aureus bacteria with an inhibition zone of up to 0.40 mm. The experimental data were combined with computational modeling obtained the values of the determination coefficient R2 = 0.6083. The modeling was assessed by p-value of < 0.0001 and F-value of 13.46. Statistically, the obtained model is relevant to the relationship between the number of bacterial colonies and the concentration of chitosan solution with the bacterial inhibition zone. Based on numerical analysis and modeling, the predicted values of the number of s. aureus bacterial colonies and chitosan concentrations were 550,000 CFU/ml and 42.5%. Therefore, Pearl shells can be isolated into chitosan, as well as chitosan has the potential to be a good antibacterial agent. The model has good prediction performance, but it rquires to increase the number of point spreads and it is necessary to validate the prediction results to obtain actual predictions.
Penerapan Metode K-Nearest Neighbor Untuk Prediksi Jumlah Kasus HIV di Provinsi Jawa Barat Muhammad Adam Rizky Habibi; Shofa Shofia Hilabi; Bayu Priyatna; Elfina Novalia
Jurnal Teknologi Informasi dan Multimedia Vol. 7 No. 2 (2025): May
Publisher : Sekawan Institut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v7i2.721

Abstract

The high number of HIV/AIDS cases in Indonesia, especially in West Java Province, is a serious challenge in the field of public health. Limitations in understanding the pattern of spread and predicting the trend of HIV cases cause countermeasures to be less than optimal. To overcome this, this study was conducted with the aim of predicting the number of HIV cases in West Java using the K-Nearest Neighbor (KNN) algorithm, based on historical data from Open Data Jabar from 2019 to 2023 which includes 1,617 data from various districts / cities. The research stages include data collection, preprocessing, feature selection, normalization, division of training and test data, and model evaluation using regression metrics: Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²). The evaluation results show that the KNN model with an optimal K value of 19 produces an MAE of 142.31, MSE of 40,442.92, RMSE of 201.10, and R² value of 0.2397. Predictions for 2024 show that areas with the highest number of HIV cases are in Bandung City, Bogor Regency, Bekasi City, Bekasi Regency, and Indramayu Regency.
Segmentasi Hotel di Lombok Menggunakan Metode Klasterisasi Berbasis Harga, Fasilitas, dan Jarak Lokasi Eldy Waliyamursida; Dadang Priyanto; Galih Hendro Martono
Jurnal Teknologi Informasi dan Multimedia Vol. 7 No. 3 (2025): August
Publisher : Sekawan Institut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v7i3.722

Abstract

Lombok is one of Indonesia's premier tourist destinations, experiencing significant growth in the tourism sector. The increasing number of visitors has directly impacted the hospitality industry, resulting in a wide variety of hotels with diverse characteristics based on price, rating, and customer reviews. This diversity poses a challenge in effectively understanding hotel market segmentation. This study aims to cluster hotels in Lombok using clustering techniques to gain deeper insights into hotel segmentation patterns. The research employs the K-Means Clustering algorithm within the CRISP-DM framework, which includes the phases of Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment. The dataset comprises attributes such as nightly price, hotel rating, and the number of reviews, all collected from online platforms. The effectiveness of the clustering process is evaluated using the Silhouette Score metric. The results show that the K-Means algorithm delivers the best performance, with a Silhouette Score of 0.9042 (90%), indicating well-defined and distinct clusters. Therefore, K-Means Clustering is recommended as the most effective method for grouping hotels based on the attributes used in this study. This research provides valuable insights into hotel segmentation patterns in Lombok and can serve as a reference for hospitality industry stakeholders in formulating more targeted marketing strategies and business decisions. Future research may consider incorporating additional attributes such as geographic location and tourist seasons to enhance the clustering quality.
Prediksi Cuaca Berdasarkan Variasi miliVolt Xylem Lannea coromandelica Menggunakan Model Artificial Neural Network Backpropagation Iskandar Iskandar; Stella Elizabeth Warokka
Jurnal Teknologi Informasi dan Multimedia Vol. 7 No. 3 (2025): August
Publisher : Sekawan Institut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v7i3.727

Abstract

The rate of fluid flow in tree xylem generates an electrical potential difference (mV), which serves as a physiological indicator for monitoring plant conditions and predicting weather. This study aimed to develop a regression model based on Artificial Neural Network Backpropagation (ANN-BP) to estimate weather parameters from mV data of Lannea coromandelica. Electrical potential data were collected continuously for seven days using xylem-mounted sensors and synchronized with actual weather data, including air temperature, relative humidity, and light intensity. ANN-BP models employing three training algorithms (traingdx, traincgb, and traingd) were compared using mean squared error (MSE) as the evaluation metric. The traincgb algorithm achieved the best performance with an MSE of 3.29 × 10??. These findings demonstrate that variations in xylem electrical potential can reliably predict weather conditions in real time, supporting the development of an energy-efficient, biologically based weather monitoring system for precision agriculture and climate change mitigation.
Comparison of Social Media Between Tiktok and Instagram to Detect Negative Content Using Natural Language Processing Method Tri Antaka Jagad Laga; Nur Widjiyati
Jurnal Teknologi Informasi dan Multimedia Vol. 7 No. 3 (2025): August
Publisher : Sekawan Institut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v7i3.730

Abstract

In the digital era, social media platforms have become essential tools for communication, content creation, and information dissemination. However, with the increasing volume of user-generated content, the spread of negative or harmful content has emerged as a major challenge for platform administrators and users alike. This study aims to compare TikTok and Instagram in their capacity to detect and manage negative content using Natural Language Processing (NLP) techniques. A dataset of 2,000 user comments was collected—1,000 from each platform—through web scraping. These comments were analyzed using a variety of NLP methods, including sentiment analysis tools (VADER and TextBlob), text classification algorithms (Support Vector Machine and Random Forest), and Named Entity Recognition (NER) using the spaCy library. The comparison was conducted based on the classification performance of each NLP technique in detecting negative content, considering metrics such as accuracy, precision, recall, and F1-score. The results showed that while both SVM and Random Forest performed well in classification tasks, SVM outperformed the others in terms of overall accuracy and consistency across platforms. Sentiment analysis provided a general overview of content polarity, but it was less effective in detecting nuanced or sarcastic language. NER contributed to identifying specific entities that may be associated with negative expressions, enriching the contextual understanding of comments. This study highlights the potential of combining multiple NLP methods to improve automated content moderation systems. It also underlines the importance of platform-specific characteristics, such as user behavior and engagement style, which influence the nature and frequency of negative content. Future work should focus on improving the handling of contextual ambiguity and sarcasm to ensure more robust and adaptive moderation technologies across different social media platforms.
Prediksi Beban Kerja Server Secara Real-Time pada Pusat Data Cloud dengan Pendekatan Gabungan Long Short-Term Memory (LSTM) dan Fuzzy Logic Naufal Hanif; Dadang Priyanto; Neny Sulistianingsih
Jurnal Teknologi Informasi dan Multimedia Vol. 7 No. 3 (2025): August
Publisher : Sekawan Institut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v7i3.731

Abstract

Efficient resource management in Cloud Data Centers is essential to reduce energy waste and maintain optimal system performance. This study aims to predict server workload in real time using a hybrid approach that combines Long Short-Term Memory (LSTM) and Fuzzy Logic. CPU and RAM usage data were collected every second from a Proxmox Cluster using its API, then normalized and processed using an LSTM model to forecast future workloads. The predicted results were then classified using Fuzzy Logic into three workload categories: light, medium, and heavy. The model was evaluated using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE), where the results showed an MAE of 2.48 on the training data and 3.09 on the testing data, as well as RMSE values of 5.15 and 5.57, respectively. Based on these evaluation results, the prediction system achieved an accuracy of 97.52% on the training data and 96.91% on the testing data, indicating that the model can generate accurate and stable predictions. This method enables automated decision-making such as workload-based power management, thereby improving energy efficiency and overall system performance.
Implementasi Arsitektur Deep Convolutional Neural Network (CNN) dengan Transfer Learning untuk Klasifikasi Penyakit Kulit I Putu Agus; Khasnur Hidjah; Neny Sulistianingsih; Galih Hendro; Syahrir Syahrir
Jurnal Teknologi Informasi dan Multimedia Vol. 7 No. 3 (2025): August
Publisher : Sekawan Institut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v7i3.734

Abstract

Skin diseases are common health problems that require early diagnosis to prevent serious complications. This study aims to develop an automatic skin disease image classification system using a transfer learning approach based on Convolutional Neural Networks (CNN). Image datasets were obtained from Kaggle and underwent preprocessing stages including resizing, normalization, and augmentation. Four CNN architectures were evaluated: VGG16, ResNet50, MobileNetV2, and InceptionV3, implemented using Python and the Keras library on the Google Colab platform. The dataset was split into three training and testing ratios (90:10, 80:20, and 70:30) to assess the impact of data proportion on model performance. Models were trained by modifying the output layer to match the number of classes, and evaluated using accuracy, precision, recall, F1-score, confusion matrix, and ROC curve metrics. The results show that a 70:30 ratio yielded the most optimal training performance. InceptionV3 achieved the highest validation accuracy at 80.04%, but experienced overfitting, while VGG16 demonstrated better generalization to test data. This study proves that transfer learning with CNN is effective in improving the accuracy of automatic skin disease diagnosis and has the potential to become an efficient diagnostic solution, especially in areas with limited medical infrastructure.

Page 26 of 28 | Total Record : 275

 24   25   26   27   28 

Filter by Year

2019 2025


Reset
Filter By Issues
All Issue Vol. 7 No. 4 (2025): November Vol. 7 No. 3 (2025): August Vol. 7 No. 2 (2025): May Vol. 7 No. 1 (2025): February Vol. 6 No. 3 (2024): November Vol. 6 No. 2 (2024): August Vol 6 No 1 (2024): May Vol. 6 No. 1 (2024): May Vol. 5 No. 4 (2024): February Vol 5 No 4 (2024): February Vol. 5 No. 3 (2023): November Vol 5 No 3 (2023): November Vol. 5 No. 2 (2023): August Vol 5 No 1 (2023): May Vol. 5 No. 1 (2023): May Vol. 4 No. 4 (2023): February Vol 4 No 4 (2023): February Vol 4 No 3 (2022): November Vol 4 No 2 (2022): Agustus Vol. 4 No. 1 (2022): May Vol 4 No 1 (2022): May Vol 3 No 4 (2022): February Vol 3 No 3 (2021): November Vol 3 No 2 (2021): August Vol. 3 No. 2 (2021): August Vol 3 No 1 (2021): May Vol. 2 No. 4 (2021): February Vol 2 No 4 (2021): February Vol 2 No 3 (2020): November Vol 2 No 2 (2020): August Vol 2 No 1 (2020): May Vol 1 No 4 (2020): February Vol 1 No 3 (2019): November Vol 1 No 2 (2019): August Vol 1 No 1 (2019): May More Issue