JURNAL INFOTEL

Enhancing Museum Experience through Augmented Reality: The Case of the Indonesian Postal Museum

Alfian Akbar Gozali — 2024-05-08

This paper presents the development and implementation of Mussia AR, an interactive augmented reality (AR) application designed for the Indonesian Postal Museum. Aimed at enhancing the educational and engagement aspects of museum visits, this project addresses the need for innovative approaches in museum experiences. We followed an Extreme Programming methodology for the development, ensuring a user-centric and iterative approach. The application overlays digital information onto physical exhibits, providing visitors with an immersive and informative experience. Our development process included comprehensive user needs analysis, application design, implementation, and extensive testing for both functionality and user experience. The results from user testing indicate a significant improvement in visitor engagement and satisfaction. The application not only succeeded in providing an enhanced learning experience but also demonstrated the potential of AR technology in cultural and educational settings. Future recommendations include expanding the content, introducing multilingual support, and extending the application's compatibility to various platforms. Mussia AR stands as a testament to the effective use of AR in enriching educational experiences in museums.

An Approach to a Group Movie Recommender System using Matrix Factorization-based Collaborative Filtering

Faiha Adzra Darmawan — 2024-05-14

The growth of online movie streaming platforms has driven the demand for recommender systems that are able to deal with the daunting challenge of users finding movies that match their preferences. However, these recommender systems tend to focus on the needs of individual users, whereas in the real world, there are circumstances in which recommendations are needed for a group of users. Therefore, this study proposes a Group Recommender Systems (GRS) using Matrix Factorization (MF) with aggregation model to recommend movies for a group of users. We employ three Matrix Factorization methods to three distinct group sizes, which are small, medium, and large. Our goal is to identify the most effective approach for each group size. To evaluate the performance, we use precision and recall as measurement metrics. The results show that the MF method, After Factorization (AF) outperforms the other MF methods, i.e., Before Factorization (BF) and Weighted Bfore Factorization (WBF) in terms of precision parameters for small groups (2-4 users), which achieving a score of 0.86. Meanwhile, BF method surpassing both AF and WBF in precision parameters for medium groups (5-8 users) with a score of 0.81.

Development of Xiaomi Product Mobile Forensic Acquisition Framework on Second Space Features Based on SNI/ISO 27037:2014

Amru Rizal Fakhriansyah — 2024-05-08

Abstract — In conducting digital forensic activities, it must follow the rules of SOP procedures or frameworks as a reference. One of the acquisition frameworks used in digital forensics practice is ISO 27037:2014, which contains specific guidelines related to digital forensic investigation activities. On the other hand, mobile cellular is one of the branches of digital forensics that is always developing, but with the large variety of mobile devices today, ISO 27037: 2014 has not provided specific standards in the digital forensics process on mobile devices that have special features that are different from ordinary mobile devices. One of the special features provided by Xiaomi vendor developers that gives users access to cloning and creating new space in one mobile phone is called second space or second space. With this, it will be a problem for investigators when conducting forensic processes because the data acquisition process will produce 2 extraction results from one mobile device, but the SNI ISO 27037: 2014 standard has not regulated the validity of digital evidence obtained from these special features. This research will develop a framework in conducting the investigation process on Xiaomi mobile devices, because currently only Xiaomi mobile devices have a second room feature. By paying attention to the existing problems, this research will develop a framework in carrying out the acquisition process on xiaomi mobile devices on the special features of the second room based on SNI ISO 27037: 2014. It is hoped that this research can help investigators, especially DEFR (Digital Evidence First Responder) and can be a reference that can be used in the process of searching for electronic evidence that is in accordance with SNI ISO 27037: 2014 and can be accounted for in court.

A Semantic Segmentation of Nucleus and Cytoplasm in Pap-smear Images using Modified U-Net Architecture

Muhammad Arhami — 2024-05-08

Pap-smear images can help early detection of cervical cancer, but the manual interpretation by a pathologist can be time-consuming and prone to human error. Semantic segmentation of the cell nucleus and cytoplasm plays an essential role in Pap smear image analysis for the detection of cervical cancer automatically. This study proposes a modified U-Net architecture by adding batch normalization to each convolution layer. Batch normalization aims to stabilize and accelerate the convergence of the model during training, thus overcoming the vanishing gradient problem. The modified U-Net model achieves high accuracy and low loss during the training process, indicating its ability to learn and recognize patterns in the data. The performance evaluation of the model resulted in 91.4 % accuracy, 79.9 % sensitivity, 87.7 % specificity, 81.7 % F1-score, and 83.7 % precision. The results show that the proposed modification of U-Net architecture with batch normalization improves the segmentation performance for cervical cancer cells in Pap smear images. However, improvement in architecture is still required to increase the ability to overcome overlapping areas between the nucleus, cytoplasm, and background.

A Generic Model of Traffic Monitoring and Vehicle Counting Systems Based on Edge Computing

Hery Heryanto — 2024-05-08

One of the main issues in Indonesia is congestion. The number of vehicles continues to increase and is less balanced by the development of transportation infrastructure, especially landlines, causing more complex problems. The Indonesian government needs an intelligent application system that can provide knowledge to unravel congestion. The problem is how to perform edge computing to reduce latency so that the highway monitoring application system runs in real time. This research proposes a basic design for a vehicle monitoring application system that can accurately recognize vehicles, count the number of vehicles, and propose an edge computation that brings computation directly to the data source. The dataset is a video of traffic in Bandung, Jakarta, and several other major cities. The images in the dataset consist of 4,890 training images, 467 validation images, and 231 testing images. In the proposed model, the YOLOv5 and YOLOv7 architectures accurately detect and count vehicles. The test results show a mAP value of 99.1% with an IoU threshold of 50%. Other results include a precision value of 96.2% and a recall of 97.7%. The proposed model can accurately monitor vehicles and reduce latency with an edge computing approach.

Feature Extraction vs Fine-tuning for Cyber Intrusion Detection Model

Ahmad Sanmorino — 2024-05-13

This study investigates the effectiveness of feature extraction and fine-tuning approaches in developing robust cyber intrusion detection models using the Network-based Security Lab - KDD dataset (NSL-KDD). The role of cyber intrusion detection is pivotal in securing computer networks from unauthorized access and malicious activities. Feature extraction, involving methods such as PCA, LDA, and Autoencoders, aims to transform raw data into informative representations, while fine-tuning leverages pre-trained models for task-specific adaptation. The study follows a comprehensive research method encompassing data collection, preprocessing, model development, and experimental evaluation. Results indicate that LDA and Autoencoders excel in the feature extraction phase, demonstrating precision, high accuracy, F1-Score, and recall. However, fine-tuning a pre-trained Multilayer Perceptron model surpasses individual feature extraction methods, achieving superior performance across all metrics. The discussion emphasizes the complexity and flexibility of these approaches, with fine-tuned models showcasing higher adaptability. In conclusion, this study provides valuable insights into the comparative effectiveness of feature extraction and fine-tuning for cyber intrusion detection. The findings underscore the importance of leveraging pre-trained knowledge and adapting models to specific tasks, offering a foundation for further advancements in enhancing network security through advanced machine learning techniques.

Intelligent Traffic Light Time Cycle Simulation Model using Fuzzy Mamdani

Mulki Indana Zulfa — 2024-05-13

The growth of motorized vehicles in Indonesia has increased significantly. According to data from the Central Bureau of Statistics, the number of motorized vehicles in Indonesia has increased by around 10% each year in the last five years. One of the negative impacts of the increasing number of motorized vehicles is traffic congestion. Traffic congestion has become a serious problem in several cities in Indonesia. One of the causes is the increase in the number of vehicles at road intersections, which has an impact on congestion and the safety of road users. The rapid growth in the number of vehicles requires a more comprehensive strategy to reduce congestion and accidents at road intersections. Therefore, the need for Intelligent Transportation System, especially on the time-cycle configuration of intelligent red light is very important. This research aims to model the time-cycle of the red light using the Mamdani Fuzzy Inference System to simulate the green light time configuration so as to reduce the waiting time of road users at highway intersections. The simulation results show that the time-cycle configuration and green light time length of the Mamdani Fuzzy calculation are more varied relative to the number of vehicles. The values are relatively smaller than 6 to 54 seconds from the time configuration set by the local Department of Transportation. This shows a time efficiency for road users of up to 27%, which means that road users can complete trips 6 to 13 seconds faster.

An Integration of Real-Time Vehicle Routing and Mobile Technology in Poultry Distribution

Yulinda Uswatun Kasanah — 2024-05-13

Handling the distribution of broilers has special attention. The distribution of poultry should be done in the shortest possible time to decrease broiler mortality rate. Real-time monitoring of poultry distribution is expected to control the stress level of poultry due to the length of travel time by limiting the delivery time window. In order to control the distribution time and distance, it is necessary to integrate vehicle routing and mobile technology. By adopting the digital twin-enabled framework model and combining it with Google APIs, web and mobile applications are generated to accommodate the real-time traveling time, vehicle capacity, and pickup-delivery activity. There is a significant change in travel distance in one delivery cycle after implementing the developed technology. The total travel distance was 493 KM decreased to 436 KM, which means a decrease of 11.5% from the initial total travel distance. In addition, there was a change in the total penalty time (delay) from 102 minutes to 85 minutes, decreasing delay time by 16.6%. This mobile technology's development can indirectly increase vehicle utilization by not overloading the vehicle capacity and reducing vehicle travel distance.

In-Depth Exploration and Comparison of Machine Learning Performances for Early-Stage Diabetes Risk Prediction

Nor Kumalasari Caecar Pratiwi — 2024-05-14

Abstract — Diabetes mellitus is distinguished by an inability of the human system to produce insulin on an ongoing basis, as well as by the inefficient utilization of the insulin hormone, resulting in an elevated level of blood glucose. Global diabetes rates have nearly doubled since 1980, reaching 9.3% among adults. Alarmingly, of the 463 million individuals with diabetes, 50.1% are unaware of their condition. Indonesia ranks seventh globally with 10.7 million diabetes cases. In 2019, it was fifth globally for adults (20–79 years) with undiagnosed diabetes. This silent epidemic demands urgent attention and comprehensive strategies for early detection and management. In recent years, researchers have increasingly studied machine learning for early diabetes recognition. In this study, we aim to predict early-stage diabetes risk by utilizing 16 health condition features. We explore 12 distinct machine learning algorithms, applying a hyperparameter grid to tune each algorithm. This involves systematically testing combinations of hyperparameters to identify the optimal settings for achieving the most accurate and reliable predictive models. The results indicate that the Light GBM algorithm achieved the highest accuracy of 0.9692. By contrast, the logistic regression and Naive Bayes algorithms demonstrated the lowest performance, each with an accuracy of 0.8923. The implications of these results underline the capability of employing machine learning algorithms to precisely and effectively detect individuals susceptible to diabetes, enabling the implementation of individualized healthcare approaches.

A Systematic Review of Deep Learning for Intelligent Transportation Systems with Analysis and Perspectives

Aria Hendrawan — 2024-05-21

This study presents a systematic review of deep learning for intelligent transportation systems. Statistics are used to find the most cited articles, and the number of articles and quotes are used to find the most productive and influential authors, institutions, and countries or regions. Key topics and patterns of change are discovered using the authors’ keywords, and the most common issues and themes are revealed using flow maps and showing the corresponding trends. A co-occurrence keyword network is also developed to present the research landscape and hotspots in the field. The results explain how publications have changed over the past seven years. Researchers can use this study to have a deeper understanding of the current state and future trends in the role of deep learning in intelligent transportation systems.

Combination of Multi-Objective Optimization on The Basis of Ratio Analysis and ROC in The Selection of Extracurricular Activities

Dyah Ayu Megawaty — 2024-05-31

The selection of extracurricular activities for students often involves several challenges and problems. Some problems in the selection of extracurricular activities include limited time, interests and talents, limited facilities and infrastructure, and awareness of choices. Problems in the selection of extracurricular activities include limited time, interests and talents, limited facilities and infrastructure, and awareness of choices. The purpose of this study is to provide recommendations for a decision support system model for students in the selection of extracurricular activities by applying the ROC method as a method of weighting criteria and the MOORA method as an alternative ranking tool for extracurricular activities that become recommendations for students. The combination of MOORA and Rank Order Centroid (ROC) methods is an approach that can be used in complex multi-criteria decision analysis. This method combines the strengths of both methods to provide more comprehensive and effective solutions in decision-making. The results of the study on the selection of extracurricular activities using a combination of MOORA and ROC methods, recommendations for extracurricular activities for Futsal extracurricular activities with a value of 0.444 as recommendations based on the final calculation results with the MOORA method got rank 1, for rank 2 recommended extracurricular activities Basketball with a final value of 0.437, and rank 3 recommended extracurricular activities Karate with a final value of 0.426.

Combating Misinformation: Leveraging Deep Learning for Hoax Detection in Indonesian Political Social Media

Yuliant Sibaroni — 2024-05-31

The rampant spread of hoax news in social media, especially in the political domain, poses a significant challenge that requires immediate attention. To address this issue, automatic hoax news detection using machine learning-based artificial intelligence has emerged as a promising approach. With the approaching presidential election in Indonesia in 2024, the need for effective detection methods becomes even more pressing.This research focuses on proposing an efficient deep learning model for detecting political hoax news on Indonesian social media. Word2vec feature representation and three deep learning models – LSTM, CNN, and Hybrid CNN-LSTM – are evaluated to determine the most effective approach. Experimental results reveal that the CNN-LSTM hybrid model outperforms the others, achieving an accuracy of 96% in detecting hoax news on Indonesian social media in the political domain. By leveraging state-of-the-art deep learning techniques, particularly the CNN-LSTM hybrid model, this study contributes to the advancement of hoax news detection in Indonesia's political landscape. The findings underscore the importance of utilizing sophisticated machine learning methods to combat the spread of misinformation, particularly during crucial political events such as elections.

Identification of Evaluation Results in E-Banking Services Transaction for Product Recommendation using the BIRCH and Davies Bouldin Index Method

Septian Eka Ady Buananta — 2024-05-31

E-banking transaction services in the banking world include many products offered to customers. However, the existence of regulatory factors may limit the extent to which banks can promote e-banking services, especially in cases where promotions involve incentives or special offers. Besides, there is a need for data analysis that is used to help the process of recommending product promos from these services. Recommendations for this product promo can be known from the evaluation process of data collected from e-banking transaction services for purchases and payments. The clustering method suitable for providing significant and influential results compared to other methods is BIRCH, which is assisted by the Davies Bouldin Index method to determine the list of product groups with the lowest value. The results of this evaluation process show that data can be grouped based on which services have low levels of use. The services in question are Deposits, Credit Cards on Mobile Services, OVB, and Inter-Bank Transfers on Mobile Services. Therefore, this service can be used as a reference to increase product promotion by the bank.

Image Segmentation Performance using Deeplabv3+ with Resnet-50 on Autism Facial Classification

Melinda Melinda — 2024-05-31

In recent years, significant advancements in facial recognition technology have been marked by the prominent use of convolutional neural networks (CNN), particularly in identification applications. This study introduces a novel approach to face recognition by employing ResNet-50 in conjunction with the DeepLabV3 segmentation method. The primary focus of this research lies in the thorough analysis of ResNet-50's performance both without and with the integration of DeepLabV3+ segmentation, specifically in the context of datasets comprising faces of children on the autism spectrum (ASD). The utilization of DeepLabV3+ serves a dual purpose: firstly, to mitigate noise within the datasets, and secondly, to eliminate unnecessary features, ultimately enhancing overall accuracy. Initial results obtained from datasets without segmentation demonstrate a commendable accuracy of 83.7%. However, the integration of DeepLabV3+ yields a substantial improvement, with accuracy soaring to 85.9%. The success of DeepLabV3+ in effectively segmenting and reducing noise within the dataset underscores its pivotal role in refining facial recognition accuracy. In essence, this study underscores the pivotal role of DeepLabV3+ in the realm of facial recognition, showcasing its efficacy in reducing noise and eliminating extraneous features from datasets. The tangible outcome of increased accuracy of 85.9% post-segmentation lends credence to the assertion that DeepLabV3+ significantly contributes to refining the precision of facial recognition systems, particularly when dealing with datasets featuring faces of children on the autism spectrum.

A Bandwidth and Gain Enhanced Hexagonal Patch Antenna using Hexagonal Shape SRR

Harfan Hian Ryanu — 2024-05-08

In the evolving digital era, the primary focus of the telecommunications industry is on the 5G network, expected to deliver high data rates, low latency, large network capacity, and improved connectivity. This article discusses efforts to adopt optimal frequencies for 5G, introducing techniques to enhance the characteristics of microstrip antennas using Double Negative (DNG) metamaterial properties. The hexagonal-shaped Split Ring Resonant (HSRR) metamaterial is considered a potential method to increase the bandwidth and gain of 5G antennas. Simulation of HSRR unit cells shows a positive impact on DNG characteristics. Meanwhile, the antenna design incorporating HSRR superstrate elements significantly increases gain to 4.47 dBi, and the implementation of HSRR structures on the groundplane results in a remarkable 368% increase in bandwidth compared to conventional antennas without metamaterial.