Engineering, MAthematics and Computer Science Journal (EMACS)

American Sign Language Translation to Display the Text (Subtitles) using a Convolutional Neural Network

Muhammad Fajar Ramadhan — 2024-09-22

Sign language is a harmonious combination of hand gestures, postures, and facial expressions. One of the most used and also the most researched Sign Language is American Sign Language (ASL) because it is easier to implement and also more common to apply on a daily basic. More and more research related to American Sign Language aims to make it easier for the speech impaired to communicate with other normal people. Now, American Sign Language research is starting to refer to the vision of computers so that everyone in the world can easily understand American Sign Language through machine learning. Technology continues to develop sign language translation, especially American Sign Language using the Convolutional Neural Network. This study uses the Densenet201 and DenseNet201 PyTorch architectures to translate American Sign Language, then display the translation into written form on a monitor screen. There are 4 comparisons of data splits, namely 90:10, 80:20, 70:30, and 60:30. The results showed the best results on DenseNet201 PyTorch in the train-test dataset comparison of 70:30 with an accuracy of 0.99732, precision of 0.99737, recall (sensitivity) of 0.99732, specificity of 0.99990, F1-score of 0.99731, and error of 0.00268. The results of the translation of American Sign Language into written form were successfully carried out by performance evaluation using ROUGE-1 and ROUGE-L resulting in a precision of 0.14286, Recall (sensitivity) 0.14286, and F1-score.

Integration of QFD, HOQ, Taguchi, and Kansei Engineering for Smart Desk Lamp Design

Maranatha Barus — 2024-09-24

This research focuses on the analysis of smart desk lamps. To the authors’ knowledge, there is no previous study about Voice of Customer regarding smart desk lamps in Indonesia, to know the requirements for a smart desk lamp from Indonesian customer using the QFD and House of Quality (HOQ) The overall value of the interaction matrix with HOQ, the relative weight results for each customer and functional requirements are obtained. The highest technical requirement from HOQ is automatic on/off. The Taguchi method is to find out the best design for each Kansei Engineering that has been created. The Kansei Engineering that have been created are easy to use, adjustable lamp, affordable price, modern design, hi-tech. Each Kansei Engineering produces the required design according to the S/N Ratio (signal to noise ratio). Based on the QFD questionnaire and design using Kansei Engineering, one best design was obtained, namely hi-tech. The design consists of 3 parts, namely the top, middle and bottom. At the top, the slim rectangular shape is preferable with lights position in the middle. Pole position is round, upright position. At the bottom, it has a circular shape.

Overcoming Overfitting in CNN Models for Potato Disease Classification Using Data Augmentation

Simeon Yuda Prasetyo — 2024-09-30

Classification of diseases in potato plants is crucial for agriculture to ensure quality and yield. Potatoes, being staple foods worldwide, are vulnerable to diseases that cause significant production losses. Early and accurate disease identification is essential. This study evaluates the impact of data augmentation on reducing overfitting in deep learning models for potato disease classification. Various CNN architectures, including VGG16, VGG19, Xception, and InceptionV3, were compared in transfer learning and fine-tuning phases. The "Potato Disease Dataset", consisting of 451 images across seven classes, was used. The dataset was split into training, validation, and test sets, and augmentation increased the training set from 360 to 2160 images. The results indicate that models trained with augmented data exhibited improved performance in terms of accuracy, precision, recall, and F1-scores compared to those trained without augmentation. The learning curves show that data augmentation helps in reducing overfitting and enhancing model stability. Data augmentation is crucial for developing robust deep learning models for potato disease classification. Future work will explore advanced augmentation techniques and other architectures to enhance model performance.

Effective Approaches for User Engagement Improvement in Mobile Health Applications: A Comprehensive Literature Analysis

Samuel Philip — 2024-09-30

Mobile health (mHealth) applications have become an integral part of our existence, offering multiple functions and a new level of user engagement. However, the competitive market presents difficulties for development teams attempting to attract and retain customers. User engagement is crucial to the success of mHealth applications, as it promotes interaction, adherence, and behavior modification. This paper presents a systematic literature review in order to investigate methods for enhancing user engagement in mHealth applications. The review identifies successful strategies from existing research and seeks to provide developers with guidance for creating engaging mobile applications. The selected studies are subjected to systematic searching, screening, data extraction, and quality evaluation, followed by narrative synthesis and thematic analysis. The findings emphasize the importance of gamification, design, personalization, social media integration, and push notifications in boosting user engagement. The review also emphasizes the need for experimental research to evaluate the efficacy of different user engagement strategies to achieve more accurate and reliable results. By addressing gaps and employing effective engagement strategies, mHealth applications can increase user satisfaction, encourage continued use, and improve health outcomes. The study lays the groundwork for future research and makes suggestions for designing strategies to increase user engagement in mHealth applications

Web Based Application Development for Creating Collaborative Project Using NodeJs

Muhammad Danaparamita — 2024-09-30

In an era marked by rapid technological advancements, the ease of accessing information has unlocked unprecedented opportunities for individuals to realize their aspirations. However, the mere acquisition of knowledge or technical skills does not always lead to success or recognition, particularly when striving to create something truly remarkable. The success story of The Beatles serves as a prime example of how collaboration can amplify individual talents and lead to extraordinary achievements. The band’s collective effort demonstrates that co-creation among individuals can produce results far greater than the sum of its parts. With the rise of digital connectivity, collaborative efforts have become more accessible than ever before. Advances in technology have bridged physical distances, allowing for global teamwork that transcends geographic barriers. Despite these advancements, successful collaboration hinges on building trust, which is often nurtured through transparency. Transparent communication fosters a culture of honesty, openness, and mutual respect, which, in turn, strengthens trust among collaborators. To address the need for enhanced collaboration in creative and technical projects, this paper proposes the development of a web-based application platform. The goal of this platform is to streamline the collaborative process and facilitate the collaborative process and improve outcomes. The results indicate that the platform effectively supports users in initiating projects with multiple collaborators by connecting them with others who share similar goals. Additionally, the platform fosters trust between project creators and potential members through its transparent display of project details.

Simulation Techniques in Sugarcane Transportation Model Using R Programming Language

I Gusti Agung Anom Yudistira — 2024-09-30

The R programming language is generally known for its strength in Monte Carlo simulations, and numerical computing. This study will try to utilize R for discrete event simulations, namely in transportation systems, especially sugarcane transportation. The purpose of this paper is to study the performance of the sugarcane transportation system from the plantation to the factory, by utilizing the R programming language. The things that will be studied are to obtain changes in the system parameters so that more optimal performance is obtained. These parameters include the time required for the sugarcane to be in the transportation system, the length of the sugarcane pile in the plantation before being transported, the amount of resources needed for all transportation activities (loading, transporting and unloading), the number of transport equipment, loading equipment and unloading equipment needed, so that the harvest target is met and the waiting time for the sugarcane to be milled is as minimal as possible. As well as the level of utility of all resources provided in the system. The stages in this study include 1) literature review, 2) describing the sugarcane transportation system, 3) building assumptions and system constraints, 4) designing the transportation system conceptually, 5) developing programming code, 6) model testing/verification, 7) model validation, and 8) conducting experiments on the model. The results of the analysis of the model output indicate that the “open source R” programming language can be effectively applied to model the sugarcane transportation system.

Machine Learning-Based Malicious Website Detection Using Logistic Regression Algorithm

Puan Bening Pastika — 2024-09-30

Cybercrime is an increasing threat that occurs while exploring the internet. Cybercrime is committed by cybercriminals who exploit the web's vulnerability by inserting malicious software to access systems that belong to web service users. It is detrimental to users, therefore detecting malicious websites is necessary to minimize cybercrime. This research aims to improve the effectiveness of detecting malicious websites by applying the Logistic Regression algorithm. The selection of Logistic Regression is based on its ability to perform binary classification, which is important for distinguishing between benign and potentially malicious websites. This research emphasizes a preprocessing stage that has been deeply optimized. Data cleaning, dataset balancing, and feature mapping are enhanced to improve detection accuracy. Hybrid sampling addresses data imbalance, ensuring the model is trained with representative data from both classes. Experimental results show that the Logistic Regression implementation achieves an excellent level of accuracy. The developed model recorded an accuracy of 92.60% without cross-validation, which increased to 92.71% with 5-fold cross-validation. The novelty of this research lies in the significant increase in accuracy compared to previous methods, demonstrating the potential to improve protection against malicious website threats in an increasingly complex and risky digital environment. This research makes an important contribution to the development of digital security detection technologies to address the ever-growing challenges of cybercrime.

Building Customer and Product Networks with Cosine Similarity in Graph Analytics for Deep Customer Insight

Aan Albone — 2024-09-30

The goal of social networks is to establish a link that facilitates information sharing and product recommendations between users. For the purpose of comprehending and evaluating links, relationships, and networks, graph theory is indispensable. Our customer network allows us to engage current customers with more products from similar customers and recommend products from one customer to another that are connected by a cosine similarity to the 70% above. If the price of a product is higher than that of comparable products, we can observe the demand for that product in the product network.

Editorial Page and Table of Content

Alexander Agung Santoso Gunawan — 2024-09-22