cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Arnawan Hasibuan
Contact Email
arnawan@unimal.ac.id
Phone
+62 812-6448-121
Journal Mail Official
arnawan@unimal.ac.id
Editorial Address
Faculty of Engineering, Universitas Malikussaleh Kampus Unimal Bukit Indah, Blang Pulo, Kec. Muara Satu Lhokseumawe
Location
Kota lhokseumawe,
Aceh
INDONESIA
Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Published by Universitas Malikussaleh
ISSN : -     EISSN : 26567520     DOI : -
Core Subject : Science, Engineering,
Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering
The "Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)" is a scientific publication that compiles innovative works from researchers, academics, and practitioners in the field of multidisciplinary engineering. This proceeding serves as a platform to present cutting-edge research, studies, and discoveries shared during the ICOMDEN forum, organized by the international engineering community. The proceedings cover a wide range of disciplines in engineering, including but not limited to: Mechanical Engineering, Civil Engineering, Electrical and Electronics Engineering, Computer Science and Software Engineering, Materials Engineering, Industrial Engineering, Environmental Engineering, and other related fields. Each paper published in this proceeding undergoes a rigorous peer-review process to ensure high scientific quality and impactful contributions. By integrating perspectives from various engineering disciplines, the proceedings aim to foster cross-disciplinary collaboration and provide innovative solutions to complex challenges in the field of engineering. The ICOMDEN Proceedings highlight research and technological advancements relevant to industry and society, promoting the application of sustainable engineering practices. This publication is intended to be a key reference for researchers, students, and engineering professionals to expand their knowledge and generate new ideas in addressing global challenges in engineering.
Arjuna Subject : Teknik (semua kategori) - Teknik (Lain-Lain)
Articles 119 Documents
 1   2   3   4   5 
Comparison of Exponentially Weighted Moving Average and Triple Exponential Smoothing Methods for Cryptocurrency Price Forecasting sukma rizki; Zarayunizar Zarayunizar; Said Fadlan Anshari
Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN) Vol. 2 (2024): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Publisher : Faculty of Engineering, Malikussaleh University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Cryptocurrencies have rapidly become a prominent part of today's information landscape. Bitcoin (BTC), one of the first cryptocurrencies, was introduced by Satoshi Nakamoto, a pseudonym whose true identity remains unknown. Nakamoto is credited with creating the blockchain system that underpins Bitcoin. As technology has advanced, cryptocurrencies have evolved into digital currencies that can be used as a medium of exchange. This has garnered significant attention from investors, particularly due to the substantial fluctuations in cryptocurrency values over time. Therefore, choosing the right method for making investment decisions is crucial. This research compares two leading methods for cryptocurrency price forecasting: Exponentially Weighted Moving Average (EWMA) and Triple Exponential Smoothing (TES). Each method has its own strengths and weaknesses in forecasting. In this study, EWMA achieved an average MAPE score of 54% and an MSE of 1818, while TES recorded an average MAPE of 45% and an MSE of 11408. The results indicate that TES outperforms EWMA by a margin of approximately 10%. To assess the methods' effectiveness, evaluation metrics were applied, categorizing performance as excellent, good, feasible, or not feasible.
Development of a Library Information Chatbot for Lampung University Based on Natural Language Processing Puput Budi Wintoro; Khairudin; Zulmiftah Huda; Rio Ariestia Pradipta
Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN) Vol. 2 (2024): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Publisher : Faculty of Engineering, Malikussaleh University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The University of Lampung (Unila) Library has over 86,783 registered patrons, with 12,329 active users, including faculty, students, staff, and external patrons. Services include verification, circulation, procurement, e-books, and journals. However, limited staff availability to respond to inquiries has negatively impacted service satisfaction. To address this issue, the implementation of chatbot technology is proposed as a solution. A chatbot simulates human conversation through text, voice, or visuals. There are two types: Flow-Based Chatbots, which follow a predetermined conversation flow, and Open-Ended Chatbots, capable of handling dynamic conversations. Development methods include Fixed Rule-Based and Machine Learning/Natural Language Processing (ML/NLP) Based Chatbots. This research aims to develop a Flow-Based Chatbot using ML/NLP on the Dialogflow platform, integrated with Unila Library's local database through a Python-based API, specifically FastAPI. The implementation of this chatbot is expected to enhance the responsiveness and availability of library services, ultimately increasing patron satisfaction.
Spammer Detection On Computer Networks Using Gaussian Naïve Bayes Classifier And K-Medoids As Acquisition Training Data OK Muhammad Majid Maulana Majid; Rizal Tjut Adek; Zara Yunizar
Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN) Vol. 2 (2024): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Publisher : Faculty of Engineering, Malikussaleh University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This research focuses on the implementation of the Gaussian Naïve Bayes algorithm for spammer detection in computer networks, leveraging K-Medoids clustering for training data acquisition. The increasing number of internet users, combined with the challenges of detecting spam activity on a network, has made manual detection ineffective. This study addresses the need for automated spam detection using machine learning algorithms. The Gaussian Naïve Bayes algorithm was chosen for its simplicity and effectiveness in handling continuous data, making it suitable for classifying network traffic as either normal or spammer. To acquire labeled training data, K-Medoids clustering was employed, offering robustness against outliers, which traditional clustering algorithms like K-Means often struggle with. The research involved collecting traffic data from a Mikrotik Routerboard at various intervals, followed by data preprocessing to remove irrelevant or null features. After preprocessing, the data was clustered using K-Medoids into two groups: spammer and normal. The Gaussian Naïve Bayes classifier was then applied to the clustered data, producing a model with high accuracy, precision, recall, and F1-score. Specifically, the model achieved 99.71% accuracy, 100% precision, 99.71% recall, and a 99.85% F1-score, indicating a well-balanced performance in spam detection. The results demonstrate that the Gaussian Naïve Bayes algorithm, combined with K-Medoids clustering, is effective for detecting spammers in computer networks. Future research could explore higher-layer network traffic and broader datasets, utilizing different routers for a more comprehensive evaluation. This approach provides a reliable solution for network administrators seeking to improve network security by detecting and mitigating spam activity.
Strategic Framework for Implementing Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) for Personalized AI in Informatics Engineering: A Case Study of Malikussaleh University Abil Khairi; Wahyu Fuadi; Yesy Afrillia
Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN) Vol. 2 (2024): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Publisher : Faculty of Engineering, Malikussaleh University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study develops a strategic framework for integrating Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) to support personalized Artificial Intelligence (AI) applications within the Informatics Engineering Department at Malikussaleh University. By utilizing localized datasets, the framework aims to enhance research productivity and improve educational outcomes while prioritizing data privacy and security. The study examines the opportunities and challenges associated with embedding these technologies into the university’s existing infrastructure, proposing a phased approach to adoption. Emphasis is placed on the modernization of academic practices through AI-driven tools that cater to local educational and research needs. The findings offer insights into implementing advanced AI systems that could serve as a model for similar educational settings focused on sustainable AI adoption.
Implementation Of Purity K-Means Algorithm In Accident Data Clustering In North Padang Lawas District Khopipah Parawansah Siregar; Bustami Bustami; Sujacka Retno
Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN) Vol. 2 (2024): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Publisher : Faculty of Engineering, Malikussaleh University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Traffic safety is an important issue, especially in areas with high accident rates, such as North Padang Lawas Regency in North Sumatra. This study uses the K-Means Purity Algorithm to group regions based on the level of vulnerability to traffic accidents. The data analyzed includes the number of accidents, deaths, serious injuries, and minor injuries from 2019 to 2023. The results of clustering show that some sub-districts have fluctuating levels of vulnerability. Batang Onang District, for example, was categorized as "Not Vulnerable" in 2019 and 2021, but increased to "Vulnerable" in 2020, 2022, and 2023, indicating a spike in risk. In contrast, Dolok District is mostly in the "Not Vulnerable" category, except in 2023. East Halongonan sub-district is almost always in the "Vulnerable" category, indicating a consistently high risk, while Hulu Sihapas and Simangambat experience fluctuations in vulnerability levels from year to year. Ujung Batu, which is generally classified as "Not Vulnerable," indicates an increased risk in certain years. In conclusion, the K-Means algorithm successfully maps accident-prone areas, providing important insights for more effective interventions. This information can help the government in designing better road safety strategies, such as infrastructure improvements and traffic safety awareness campaigns, to reduce future accidents. Keywords: Traffic Accidents, K-Means Purity Algorithm, Data Mining, North Padang Lawas, Accident Zoning
Comparative Analysis of K-Nearest Neighbor and Support Vector Machine Methods for Assessing Quality Standards of Palm Oil Bunches Siti Hajar; Rozi Kesuma Dinata; Maryana
Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN) Vol. 2 (2024): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Publisher : Faculty of Engineering, Malikussaleh University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Oil palm (Elaeis guineensis Jacq) is a crucial crop in the agricultural sector, particularly in Indonesia, as it produces various economically valuable products. The quality of oil palm fruit bunches (TBS) significantly influences the production process of crude palm oil (CPO), making accurate quality assessments essential for maintaining industry standards. This study aims to compare the effectiveness of two machine learning methods, K-Nearest Neighbor (K-NN) and Support Vector Machine (SVM), in determining the acceptable quality of TBS. Using TBS data from the years 2019 to 2023, the research analyzes several variables, including maturity level and yield percentage, to develop a web-based system for classifying TBS. The classification process involves preprocessing the data, applying the algorithms, and evaluating their performance based on key metrics such as accuracy, recall, and precision. The results indicate that the K-NN method outperforms SVM, achieving an accuracy of 100%, a recall of 100%, and a precision of 100%. In contrast, the SVM method demonstrates an accuracy of 91%, a recall of 100%, and a precision of 91%. These findings highlight the effectiveness of K-NN in classifying TBS quality while also demonstrating the reliability of SVM. This research is expected to provide valuable insights and effective solutions for decision-making regarding the acceptance of TBS quality, ultimately benefiting stakeholders in the palm oil industry and serving as a reference for future studies in data mining classification.
Implementation Of Support Vector Regression In Prediction Air Quakity Index In Banda Aceh City Rizky Fasya Ramdhani; Rozzi Kesuma Dinata; Ar Razi
Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN) Vol. 2 (2024): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Publisher : Faculty of Engineering, Malikussaleh University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Air quality is one of the important aspects in maintaining environmental balance and public health. Increasing air quality in the environment is a matter of concern. Therefore, a method that can predict the Air Quality Index (AQI) effectively is needed to be able to monitor and support decision making on environmental impacts. This study aims to predict the Air Quality Index in Banda Aceh City using the Support Vector Regression algorithm, with five main parameters used in the study, namely particulate matter , Sulfur dioxide, Nitrogen dioxide, Carbon monoxide , and Ozone . In this research, the Support Vector Regression algorithm was chosen because of its ability to handle non-linear data and also because it can provide accurate predictions on data. The prediction system designed will be web-based using the flask framework and MySQL database, while the Support Vector Regression modeling will be done on google colab for the media used. In the process of modeling the data will be divided into 80% training data and 20% test data to ensure the model can capture long and short-term patterns. The results of the prediction will be compared using the Root Mean Squarred Error (RMSE) and Mean Squarred Error (MSE) evaluation metrics. The results of the evaluation using both metrics yielded RMSE values of 1.9001 and MSE of 3.6015. These values indicate good performance of the model in predicting the data. This research is expected to provide insight for future similar research in terms of prediction using the Support Vector Regression algorithm.
Food Security Optimization Forecasting Fertilizer Production With Method Weighted Moving Average (WMA) Rifkial Iqwal; Dahlan Abdullah; Nunsina
Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN) Vol. 2 (2024): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Publisher : Faculty of Engineering, Malikussaleh University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This research focuses on optimizing food security through the application of fertilizer production forecasting method at PT Pupuk Iskandar Muda (PIM) using Weighted Moving Average (WMA). Effective food security relies heavily on stable and adequate fertilizer availability, which in turn requires accurate production predictions to ensure efficiency. In this study, historical data of urea and ammonia fertilizer production from January 2019 to December 2023 is used to build a forecasting model that can provide an overview of future production trends. The WMA method was chosen due to its adaptive nature, where greater weight is given to the most recent data, allowing the model to be more responsive to changes and emerging trends. The results showed that for urea production, WMA produced a MAPE value of 1773.8% and MAD of 13,223.2, while for ammonia production, the MAPE was recorded at 3085.5% with MAD of 7,538.5. Total production showed a MAPE of 69.7% with a MAD of 20,568.9, indicating significant fluctuations in production during the period under study. Nevertheless, the WMA method still provides a fairly good prediction and can be used as a reference in future production planning. In addition, the results of this study also provide valuable insights into the production dynamics at PIM, which is critical in supporting the national food security strategy. This research recommends further exploration of other more advanced forecasting methods, such as ARIMA or machine learning techniques, to improve prediction accuracy and better anticipate changes in production patterns. Keywords: Food security, Weighted Moving Average, Fertilizer Production Forecasting, MAPE, MAD.
Expert System for Diagnosing Bacterial Infections in Children Using the Dempster Shafer Method Naufal Yeza Ananda Yeza; Mukti Qamal; Zahratul Fitri; Ellya Nova Lubis
Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN) Vol. 2 (2024): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Publisher : Faculty of Engineering, Malikussaleh University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study seeks to apply the Dempster-Shafer Method within an expert system designed for diagnosing bacterial infections in children. Developed as an Android application, the system not only aids in identifying the type of bacterial infection based on observed symptoms but also improves efficiency regarding time and costs while enhancing parental awareness of various bacteria that could impact their children's health. Symptoms evaluated include fever, assigned a weight of 1, diarrhea (from mild to bloody) with a weight of 0.8, nausea and vomiting with a weight of 1, headaches with a weight of 0.8, and severe abdominal pain also weighted at 0.8. The Dempster-Shafer Method processes uncertain information through calculations based on symptom weights defined by pediatric health specialists. Results reveal that this method effectively supports the diagnosis of bacterial infections in children, yielding the highest probability values for Escherichia coli (P02) and Salmonella typhi (P03), calculated at 1.33 and subsequently rounded to 1.0, corresponding to 100%, thus offering a more precise and advantageous approach for medical decision-making.
The Implementation of Support Vector Machine to Analyze Compliance of Land and Building Taxpayers Nurul Nafisa; Rozi Kesuma Dinata; Rizki Suwanda
Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN) Vol. 2 (2024): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Publisher : Faculty of Engineering, Malikussaleh University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Land and Building Tax (LBT) is an important source of revenue for local governments, supporting development and community welfare. However, low taxpayer compliance rates often pose a challenge in achieving the targets for Local Own-Source Revenue (LOSR). This study aims to develop a data-driven classification system to map areas with varying levels of LBT taxpayer compliance in Lhokseumawe City and to implement the Support Vector Machine (SVM) method to improve the accuracy of predicting taxpayer compliance. The research data was obtained from the Regional Financial Management Agency (RFMA) of Lhokseumawe City, encompassing LBT data from 2021 to 2023, with variables such as principal amount, penalties, total payments, due dates, and payment dates. This classification system divides taxpayers into two categories: Compliant and Non-Compliant. The results of testing the SVM model indicate that Banda Sakti sub-district has a compliance rate of 98%, Muara Satu has a compliance rate of 99%, Muara Dua has a compliance rate of 99%, and Blang Mangat has a compliance rate of 100%. The accuracy metrics from the implementation of the Support Vector Machine method for assessing land and building tax compliance show a Precision of 86%, a Recall of 100%, and an Accuracy of 86%. By applying the SVM method, it is hoped that there will be an increase in efficiency in the tax collection and management processes, thereby optimally increasing Local Own-Source Revenue (LOSR) and supporting better regional development.

Page 2 of 12 | Total Record : 119

 1   2   3   4   5 

Filter by Year

2018 2024


Reset
Filter By Issues
All Issue Vol. 2 (2024): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN) Vol. 1 (2018): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)