Page 1 (data 1 to 30 of 256) | Displayed ini 30 data/page
1 2 3 4 5 6 7 8 9 NEXT >>

1	Artificial Intelligence (AI)	ABS-3
COMPARISON BETWEEN PCA-SVM WITH PSO-SVM FOR RECOGNIZE EMG SIGNAL Daniel S Pamungkas and Sumatri K Risandriya Politeknik Negeri Batam Abstract The comparison between Support Vector Machine (SVM) combined with Principal Component Analysis (PCA) with a combination of SVM with Particle Swarm Optimization (PSO) related to signal electromyographic signals (EMG) is given in this article. A Myo sensor bracelet was used for this experiment. This device is placed in the user^s upper arm. The experiment aims to recognize the five gestures of the user^s fingers. Both algorithms use the same features in the time domain. The experiments show that the PSO-SVM algorithm is more effective in identifying the user^s finger^s gesture than the SVM one. This combination reaches about 3% higher than the PCA-SVM. Keywords: SVM, PCA, PSO, EMG Share Link | Plain Format | Corresponding Author (Daniel Sutopo Pamungkas)

2	Artificial Intelligence (AI)	ABS-259
Pothole and Crack Detection on Asphalt Pavement in Bandung through Machine Learning Approach Rifdah Puspita Sari (a), Yackob Astor (b*), Iwan Awaludin (c), Salman Shalahuddin (d) a) Department of Civil Engineering, Politeknik Negeri Bandung, Jl. Gegerkalong Hilir, Kabupaten Bandung Barat 40559, Indonesia b) Department of Civil Engineering, Politeknik Negeri Bandung, Jl. Gegerkalong Hilir, Kabupaten Bandung Barat 40559, Indonesia *yackobastor[at]polban.ac.id c) Department of Computer and Informatics Engineering, Politeknik Negeri Bandung, Jl. Gegerkalong Hilir, Kabupaten Bandung Barat 40559, Indonesia d) Independent Researcher, Bandung, Indonesia Abstract Road condition surveys are typically performed manually. Surveyors walk along the road directly to identify and measure the type of damage. This approach is time-consuming and labor-intensive. With advancements in Artificial Intelligence, it is possible to detect road damage such as potholes and cracks, hence improving the efficiency of data processing in road condition surveys. This research aims to semi-automatically detect asphalt road damage through image data processing using a machine learning approach. The YOLOv8n model was used for road damage detection, achieving a highest mAP50 of 0.36. Therefore, the model was used to detect potholes and cracks in Terusan Jakarta Road. As a result, the Surface Distress Index (SDI) score for 1 km road segment of Terusan Jakarta Road based on the detection was 17, indicating that the road is in good condition and requires routine maintenance. Keywords: Road damage- Road condition survey- Surface Distress Index- Object detection- Machine Learning Share Link | Plain Format | Corresponding Author (Rifdah Puspita Sari)

3	Artificial Intelligence (AI)	ABS-7
Please Just Try to Submit This Sample Abstract Please Just Try to Submit This Sample Abstract Please Just Try to Submit This Sample Abstract You Can Edit It Again Later Abstract Please Just Try to Submit This Sample Abstract You Can Edit It Again Later Keywords: Please Just Try to Submit This Sample Abstract Share Link | Plain Format | Corresponding Author (afwan auliyar rakhman)

4	Artificial Intelligence (AI)	ABS-266
DIVERGENT OR CONVERGENT QUESTIONS: AN ANALYSIS IN THE CLASSROOM INTERACTION 1Rahmawati Fitriana,2Sekta Lonir Oscarini Wati Bhakti,3Suminto,4Noor Fachman Tjetje Politeknik Negeri Samarinda Abstract Abstract. As a part of design model in the classroom, the position of questions is part of the successfully instructional design. The aim of this study is to know the types questions used in the form of convergent and divergent and to observe how those questions employ in classroom questions. This is a qualitative Desain study with the respondent is a lecturer, sample is 40 students of D3 Accounting study program in Samarinda State Polytechnic in Samarinda. Theory underpinning of this study is from Wilen ^s theory (1991) with coordinated with Bloom Taxonym. Wilen^ theory Is categorized level of high and low questions classification. Level-1 Low Order Convergent (based on literal/ factual recall/memorization based), Level 2 - High Order Convergent- engaging students in productive thinking, Level 3 - Low Order Divergent- encourage learners to analyze information, draw conclusions, and Level 4-High Order Divergent- involve students into creative and evaluative thinking. Result shown that from 40 students, only 6 students reach on level-6-evaluation/High order divergent, the rest is ranked between Lower Order Convergent (LOC) and Lower Order divergent (LOD). Rephrasing different questions, preparing or using clues of simple words to lead students^ knowledge, designing and preparing clear and brief questions is an effective way of question discussed. Keywords: convergent and divergent question, Bloom taxonomy level, students^ level of questions Share Link | Plain Format | Corresponding Author (Rahmawati Fitriana)

5	Artificial Intelligence (AI)	ABS-270
Development of Machine Learning Model for Sentiment Analysis: A Case Study of Indonesia Presidential Candidates 2024 Rizqia Lestika Atimi (a*), Refid Ruhibnur (b), Indra Pratiwi (c) a, b, c) Departement of Information Technology Politeknik Negeri Ketapang Abstract In the modern political era, sentiment analysis can be utilized by politicians to assess the level of public support and opposition. During the 2024 Presidential and Vice-Presidential Debate period, the names of the presidential and vice-presidential candidates have increasingly become a topic of discussion among the Indonesian public, especially on social media. The large number of active users on the social media platform X in Indonesia, reaching 27.5 million as of July 2023, has a significant impact on the volume of tweets generated. Consequently, this platform can be utilized to gain insights into public sentiment regarding the preferred candidates for Indonesia^s 2024 presidential election. Therefore, an approach is needed to understand, extract, and process tweet data to identify and obtain information about the sentiments contained within it. Sentiment analysis can be an effective and efficient analytical approach to identify and classify public sentiment. This research develops a sentiment analysis model using a machine learning algorithm approach. The Naive Bayes machine learning algorithm is implemented to classify public sentiment into positive and negative categories. The stages carried out in the development of a sentiment analysis model include text preprocessing, labelling, weighting, machine learning algorithm implementation, and model evaluation. The model evaluation using confusion matrix shows that the developed sentiment analysis model can classify sentiment into two classes of positive and negative sentiment with a model performance accuration value of 72.44%. From the results of model implementation, it is known that during the 2024 presidential and vice-presidential candidate debate, the presidential candidate who received the most positive sentiment from the public was the Prabowo Subianto-Gibran Rakabuming Raka and the most negative sentiment from the public was the Anies Baswedan-Muhaimin Iskandar. Keywords: Share Link | Plain Format | Corresponding Author (Rizqia Lestika Atimi)

6	Artificial Intelligence (AI)	ABS-271
Analyzing the Effectiveness of Face Detection Algorithms in Improving Face Recognition Accuracy for Student Attendance Recording in Project-Based Learning Models Darmanto and Eka Wahyudi Politeknik Negeri Ketapang, Ketapang, Kalimantan Barat, Indonesia 78813 Abstract This study aims to compare the performance of two face detection algorithms, MTCNN and RetinaFace, in the context of a face recognition-based attendance system. The evaluation was conducted to measure the effectiveness of both models in terms of detection speed and accuracy using a diverse image dataset. This dataset includes images with varying numbers of faces, lighting conditions, and capture angles. The research process involved preprocessing images for consistency, setting parameters according to model documentation, and testing both algorithms on the same dataset. The results indicate that MTCNN has an average detection time of 1.97 seconds, making it more suitable for applications requiring quick responses, such as real-time attendance systems. Conversely, RetinaFace took an average of 8.75 seconds but showed advantages in detecting a higher number of faces, especially in more complex or less ideal images. Under optimal conditions, both algorithms were able to detect the same number of faces. However, in images with low lighting or challenging angles, RetinaFace demonstrated better performance. The conclusion of this study is that MTCNN is more suitable for applications prioritizing speed, while RetinaFace is ideal for situations requiring high accuracy despite longer processing times. The choice of algorithm depends on the specific needs of the application and its operating environment. Keywords: Face detection, MTCNN, RetinaFace, automatic attendance, face recognition. Share Link | Plain Format | Corresponding Author (Darmanto Darmanto)

7	Artificial Intelligence (AI)	ABS-272
Analysis Of The Comparison Between Jaro-Winkler And Levenshtein Distance Algorithms For Indonesian Language Error Checking In Theses Of Politeknik Negeri Ketapang Students Novi Indah Pradasari, Darmanto, Ar-Razy Muhammad Politeknik Negeri Ketapang Abstract This research analyzes the performance comparison between the Jaro-Winkler and Levenshtein Distance algorithms in detecting spelling errors in Indonesian-language theses written by students of Politeknik Negeri Ketapang. The growing need for automated language error-checking systems, particularly in academic writing, drives the exploration of these algorithms^ effectiveness in identifying misspellings. The study utilizes a dataset of student theses containing various types of annotated spelling errors to assess both algorithms. Key performance indicators include accuracy, speed, and sensitivity to different error types. The Jaro-Winkler algorithm emphasizes phonetic similarity, particularly for errors occurring at the beginning of words, making it suitable for detecting errors in words that are phonetically similar but incorrectly spelled. Meanwhile, the Levenshtein Distance algorithm calculates the minimum edit distance between words, allowing it to excel in identifying typographical errors. Experimental results show that each algorithm has specific strengths: Jaro-Winkler is more effective for phonetically-based errors, while Levenshtein performs better for minor typographical errors. This comparison provides insights into the potential integration of both algorithms into Indonesian language error-checking tools to improve the accuracy of automated systems for academic writing correction. Keywords: Please Just Try Jaro-Winkler, Levenshtein Distance, spelling errors, algorithm comparison, Indonesian language, academic writingto Submit This Sample Abstract Share Link | Plain Format | Corresponding Author (Novi Indah Pradasari)

8	Artificial Intelligence (AI)	ABS-274
Integrated Monitoring of Pests and Diseases in Paddy Plants Based on Convolutional Neural Network Mike Yuliana, Jalu Tirtabuana Politeknik Elektronika Negeri Surabaya Abstract Pests and diseases are a serious threat to rice production which can cause huge losses for farmers. Early detection and monitoring of pests and diseases of rice plants is an important key in reducing production losses and maintaining plant health. The paper aims to develop an integrated system for monitoring pests and diseases in rice plants based on deep learning using a Convolutional Neural Network (CNN) with image processing results to be uploaded to the web. This research also collects image data from rice plants infected with pests and diseases and will be used to train a CNN model that can recognize and classify types of pests and diseases in rice plants. The trained CNN model will be integrated with a web application. This web application will allow users, such as farmers or agricultural experts, to discover the health condition of rice plants in agrarian areas where testing has been conducted. Developing an integrated pest and disease monitoring system for rice plants based on a Convolutional Neural Network, which uses image processing with the results uploaded to the web, will make an important contribution in supporting efforts for early detection and monitoring of pests and diseases in rice plants. The results obtained during the experiments in this paper are the smallest loss value in the training model testing was obtained with a learning rate of 0.001, batch size of 64, and epoch 20, yielding a value of 0.1876 for pest and disease detection. Keywords: Convolutional Neural Network, pest and disease detection, farmers, learning rate, rice plants Share Link | Plain Format | Corresponding Author (Mike Yuliana)

9	Artificial Intelligence (AI)	ABS-19
Voice-Based Interaction System with Raspberry Pi 4 Tiara Agustina, Novian Fajar Satria, Endra Pitowarno Politeknik Elektronika Negeri Surabaya Surabaya, Indonesia Abstract This paper presents the design and implementation, a voice-based mobile service robot interaction system. Leveraging advanced speech recognition technology, the system allows users to interact with the robot through simple voice commands. The mechanical, system, communication, and electronic design aspects are thoroughly discussed. Key libraries such as Python SpeechRecognition and Robot Operating System (ROS) are utilized to enhance functionality. This research contributes to the field by providing a robust solution for interactive communication between robots and users, improving service quality in various contexts.The system undergoes extensive testing to ensure high accuracy and reliability. Results indicate that can recognize voice commands with an accuracy of 96.5%. Keywords: Voice-Based Interaction, Mobile Service Robot, Speech Recognition, Human-Robot Interaction, System Design, Performance Testing Share Link | Plain Format | Corresponding Author (Tiara Agustina)

10	Artificial Intelligence (AI)	ABS-23
3D Modeling Using a Terrestial Laser Scanner On the Citarum Baru Dayeuhkolot Bridge Rizal Fadilah (a), Thariq Abdul Jalil (a), Yackob Astor (a), Yulia Widyaningsih (a*) a) Department of Civil Engineering, Bandung State of Polytechnic Jalan Geger Kalong Hilir Ds Ciwaruga, Kec. Parongpong, Kab. Bandung Barat *yulia.widyaningsih[at]polban.ac.id Abstract Bridge inventory data collection is essential due to the growing number of bridges- one type of data that must be gathered is building documentation, which may help develop conservation or reconstruction. Bridge documentation is required to examine the current state of the bridge. Utilizing a Terrestrial Laser Scanner (TLS) to identify the geometry of the bridge is a single approach to documenting a bridge. Additionally, as a bridge ages, its performance declines, and its requirement for repair, maintenance, and replacement increases, leading to the need to conduct excellent maintenance management by regularly inspecting the bridge. Until this day, there have always been obstacles with the bridge inspection procedure, such as difficult access, long periods, or the lack of inspection aids. As a result, using advanced, contemporary instruments to aid in bridge inspections is vital. Survey technology, such as three-dimensional (3D) laser scanning technology, is one tool that can be utilized for bridge inspection. It is predicted that damage analysis inaccessible through conventional examination will be made easier by applying TLS. The 3D point cloud model from data processing can be combined with the point clouds to create a solid model. Research on the New Citarum Dayeuhkolot Bridge, located on Dayeuhkolot Street No. 366 - 348, Dayeuhkolot District, Bandung Regency, West Java, was conducted as part of this study. Multiple steps are involved in producing a 3D model with TLS, including data collection, registration, filtering, and mesh point clouds process. The dimensions of the current bridge are precisely calculated using the output of the 3D model. Using dimensions from manual measurements, which had the maximum comparative difference value of 1.39%, the 3D TLS model^s outputs were dimensionally validated in the final modeling stage. Keywords: Terrestial Laser Scanning (TLS)- Bridge Inspection- 3D Modeling Share Link | Plain Format | Corresponding Author (Yulia Widyaningsih)

11	Artificial Intelligence (AI)	ABS-44
Landslide Vulnerability Assessment in East Java, Indonesia, using Fuzzy Analytical Hierarchy Process - Natural Breaks Arna Fariza(a*), Arif Basofi(a), Abier Rahma Sofyantie(a) a) Department of Informatics and Computer Engineering, Politeknik Elektronika Negeri Surabaya Jl. Raya ITS Sukolilo Kampus PENS *arna[at]pens.ac.id Abstract Landslides pose a significant threat in flood-prone regions like East Java, Indonesia, causing fatalities, disruption, economic losses, and environmental damage. Traditional assessment methods may not adequately capture the complexities and uncertainties inherent in landslide occurrence for early warning into people. This study explores the potential of the Fuzzy Analytical Hierarchy Process (FAHP) combined with Natural Breaks classification to map landslide vulnerability in East Java resulting in low, moderate, and high landslide vulnerability indices in 38 cities/districts using 6 criteria: hazard, social vulnerability, economic vulnerability, physical vulnerability, environmental vulnerability, and capacity index. The weights obtained from FAHP will be classified using the natural breaks algorithm. the FAHP method produced a GVF of 0.9800, with a lower Standard Deviation of Assessment Metrics (SDAM) of 0.0059, indicating greater consistency across districts. In contrast, the AHP method achieved a slightly higher GVF of 0.9922 but had a higher SDAM of 0.0155, reflecting increased variability in its assessments. The importance of utilizing robust methodologies of FAHP and AHP for effective landslide vulnerability assessment, ultimately contributing to better disaster preparedness and risk mitigation strategies in the region. Keywords: Landslide- vulnerability- Fuzzy analytical hierarchy process- natural breaks- spatial mapping Share Link | Plain Format | Corresponding Author (Arna Fariza)

12	Artificial Intelligence (AI)	ABS-48
Enhancing Indonesian Text Processing with Rule-Based Stemming for Affixed and Reduplicated Words Irwan Setiawan, Fitri Diani, Yadhi A. Permana, Suprihanto Department of Computer and Informatics Engineering, Politeknik Negeri Bandung, Indonesia Abstract This paper presents the development and evaluation of two rule-based stemming algorithms, SFAIS (Suffix-First Approach Indonesian Stemmer) and PFAIS (Prefix-First Approach Indonesian Stemmer), aimed at addressing the unique morphological challenges of the Indonesian language. Our study, which includes the creation of comprehensive datasets comprising 31,310 unique root words and 19,075 unique affixed words, including 1,966 reduplicated words derived from 6,872 root words, is a significant contribution to Indonesian natural language processing. These datasets are made publicly available to support further research. SFAIS demonstrated an Index Compression Factor of 65.09, Word Stemmed Factor of 99.89%, and Correctly Stemmed Words Factor of 93.24%, while PFAIS showed an Index Compression Factor of 63.94, Word Stemmed Factor of 98.08%, and Correctly Stemmed Words Factor of 92.17%. SFAIS achieved an overall accuracy of 93.14%, outperforming PFAIS, which gained 90.40%. Error analysis revealed that SFAIS had a lower total error count (1,309) than PFAIS (1,832), with fewer under-stemming and miss-stemming errors. These results highlight the efficacy of the suffix-first approach in accurately processing Indonesian affixed and reduplicated words. Our study significantly contributes to Indonesian natural language processing by providing more accurate stemming algorithms and valuable datasets. Keywords: Indonesian Language Processing, Rule-Based Stemming, Morphological Analysis, Affixed Words, Reduplication Words Share Link | Plain Format | Corresponding Author (Irwan Setiawan)

13	Artificial Intelligence (AI)	ABS-67
Optimization of CoM Against CoP to Improve The Balance of Humanoid Soccer Robot Abulkhair Rizvan Yahya, Anhar Risnumawan, Nofria Hanafi, Wildan Habibi Al-Fanan, Syahrul Febriansyah Politeknik Elektronika Negeri Surabaya, Jl. Raya ITS, Keputih, Sukolilo, Surabaya, East Java 60111, Indonesia Abstract Humanoid soccer robot EROS often has difficulty in maintaining balance, which results in failure to complete tasks without falling. This research develops a balance control system using a load cell sensor to determine the position of the center of pressure (CoP) and PID control to adjust the position of the center of mass (CoM) of the robot to stay within the support polygon area generated by CoP. Tests were carried out on the forward movement with a step variation of 0 mm to 70 mm. The results show that the PID control system successfully keeps the CoM within safe stability limits, so that the robot can walk stably. This optimization proves the effectiveness of PID control in improving the balance of the humanoid robot during walking, allowing the robot to complete the task without falling. Keywords: Humanoid Soccer Robot- PID Control System- Center of Mass (CoM)- Center of Pressure (CoP)- Support Polygon Share Link | Plain Format | Corresponding Author (Abulkhair Rizvan Yahya)

14	Artificial Intelligence (AI)	ABS-78
Mobile Based Flood Disaster Detection Using K-Nearest Neighbors Algorithm Yaqutina Marjani Santosa (a*), Nur Budi Nugraha(a), Alifia Puspaningrum(a) (a)Department of Informatics Engineering, Politeknik Negeri Indramayu, West Java, 45252, Indonesia Abstract Flood disaster is one of the most frequent disasters in the world. One of the main challenges in flood disaster detection is the limitation in accurately predicting when, where, and how severe a flood will occur. In this study, a mobile-based flood status detection system is proposed that utilizes the k-Nearest Neighbors (kNN) algorithm. The proposed approach will integrate various variables such as real-time rainfall data, topographic information, land use data, and historical flood records to produce an accurate and responsive prediction model. In addition, this study will also explore ensemble techniques by combining kNN and other machine learning algorithms to improve prediction performance. The trial demonstrated the effectiveness of the system, achieving 93.5% accuracy on the test data. Comparative analysis showed that kNN is on par with other machine learning algorithms in detecting flood status, with advantages in terms of interpretability and ease of implementation on mobile devices. The performance of the mobile application is very promising, with an average prediction time of 0.5 seconds, indicating its suitability for direct use. The results of this study are expected to make a significant contribution to the development of a more effective, adaptive, and easy to implement flood early warning system in various geographic contexts. Keywords: Detection- Flood Disaster- kNN- Rainfall Share Link | Plain Format | Corresponding Author (Nur Budi Nugraha)

15	Artificial Intelligence (AI)	ABS-85
Development of Monitoring System for Early Childhood Education Learning Progress Muhammad Sufi Aulia, Ary Setijadi Prihatmanto ,Rahadian Yusuf,Agus sukoco School of Electrical Engineering and Informatics, Bandung Institute of Technology Jalan Ganesha 10, Bandung 40132, Indonesia Abstract ECE (Early Childhood Education ) is important for children learning since it sets a benchmark of learning for children when they begin schooling. However, identification of child development in the context of ECE has been found to be a huge challenge. The objective of this study is to design a highly effective monitoring system based on deep learning, object detection, and YOLO to improve the correctness and speed of monitoring ECE learning progress. Through the use of this technology, the system is designed to be able to analyses and categorise different activities of children in realtime with the feedback to the teachers and parents being immediate. It makes the process of monitoring much easier apart from enhancing communication between the teachers and the parents, not forgetting the progressive growth of the children. This capability was tested based on data captured by cameras placed in the classrooms then passed through yav8 to improve its accuracy as well as real-time monitoring abilities. The study shows how technology application in monitoring ECE improves the system^s ability to meet the need of the children. Keywords: Early Childhood Education (ECE), Deep Learning, Object Detection, YOLO (You Only Look Once), Real-time Monitoring Share Link | Plain Format | Corresponding Author (Muhammad Sufi Aulia)

16	Artificial Intelligence (AI)	ABS-87
A Retrieval-Augmented Generation-based Chatbot using Llama 3 Humaira, Yori Adi Atma, Rika Idmayanti, Alvin Fadli Dwi Mulya Department of Information Technology, Politeknik Negeri Padang, Jl. Kampus Limau Manis, Padang 25164 Abstract Artificial intelligence is widely used in a variety of sectors, including chatbot technology. This study creates a chatbot utilizing the Natural Language Processing (NLP) technique. This method enables the system to work more intelligently in understanding the user^s language and to respond in a natural language. This chatbot examines a case study of Question/Answer (Q/A) information from the Information Technology (IT) Department at Padang State Polytechnic (PNP). This chatbot employs Large Language Model (LLM) technology, notably Llama 3 and Retrieval-Augmented Generation (RAG). RAG serves to improve the performance of Llama 3. The use of RAG in this situation enables the chatbot^s knowledge to be dynamically updated. This research resulted in the successful development of an interactive chatbot that uses natural language. The natural language spoken is Indonesian. The system testing was conducted using the researchers^ intuitive approach. Users provided questions to the chatbot system, and the chatbot responded by giving answers. These responses were successfully aligned with the context of the available documents. Keywords: RAG, LLM, Llama 3, Q/A, NLP, Chatbot, Information Share Link | Plain Format | Corresponding Author (humaira humaira)

17	Artificial Intelligence (AI)	ABS-96
Development and Design of a Humanoid Robot to Allow Walking Naturally as Human Tsaqofi Muhammad Ishaq (a), Novian Fajar Satria (a), Endra Pitowarno (a), Rachmat Santoso (a), Dwi Kurnia Basuki (a) (a) Politeknik Elektronika Negeri Surabaya Sepuluh Nopember Institute of Technology, Jl. Raya ITS, Keputih, Kec. Sukolilo, Surabaya, Jawa Timur 60111 Abstract The mechanical development of humanoid robots generally requires a flexible design to allow for unrestricted movement. Several simulation approaches were employed to ensure the viability of the new mechanical design, including stress analysis and inverse kinematic testing. Motion simulation was conducted using Blender, followed by real-world testing on the robot. The experiments demonstrate that the new leg design enables he robot to perform more complex motions. Stress analysis results indicate that the new components can support the robot^s mass up to 4 kilograms. Additionally, comparisons between Blender simulations and real-world tests show differences in performance between the old and new designs. The new design achieved angles up to 10 degrees greater than those predicted by the Blender simulation. Keywords: Stress Analysis, Blender Simulation, Real-world Simulation Share Link | Plain Format | Corresponding Author (Tsaqofi Muhammad Ishaq)

18	Artificial Intelligence (AI)	ABS-99
Machine Learning Model Comparison Analysis For Proportional Control Of Hand Wrist Gestures Using EMG Signal Leoni Daiichi, Rika Rokhana, Paulus Susetyo Wardana Electronics Engineering, Electronic Engineering Polytechnic Institute of Surabaya Jl. Raya ITS - Kampus PENS, Surabaya 60111, Indonesia Abstract Keywords: Electromyography, Muscle Signal, Electrode, Neural Network, k-Nearest Neighbor. Share Link | Plain Format | Corresponding Author (Leoni Daiichi)

19	Artificial Intelligence (AI)	ABS-108
Optimization of Supply Chain Management in E-Commerce MSMEs Based on Artificial Intelligence to Increase the Competitiveness of MSMEs in North Sulawesi Marike Amelda Silvia Kondoj- Toban Tiku Pairunan- Fitria Claudya Lahinta- Viltie Wensen a) Informatic Engineering, Manado State Polytechnic b) Informatic Engineering, Manado State Polytechnic c) Informatic Engineering, Manado State Polytechnic d) Informatic Engineering, Manado State Polytechnic Abstract Micro, small and medium enterprises (MSMEs), including North Sulawesi, have a strategic role in the national economy. Human resources, technology, and supply chain management are needed to increase the productivity of MSMEs. MSMEs in North Sulawesi could have been more optimal in producing products according to consumer needs. This research is urgent to create an integrated supply chain management system to support raw material procurement activities and product delivery to consumers to minimize and maximize consumer value and competitive profits so that MSMEs can compete in the global market. The system is created using PHP and MySQL programming. This study tested the experimental method on a laboratory scale and with relevant partners. Use the Support Vector Machine (SVM) method for supply chain management. The test results prove that the supply chain management system created can display the calculation of estimated stock requirements and raw material estimates calculated based on composition data. Therefore, this system is suitable for use and can be developed according to the needs of MSMEs. Keywords: MSMEs, supply chain, integrated, SVM, North Sulawesi. Share Link | Plain Format | Corresponding Author (Marike Amelda Silvia Kondoj)

20	Artificial Intelligence (AI)	ABS-110
Chatbot for PENS Library Services Using Text Mining and Rule-Based Methodsact Ira Prasetyaningrum,Feby Nihayatus Shibghoh,Arna Fariza Politeknik Elektronikam Negeri Surabaya Abstract The PENS-library needs to carry out innovations so that services at the library can provide optimal support for its users. The proposed solution is an online library with chatbot AI technology using automatic interaction through websites and messaging apps. The chatbot will enable users to receive quicker responses without human supervision. The feature extracts the keywords of user questions and provides appropriate answers. Currently, information services at the PENS library can only be obtained directly, which makes it vital to create assistance between students and the library to quickly, easily, and accurately get the information needed. A rule-based method will be implemented in the development of this chatbot so that the answers provided will be consistent and precise, as seen in the study by Soyusiawaty and Febi (2023) with an accuracy of 90.71%. This research presents the development of a rule-based chatbot intended for the service of information about the PENS library, a way to increase efficiency, service quality improvement, and the level of students^ access to information.ease Just Try to Submit This Sample Abstract You Can Edit It Again Later Keywords: Library- Chatbot- Artificial intelligence (AI)- Rule-based method Share Link | Plain Format | Corresponding Author (Ira Prasetyaningrum)

21	Artificial Intelligence (AI)	ABS-112
The Convergence of Blockchain and Federated Learning: A Bibliometric Exploration of Decentralized AI Yuhefizar, Ronal Watrianthos Politeknik Negeri Padang, Padang, Indonesia Abstract The convergence of blockchain and federated learning has emerged as a transformative paradigm in decentralized artificial intelligence and secure data sharing. This study presents a comprehensive bibliometric analysis of research at the intersection of these technologies from 2018 to 2024, addressing the need for a holistic understanding of this rapidly evolving field. Utilizing data from the Web of Science Core Collection, we employed advanced bibliometric tools and ^Keyword Plus^ analysis to identify key research clusters and highlight emerging trends. Our findings reveal an extraordinary annual growth rate of 99.48% in publications, with 556 documents from 253 sources identified. The field demonstrates high collaboration, evidenced by an average of 4.73 co-authors per document and 44.06% international co-authorship. China emerges as the dominant force, contributing 48.7% of total publications. Analysis of influential papers underscores a consistent focus on privacy preservation, security enhancement, and application in domains such as Industrial IoT and vehicular networks. Emerging trends include the integration with edge computing, optimization of resource allocation, and applications in smart transportation and healthcare. This study contributes a comprehensive bibliometric analysis on blockchain and federated learning convergence highlighting the potential synergies of these technologies in addressing critical challenges in data privacy and collaborative AI, as well as identifying key areas for future research and development. Keywords: AI, Blockchain, Federated Learning, Bibliometric Share Link | Plain Format | Corresponding Author (Ronal Watrianthos)

22	Artificial Intelligence (AI)	ABS-138
Processing Data from the ADIS 16364 Device to Determine Ship Motion Jamal, Hardiyanto, Fazrian, M Ibrahim Anselistyo, Ramanda Bayu Saputra Please Just Try to Submit This Sample Abstract Department of Naval Architecture, Politeknik Negeri Bengkalis, 28711 Bengkalis, Indonesia Abstract Ship motion is an important factor in ship design and application, which is important to know through valid measurements. ADIS 16364 is a motion measuring instrument consisting of accelerometer and gyroscope sensors. Currently, ADIS data can only measure translational acceleration and angular acceleration and cannot yet calculate ship motion. To process the measurement data, we use various methods, such as moving average filter (MAF), and trapezoid integration. We validate by comparing the results of ship motion measurements in the Manoeuvring Ocean Basin (MOB) using the ADIS 16364 measuring instrument and the QUALISYS Motion Capture System, which we can do together. The validation results show that we can improve ADIS 16364 data to be in line with internationally recognized standard tools in ship motion analysis. The difference value obtained from the root mean square percentage error (RMSPE) value is between 2.15% and 3.84%. Keywords: ADIS 16364, QUALISYS, Moving average filter, Ship motion Share Link | Plain Format | Corresponding Author (Jamal Jamal)

23	Artificial Intelligence (AI)	ABS-153
When artificial intelligence meets performances The performances model of tourism destinations powered by artificial intelligence Tomy Andrianto- Wahyu Rafdinal- Gundur Leo- Mohammad Rizal Gaffar- Fajar Kusnadi Kusumah Putra Politeknik Negeri Bandung Abstract The massive adoption of artificial intelligence (AI) has occurred after the COVID-19 pandemic, currently, AI is still being used. However, research analysing the impact of using AI on tourism destinations is still limited. Therefore, this study aims to find the effect of AI adoption on managerial performance and destination performance by integrating the human-organization-technology fit (HOT-fit) model and the technology-organization-environment (TOE) model. The data were gathered through a survey of 105 tourist destination managers who used AI and evaluated through the structural equation model-partial least squares (SEM-PLS) and essential performance map analysis (IPMA). By using SEM-PLS and IPMA, the findings of this study reveal that human, organisational, technological and environmental factors are essential factors influencing managerial and destination performance. This study encourages tourist destination managers to improve performances by utilising AI effectively, ensuring compatibility between humans, organisations, technology and the environment. The application of AI integrated with the HOT-fit and TOE models will help tourist destinations be more responsive to environmental and technological changes that improve destination performance. This study offers a new perspective into the theory and applications of the HOT-fit and TOE models in explaining managerial performance and destination performance in the context of AI in the tourism industry. Keywords: Artificial intelligence, Human-organization-technology fit model, Technology-organization-environment model, Managerial performance, Destination performance Share Link | Plain Format | Corresponding Author (Mohammad Rizal Gaffar)

24	Artificial Intelligence (AI)	ABS-154
WPQA: a Lite Indonesian Question Answering for Wikipedia Mohammad Yani, Cindy Apriliyani, Muhamad Mustamiin, and Rendi Politeknik Negeri Indramayu Abstract In recent years, researchers in natural language processing have developed many pre-trained models based on BERT. One of these models is IndoBERT, an Indonesian-language version of BERT trained using Indonesian-language online articles. IndoBERT has indeed been used to evaluate Indonesian-language benchmark datasets. However, practical implementations are still limited, including the implementation of IndoBERT in a question-answering system application to obtain information from Wikipedia. In this study, the author proposes a simple Indonesian-language question-answering system called the Lite Indonesian Questions Answering for Wikipedia (WPQA), which can generate answers from Wikipedia for a given question. This system consists of three components: input, process, and output. This system inputs keywords and questions. Then, the input is processed using the IndoBERT model to search for answers from the given context. The result is an answer obtained from the context search. The system is evaluated by using a psychometric tool to measure users^ perceptions of the system. In the evaluation, we have a user satisfaction rate of 82%, who state that they are satisfied with the system. The percentage is measured by using Likert scale. The evaluation results show that WPQA can be used to search for information on Wikipedia topics from a Wikipedia context. Keywords: question answering, wikipedia indonesia, indobert Share Link | Plain Format | Corresponding Author (Mohammad Yani)

25	Artificial Intelligence (AI)	ABS-160
MANAGEMENT INFORMATION SYSTEM IOT-BASED RFID MEDICINE Erischa Indah Kusuma, Dr. Ir. Rika Rokhana, MT, Hendhi Hermawan, S.ST., M.T Politeknik Elektronika Negeri Surabaya Abstract Drug management information system with RFID based on the Internet of Things (IoT) has been proven to be an effective solution to overcome the problems of health services and pharmacy operations. Based on research in DKI Jakarta in 2003, it was found that 26.5% of pharmacies did not meet drug management standards. The implementation of RFID technology in this system enables automatic identification that improves data accuracy and real-time management of drug stocks. By placing an RFID tag on each medicine box, identity information and stock quantities can be accessed quickly and automatically, preventing shortages or overstocks and speeding up the re-procurement process. Test results showed a 30% increase in pharmaceutical stock management efficiency and a 95% increase in data accuracy. Overall, the system provides significant benefits in efficiency, accuracy, and transparency, helping pharmacies to effectively improve the management of pharmaceutical supplies so as to provide better services to patients and ensure safe and appropriate use of drugs. Keywords: RFID, Drug Management Information System, Pharmacy. Share Link | Plain Format | Corresponding Author (Erischa Indah Kusuma)

26	Artificial Intelligence (AI)	ABS-162
Graph Neural Network - Local Search for Solving Traveling Salesman Problem Robieth Sohiburoyyan, Salamet Nur Himawan, and Iryanto Politeknik Negeri Indramayu, jalan lohbener lama no.08 Abstract Travelling salesmen problem (TSP) is a famous research field in optimization problems. Despite its simplicity, solving the problem for large amount of city is computationally infeasible. In this case, finding the optimal solution can be extremely difficult and quite challenging. Given the widespread applications of TSP and the need of improved methods to solve the problem, further research is needed. Main purpose of this research is to implement the Graph Neural Network (GNN) and local search, 2 and 3 optimal algorithm, in addressing the TSP. To see performance of the hybrid methods, several simulations are carried out such benchmark test in TSPLIB, the square grid TSP, and practical applications. Results of this research show that the hybrid methods have promising results in solving the problems. Existence of the local search increases quality of the solutions. For instance, the best relative error of the GNN-2-3 optimal algorithm is within range 0 - 4.31% in solving several cases of the TSP benchmark in TSPLIB. Further, the hybrid method can find five of seven exact solutions of the square grid TSP. Keywords: Travelling salesmen problem, Graph Neural Network, local search Share Link | Plain Format | Corresponding Author (Robieth Sohiburoyyan)

27	Artificial Intelligence (AI)	ABS-165
The Diagnosis of Dengue Virus Using Principal Component Analysis and Random Forest Based on Raman Spectroscopy Aldo Novaznursyah Costrada, Nina Siti Aminah, Dessy Natalia, Herman, Annita Alni, and Mitra Djamal Bandung Institute of Technology Abstract A classification system based on Raman spectra of dengue virus infected blood serum has been developed and proposed in this study. This development can be useful for health workers in diagnosing dengue fever patients infected with dengue virus. In this study, Raman spectral data from dengue virus infected blood serum samples were used for classification using dimensionality reduction technique combined with Random Forest (RF) classifier. Experimental and quantitative analysis is based on blood serum samples that have been diagnosed with dengue virus through NS1 and IgG/IgM testing. Principal component analysis (PCA) was used as a dimension reduction technique combined with RF (PCA-RF) to highlight variations that can distinguish the Raman spectra of dengue and non-dengue virus infected blood serum. The partition of training data and test data in this model is 8:2 of the total data, also the Iterations of 50 times and estimators of 100 decision trees were applied to each model. The proposed technique has shown good potential to be used in the differentiation between dengue and non-dengue virus infected sera. PCA-RF technique has the best result with 95.89% of accuracy and 0.176 of RMSE, while RF has 89.05% of accuracy and 0.315 of RMSE. Keywords: Dengue Virus, Raman Spectroscopy, Principal Component Analysis, Random Forest Share Link | Plain Format | Corresponding Author (Mitra Djamal)

28	Artificial Intelligence (AI)	ABS-177
Optimization of Tsunami and Earthquake Awareness Through Digital Mapping Using a Decision Support System with Simple Additive Weighting (SAW) in Padang City Andrew Kurniawan Vadreas, Harfebi Fryonanda, Hendra Saputra, Raihan Efel Maulana, Dwi Welly Sukma Nirad Politeknik Negeri Padang Abstract Padang is a city that is prone to earthquakes and tsunamis due to its location between the India and Asia plates on the west coast and being crossed by the Great Sumatran fault. The Padang coastal region is a strong source of earthquakes and tsunamis. Despite having experienced earthquakes in 2006, 2007, and 2009, Padang still faces difficulties in managing tsunami evacuation because of the lack of infrastructure and straight roads from the coast to higher ground. The presence of rivers in Padang causes the tsunami waves to be concentrated within a 200-meter radius and the evacuation routes are hindered by the presence of bridges that are not durable against tsunamis and earthquakes. Additionally, traffic congestion after an earthquake exacerbates the evacuation problems. This study aims to map the risk and potential of earthquakes and tsunamis in Padang 3 KM from the coast by comparing population and building data with the availability of shelters. The Simple Additive Weighting (SAW) method, as part of Geographic Information System, is used to analyze demographic data and shelter locations. The results show that Koto Tangah is the area with the highest risk level for earthquakes and tsunamis. Keywords: Shelter, Geographic Information System (GIS), Simple Additive Weighting (SAW), Digital Mapping Share Link | Plain Format | Corresponding Author (Andrew Kurniawan Vadreas)

29	Artificial Intelligence (AI)	ABS-178
The Design and Construction of a Weather Monitoring Station at the Bengkalis State Polytechnic Campus Using Internet of Things (IoT) Technology Marzuarman (*), Stephan, Muhammad Afridon, Nirwan Budianto, Doni Mirza Rinaldi, Bagas Prasetyo Department of Electrical Engineering. Bengkalis State Polytechnic Bengkalis, Riau, Indonesia *marzuarman[at]polbeng.ac.id Abstract Weather information is important for humans. The high rainfall on Bengkalis island must be predicted to prevent extreme weather phenomena, including storms, heavy rain, and snow, which have potential to cause disasters. This has an impact on the safety of ship transportation on Bengkalis Island. Thus, a sistem was develop to monitor weather in real-time by using the Internet of Things. The system consists of an Arduino Mega controller and seven weather parameter measuring sensors (temperature, humidity, air pressure, light intensity, wind speed, wind direction, and rainfall). This system is equipped with a SIM800L GPRS module to connect data to the Firebase real-time server for the purpose of displaying the data on the Android application. Based on the test results, the DHT-22 sensor had an average error of 0,61% in temperature testing and 0,48% in humidity testing. The wind speed sensor test had an average error of 4,11%. The BH1750 sensor test had an average error of 3,58%, while the BMP280 sensor test had an average error of 0,035%. In the wind direction sensor test, each direction obtained an angle of 44 degrees, with the exception of the north direction which obtained an angle of 45 degrees and the northeast direction obtained and angle of 43 degrees. While the rainfall sensor had an average rainfall value of 1,580 mm on each sensor tip. This research has successfully developed a real-time weather monitoring system at the Bengkalis State Polytechnic Campus. The system enables users to conveniently monitor the weather conditions at the Polbeng campus and Bengkalis Island at any time and from any location using only an android smartphone. Keywords: Weather Station- Internet of Things (IOT)- Bengkalis State Polytechnic Share Link | Plain Format | Corresponding Author (Marzuarman Marzuarman)

30	Artificial Intelligence (AI)	ABS-184
Investigating The Role of AI for Fact-Checking: A Systematic Literature Review Alhadi Saputra, Indra Mudrawan, Ary Widiyanto Badan Riset dan Inovasi Nasional dan Universitas Pelita Bangsa Abstract Technological advances, including artificial intelligence (AI), have enabled the filtering and modifying of information in response to the proliferation of false and misleading information in journalism and media. This research paper explores the role of artificial intelligence (AI) in fact-checking, looking at the role based on the current state, advantages, challenges, and limitations and suggesting future research directions. This research aims to optimize AI technology to provide more accurate and reliable fact-checking solutions, providing a comprehensive overview of the current technology and its applications. We use a systematic literature review as a method. The analyzed studies reveal that while AI has the potential to automate the verification process, it encounters challenges like data quality issues, algorithmic bias, and context-aware systems. These issues impact the reliability and effectiveness of AI-driven fact-checking systems. Keywords: Artificial Intelligence, Misinformation, Fact Checking Share Link | Plain Format | Corresponding Author (Alhadi Saputra)

Page 1 (data 1 to 30 of 256) | Displayed ini 30 data/page
1 2 3 4 5 6 7 8 9 NEXT >>

Powered By Konfrenzi Ultimate 1.832M-Build8 © 2007-2024 All Rights Reserved