IAIC International Conference Series
https://aptikom-journal.id/conferenceseries
<p style="text-align: justify;"><strong>IAIC International Conference Series (IICS)</strong> managed by <a href="https://iaic-publisher.org/"><strong>Indonesian Association on Informatics and Computing (IAIC)</strong></a> and supported by <strong><a href="https://alphabetincubator.id/">Alphabet Incubator</a> </strong>. All URL of published articles will have a digital object identifier (DOI). The open-access <a href="http://iaic-publisher.org/" target="_blank" rel="noopener">IAIC International Conference Series</a> provides a fast, versatile and cost-effective proceedings publication service for your conference. Proceedings are an important part of the scientific record, documenting and preserving work presented at conferences worldwide.</p> <p style="text-align: justify;">Key publishing subject areas include: Computer Science, Informatics, Electronics Engineering, Communication Network and Information Technologies.</p>IAIC Publishingen-USIAIC International Conference Series2774-5880User Experience Analysis on Bakamla Messenger Applications Using User Experiences Questionnaire (UEQ)
https://aptikom-journal.id/conferenceseries/article/view/617
<p><em><span style="font-weight: 400;">User experience describes the experience a user gets when using a software product. This research aims to measure the user experience when using the Bakamla Messenger application. Measurements were carried out using the User Experience Questionnaire (UEQ) method. The research was carried out by distributing online questionnaires to users of the Bakamla Messenger application, with a total of 117 respondents. The measurement results for the attractiveness aspect of 2.26, clarity of 2.30, efficiency of 2.24, accuracy of 2.27, and stimulation of 2.28 have a positive impression value and are included in the excellent criteria. However, the novelty aspect gets a value of 0.02, meaning it has a negative impression value and is included in the bad criteria, so the innovation of the product needs to be increased. Thus, we recommend that Bakamla messenger application developers focus on improving aspects of the novelty value of the application, such as the level of security of confidential data and the messenger system being able to provide new features beyond messenger in general.</span></em></p>HozairiBuhariRofiudinSyariful Alim
Copyright (c) 2023 Hozairi, Buhari, Rofiudin, Syariful Alim
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-194111010.34306/conferenceseries.v4i1.617The Semosemo: Vehicle Rental Application in Manado City
https://aptikom-journal.id/conferenceseries/article/view/619
<p><em><span style="font-weight: 400;">In everyday human life, there are many aspects that cause a decision to be made. Agreements can be made in writing or unwritten, reciprocal agreements and unilateral agreements, obligatory agreements and one of them is a lease agreement. The lease agreement can help the parties, both from the leaser and the lessee. Car Rental is one of the businesses providing transportation services that involves the use of mobile devices to find out information about the services provided by the company. Car Rental is closely related to transportation services to help people who need car rental for various purposes. To use rental services in Manado City, usually the tenant must go to the rental place, and that is less efficient to do. Therefore, the problem found is how to make the Semosemo Vehicle Rental Application in Manado City. With the aim of making the Semosemo Vehicle Rental Application in the City of Manado. This research uses the prototype method and is also assisted by software such as React Native, Figma, and Visual Studio Code. The result is that the Semosemo application can be made to help rent vehicles in the city of Manado and the application can run accordingly.</span></em></p> <p><em><span style="font-weight: 400;"> </span></em></p>Green Ferry MandiasChristiady Somba SirappaPierre Jericho EffendyTimothy Matthew Jeremi Dirk
Copyright (c) 2023 Green Ferry Mandias, Christiady Somba Sirappa, Pierre Jericho Effendy, Timothy Matthew Jeremi Dirk
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-1941112110.34306/conferenceseries.v4i1.619Agile Method in Developing Electronic Local Government Food Reserve Distribution Services (E-CPPD) in Sukabumi City
https://aptikom-journal.id/conferenceseries/article/view/621
<p><em><span style="font-weight: 400;">Indonesia is a country with a region that has disasters here. As a Regional Apparatus Organization which must distribute regional government food reserves to the community when natural disasters strike, Dinas Ketahanan Pangan, Peternakan dan Perikanan Kota Sukabumi took the initiative to develop an application that can speed up the distribution of aid to the community. This national food reserve policy can support national defense in emergency conditions. The hope is that the development of this application can speed up the administration of official correspondence, where the administration of this correspondence is an element that slows down actions in almost every department, resulting in the length of time that citizens receive assistance. There are many discussions and interviews with various users who need to adapt an environment that requires flexibility in changes to system development, so this system development uses the spiral method. As a result, based on the user requirement list, 100% of user needs can be completed on time. The result, almost nine (9) tons of rice have been distributed to residents spread across 22 of the 33 sub-districts in Sukabumi City.</span></em></p>Asril Adi SunartoEuis Kania Kurniawati
Copyright (c) 2023 Asril Adi Sunarto, Euis Kania Kurniawati
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-1941223310.34306/conferenceseries.v4i1.621A Survey of Blockchain in Governance: Framework Selection and Future Implementation in Indonesian Government
https://aptikom-journal.id/conferenceseries/article/view/623
<p><em><span style="font-weight: 400;"> Blockchain technology enables users to connect without the need for a third party or central server. This is achieved through the use of a decentralized system, ensuring that all data and information transacted are encrypted, verified, validated, and stored using mathematical consensus algorithms. This leads to blockchain being recognized as a technology characterized by decentralization, security, anonymity, transparency, immutable data, and trust. Blockchain is frequently associated with digital currency, although digital currency is just one of the outcomes of applying blockchain technology, resulting in cryptocurrencies. Currently, blockchain technology is a trend among academics and practitioners who are researching and developing blockchain technology for application in various domains, including government. Government systems and public servants often encounter issues related to data security. Hence, the research has the purpose to offer comprehension and perspectives on implementing blockchain technology within the government sector to enhance public service information security. The research was carried out by reviewing Scopus-indexed international articles published between 2019 and 2023, which are relevant to frameworks, consensus algorithms, and applications employed in the governmental domain. The research outcomes revealed that the Hyperledger Fabric framework, coupled with the Practical Byzantine Fault Tolerance (PBFT) algorithm, is the most suitable option for potentially developing blockchain-based government or public service applications for future implementation. Regarding this research, there are future challenges in the form of constructing prototypes and evaluating their effectiveness and efficiency. Therefore, further research and development efforts are essential to ensure that the application of blockchain technology in the government sector can be realized as required in the future.</span></em></p>Eltyasar Putrajati NomanDjoko Budiyanto Setyohadi
Copyright (c) 2023 Eltyasar Putrajati Noman, Djoko Budiyanto Setyohadi
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-1941344810.34306/conferenceseries.v4i1.623Comparative SVM and Decision Tree Algorithm in Identifying the Eligibility of KIP Scholarship Awardee
https://aptikom-journal.id/conferenceseries/article/view/625
<p><em><span style="font-weight: 400;">Scholarship selection process has specific rules, but if the number of applicants exceeds the quota, a selection process is needed. Based on the observation of a university in Sukabumi, the selection for KIP scholarship has not yet had a standard method. Several methods can be used to assist the selection process, such as classification based on historical data of applicants. The algorithms used for classification include Decision Tree (DT) and Support Vector Machine (SVM). The research process uses SEMMA (Sample, Explore, Modify, Model, Assess) method. Dataset for KIP scholarship awardee from 2021-2022 consist of 519 samples with 16 attributes. From the exploration results, the most important features for model modeling are Status DTKS, Status P3KE, Father's income, mother's income, combined income, and performance. These attributes are converted into numerical data to facilitate model fitting. The K-Fold Cross-Validation results for the Decision Tree model in the case of KIP Scholarship classification yield an accuracy of 78.44% for the entire test dataset, a precision of 0.73107, indicating that 73.11% of the predictions are true, a recall (sensitivity) of 78.45%, and an F1 score of 73.20%. The results for the SVM model are an accuracy of 80.17%, a precision of 84.44%, and a recall of 80.17%.</span></em></p>AsriyanikAgung Pambudi
Copyright (c) 2023 Asriyanik, Agung Pambudi
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-1941495710.34306/conferenceseries.v4i1.625Classification of Coffee Leaf Diseases using the Convolutional Neural Network (CNN) EfficientNet Model
https://aptikom-journal.id/conferenceseries/article/view/627
<p><em><span style="font-weight: 400;"> Coffee leaf disease is a problem that needs attention because it affects the quality and productivity of the coffee harvest and is detrimental to farmers. Therefore, a system is needed to identify types of coffee leaf diseases using artificial intelligence. There are four types of coffee leaf diseases, namely Miner leaf, Phoma leaf, Rust leaf, and Nodisease leaf. The research used the EfficientNet Architecture Convolutional Neural Network (CNN) method to detect types of disease on coffee leaves. This method was chosen because it is capable and reliable in processing digital images for pattern recognition. The dataset used is 1,464 images with dimensions of 2048 x 1024 pixels with RGB type which are divided into 1,264 training data and 400 testing data. Several architectures used in EfficientNet are EfficientNet B0, EfficientNet B1, EfficientNet B2, EfficientNet B3, EfficientNet B4. Parameters used are Lanczos resampling, Epoch 25, Learning Rate 0.0001, Loss Function Sparse Categorical Cross Entropy, Optimizer Adam. The results of training data testing, namely the CNN EfficientNet B1 Architecture Model method, got the best accuracy of 97% and a loss of 0.1328 and testing data testing got an accuracy of 0.97% and a loss of 0.1328. The architecture of the EfficientNet B1 model is better than other architectural models, namely VGG16, ResNet50, MobileNetv2, EfficientNet B0, EfficientNet B2, EfficientNet B3, EfficientNet B4, EfficientNet B5, EfficientNet B6, EfficientNet B7.</span></em></p>Muhammad Imron RosadiLukman HakimM. Faishol A.
Copyright (c) 2023 Muhammad Imron Rosadi, Lukman Hakim, M. Faishol A.
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-1941586910.34306/conferenceseries.v4i1.627Application of Agile Development Methods in the Development of Integrated Systems for Vehicle Body Repair
https://aptikom-journal.id/conferenceseries/article/view/629
<p><span style="font-weight: 400;">PT XYZ Auto Body Repair is a company that focuses on repairing and servicing vehicles, especially cars that have been involved in accidents or disasters. Currently, data processing still uses physical forms, which has proven to be inefficient because it takes significant time, labor, and resources. Collecting and inputting data from various forms requires a large effort, while systems that are not integrated cause delays in providing the required information. These challenges impact the company's ability to make decisions quickly and on time, especially in the face of increasingly tight and complex business competition. Therefore, an efficient and integrated solution is needed. Seeing this problem, it was decided to develop an integrated vehicle repair system by applying agile development methods, especially the Extreme Programming model. This approach allows development in an iterative, fast, adaptive manner, and actively involves users at every stage of development. Experience has shown that applying the Extreme Programming model can produce an integrated system that meets user needs in a short time. With this system, companies can produce reports quickly without reduplication or repetitive data processing. All parts involved in the vehicle repair process will be connected to one company server, creating the efficiency and accuracy needed to support business growth in a dynamic business environment.</span></p>Didik IndrayanaPrajokoAsril Adi Sunarto
Copyright (c) 2023 Didik Indrayana, Pradjoko, Asril Adi Sunarto
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-1941707810.34306/conferenceseries.v4i1.629Sentiment Analysis of Bjorka Hacker Using the Naive Bayes and C.45 Algorithms
https://aptikom-journal.id/conferenceseries/article/view/614
<p><em><span style="font-weight: 400;"> In 2023, Indonesia was again devastated by a hacker known as Bjorka. Bjorka did not act just once or twice; every time, Bjorka made the entire Indonesian population proud. The 19 million BPJS Employment data belonging to the Indonesian people that Bjorka hacked is the BPJS Employment data belonging to the Indonesian people that Bjorka hacked. Since the release of the Bjorka story, there has been a surge in the number of people criticizing it on social media, particularly Facebook, so the criticism or opinions can be used to conduct sentiment analysis. Based on this, developing a method that can automatically classify beliefs into positive and negative categories through sentiment analysis is necessary. The sentiment analysis process begins with data preprocessing, followed by keyword analysis using the TF-IDF method, algorithm development, and analysis of classification results. The data classification methods used in this study are Naive Bayes and C4.5. The data will be analyzed using text mining and classified using the Naive Bayes and C4.5 algorithms. Based on the results of the tests, the best classification was achieved by Nave Bayes, with a score of 70 percent for the C4.5 algorithm and 68 percent for the C4.5 algorithm. The Nave Bayes algorithm can predict up to 70% data transmission rates for both positive and negative signals.</span></em></p>Wowon PriatnaEka Nur A’iniJoni WartaAgus HidayatTyastuti Sri LestariRasim
Copyright (c) 2023 Wowon Priatna, Eka Nur A’ini, Joni Warta, Agus Hidayat, Tyastuti Sri Lestari, Rasim
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-1941798710.34306/conferenceseries.v4i1.614Breast Cancer Screening Application Based on Android with the Certainty Factor Method
https://aptikom-journal.id/conferenceseries/article/view/633
<p>According to Globocan records, in Indonesia in 2020 there were 396.314 new cancer cases. And 234.511 people were declared dead. Women are a group with a high risk of developing cancer. If cancer is detected at an early stage, this can increase the chance of cure to 80-90%. Early detection of cancer can be done using several methods, for example, for breast cancer, the method of checking can be using the SADANIS (Clinical Breast Examination) and SADARI (Self Breast Examination) methods. In this research, a mobile application will be developed that can be used as a guide in carrying out early cancer detection independently. The early detection system uses an Android-based expert system and certainty factor method. The case study in this research is on breast cancer. Based on the results of accuracy testing with expert diagnosis as a reference, an accuracy value of 90% was obtained. The inaccuracy of this expert system is 10% which can be caused by several possibilities, namely the expert's subjectivity in providing confidence values for disease symptoms or the small number of symptoms entered.</p>SupraptoKenty Wantri Anita
Copyright (c) 2023 Suprapto, Kenty Wantri Anita
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-1941889610.34306/conferenceseries.v4i1.633Redesigning the User Interface in the Mobile-Based Ngaji.AI Application Using the Design Thinking Method
https://aptikom-journal.id/conferenceseries/article/view/635
<p><em><span style="font-weight: 400;">Ngaji.AI is a mobile-based application that makes it possible to learn the recite very flexibly, wherever and whenever we can use it to learn the recite. This application is supported by artificial intelligence (AI) which provides direct and accurate assessments of how to recite Al-Quran verses properly and correctly and this application has been released on the Google Playstore platform and has been downloaded by more than 5 thousand. The Ngaji.AI application is faced with a crucial challenge, after direct observation of children and through the results of previous user input on Playstore, most of the input from users states that it needs to improve the User Interface (UI) design to make it easier to operate for children. The application of the Design Thinking method is an approach that prioritizes creativity and deep understanding of users and the problems they face and is indeed suitable for developing UI/UX of an application. Testing using the System Usability Scale (SUS) in the first test before the redesign got an average score of 50.25 and after the redesign got a significant score of 83.75. This reflects a significant increase in the level of satisfaction and ease for children in learning to recite the recite on the Ngaji.AI application.</span></em></p>AminudinAldiensyahGita Indah MarthasariIlyas NuryasinSaiful AmienGalih Wasis WicaksonoDidih Rizki ChandranegaraI'anatut Thoifah
Copyright (c) 2023 Aminudin, Aldiensyah, Gita Indah Marthasari, Ilyas Nuryasin, Saiful Amien, Galih Wasis Wicaksono, Didih Rizki Chandranegara, I'anatut Thoifah
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-19419710510.34306/conferenceseries.v4i1.635Risk Management for New Student Admission Information Systems at Higher Education using the Octave Allegro Approach
https://aptikom-journal.id/conferenceseries/article/view/637
<p><em><span style="font-weight: 400;">In the current digital era, especially in the world of education, the use of information and communication technology (ICT) is growing rapidly to meet needs. Universities rely on information systems, especially in managing new student admissions. The new student admission selection information system contains sensitive and dangerous prospective student data, as well as the risks that arise in the information system, limited to data processing during the new student admission process and the administration process, thus causing problems. The New Student Registration Information System is one of the services provided by the university as part of the new student registration process. Therefore, risk management is needed to minimize the impact of risks on maintaining data integrity, confidentiality, and availability. The aim of the research is to identify, analyze, and evaluate risks when using information systems for new student admission procedures. The approach used in risk management is Octave Allegro, and Octave Allegro is used to help evaluate information assets. The method used is data collection by conducting interviews with related sources. Based on the findings on the New Student Admissions site, there are 5 risk areas; 9 IT risks were identified as a result of potential risk analysis; and 4 IT risks were mitigated based on recommendations.</span></em></p>Titus KristantoRiza Akhsani Setyo PrayogaMuhammad NasrullahMustafa KamalWahyuddin S
Copyright (c) 2023 Titus Kristanto, Riza Akhsani Setyo Prayoga, Muhammad Nasrullah, Mustafa Kamal, Wahyuddin S
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-1941106 – 114106 – 11410.34306/conferenceseries.v4i1.637Predictions using Support Vector Machine with Particle Swarm Optimization in Candidates Recipient of Program Keluarga Harapan
https://aptikom-journal.id/conferenceseries/article/view/639
<p><em><span style="font-weight: 400;">Program Keluarga Harapan (PKH) is a conditional social assistance program as an effort to alleviate poverty which is allocated to poor vulnerable households. The determination of candidates for the Program Keluarga Harapan assistance recipients is still carried out in village meetings, so it takes quite a long time and there is potential for subjectivity in the assessment carried out by Village Government officials which can lead to differences of opinion between deliberation participants in assessing the eligibility of residents as PKH recipients. For this reason, this research will use an optimization method, namely Particle Swarm Optimization (PSO) to select the most optimal attribute out of 39 attributes. After that, a classification algorithm, namely the Support Vector Machine (SVM), was chosen to form a classification model for Candidates for Social Assistance for the Program Keluarga Harapan (PKH). The classification of Candidates for Social Assistance Recipients of the Program Keluarga Harapan (PKH) was carried out in 2 experiments, namely before and after optimization. Experiments before optimization give an accuracy value of 92.44%. While the Support Vector Machine accuracy value after optimization gives an accuracy value of 92.51%. Based on the experimental results, it can be concluded that the Particle Swarm Optimization method can increase the accuracy of the Support Vector Machine algorithm by 0.07%. And the best model is the Support Vector Machine after optimizing Particle Swarm Optimization by using the 17 most optimized attributes in determining class targets.</span></em></p>Arie Satia DharmaEvi Rosalina SilabanHana Maria Siahaan
Copyright (c) 2023 Arie Satia Dharma, Evi Rosalina Silaban, Hana Maria Siahaan
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-194111512110.34306/conferenceseries.v4i1.639Forward Chaining Algorithm on Informatics Graduate Job Recommendation System Based on MBTI Test
https://aptikom-journal.id/conferenceseries/article/view/641
<p><em><span style="font-weight: 400;">The Myers-Briggs Type Indicator (MBTI) is a method for identifying an individual's personality type based on the psychological theory of Carl Gustav Jung. In the context of computer science students, they often face challenges in planning their academic journey and determining the direction of their career development during their studies, causing confusion when it comes to choosing a career path in the field of computer science in the future. To address these challenges, the researcher has developed a web-based expert system using the PHP programming language. This expert system is designed to make decisions based on a collection of user responses, which are processed using the forward chaining method, ultimately providing the user's personality type along with suitable career choices. The primary objective of the expert system is to assist students in making decisions regarding their studies and future careers. Through this research, the researcher has produced a functioning website capable of efficiently processing user responses and generating decisions regarding personality types and career options. Thus, this study provides a solution to aid computer science students in planning their academic and career paths.</span></em></p>Jhonatan Laurensius TjahjadiYulia WahyuningsiPadmavati Darma Putri TanuwijayaRyan Putranda Kristianto
Copyright (c) 2023 Jhonatan Laurensius Tjahjadi, Yulia Wahyuningsih, Padmavati Darma Putri Tanuwijaya, Ryan Putranda Kristianto
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-194112213110.34306/conferenceseries.v4i1.641Detecting and Tracking Player in Football Videos Using Two-Stage Mask R-CNN Approach
https://aptikom-journal.id/conferenceseries/article/view/643
<p><em><span style="font-weight: 400;">Football is one of the most popular sports worldwide and capable of attracting the attention of millions of fans to a single match in the top leagues. The English Premier League, Spanish LaLiga, German Bundesliga, Italian Serie A, and French Ligue 1 are the five best leagues in the world today. There was an experiment where researchers want to analyze the efficiency and accuracy percentage of tracking and detection using the deep learning method of the Mask R-CNN model in classifying positive and negative X-Ray images in football matches. In this study, we applied Mask R-CNN for the segmentation and detection of football players. This model was based on two different backbones, namely ResNet101 and DenseNet. Both backbones produced accuracy values that were not significantly different, but the DenseNet approach performed better than ResNet101 based on testing results in the validation and testing sets. Based on comprehensive experiment results on the dataset, it has been shown that the Mask R-CNN approach with DenseNet can achieve better results compared to Mask R-CNN with ResNet101. Due to insufficient understanding of the characteristics of image types and the uneven distribution of various types of data sourced from random videos, there was still room for improvement in the trained model.</span></em></p>Amir Mahmud HuseinChalvinKalvintirta Ciptady CiptadyRaymond SuryadiMawaddah Harahap
Copyright (c) 2023 Amir Mahmud Husein, Chalvin, Kalvintirta Ciptady, Raymond Suryadi, Mawaddah Harahap
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-194113213810.34306/conferenceseries.v4i1.643Customer Segmentation: Transformation from Data to Marketing Strategy
https://aptikom-journal.id/conferenceseries/article/view/645
<p><em><span style="font-weight: 400;">Customer segmentation plays a crucial role in modern business strategies, enabling organizations to effectively target and personalize their marketing efforts and enhance customer relationships. Clustering algorithms have emerged as a powerful tool for segmenting customers based on their similarities and differences. We complement the data with an RFM model to support the clustering results. RFM, which stands for Recency, Frequency, and Monetary, is a model for segmenting customers based on their historical transaction data. This study aims to explore the concept of customer segmentation and the application of the RFM model combined with clustering algorithms in the real customer dataset of a company. It presents an overview of datasets, and introduces the RFM model and its components, emphasizing the significance of recency (how recently a customer made a purchase), frequency (how often a customer makes a purchase), and monetary value (the amount spent by a customer). It highlights the practicality of the RFM model in quantifying customer behavior and categorizing customers into distinct segments. It also explains popular clustering algorithms, analyzes experimental results, and concludes with future remarks on the potential of customer segmentation. We combine unsupervised (K-Means and DBSCAN clustering) and supervised machine learning methods to build customer clusters, label each cluster based on its characteristics, and propose a strategy for each cluster.</span></em></p>Luciana AbednegoCecilia Esti NugraheniAdelia Salsabina
Copyright (c) 2023 Luciana Abednego, Cecilia Esti Nugraheni, Adelia Salsabina
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-194113915210.34306/conferenceseries.v4i1.645Analysis of Information Security Culture at FMIPA Halu Oleo University Using Partial Least Squares-Structural Equation Modeling Method
https://aptikom-journal.id/conferenceseries/article/view/647
<p><em><span style="font-weight: 400;">This research aims to analyze the information security culture at FMIPA Halu Oleo University. The results of the analysis show that exogenous latent variables, such as information security awareness, the role of faculty leaders, and information security policies, have a significant positive impact on information security culture. The research results show that the security awareness variable has a positive effect (0.221) on the Information Security Culture variable. Apart from that, the top management variable also has a positive effect (0.185) on the Information Security Culture variable. Likewise, the security policy variable has a significant positive influence (0.233) on the Information Security Culture variable. These findings provide an in-depth understanding of the factors that influence the culture of information security in the FMIPA Halu Oleo University environment, which can be the basis for recommending improvements in increasing information system security at the faculty.</span></em></p>Elsa JulfianaNatalis RansiGusti Arviana Rahman
Copyright (c) 2023 Elsa Julfiana, Natalis Ransi, Gusti Arviana Rahman
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-194115316410.34306/conferenceseries.v4i1.647Comparative Analysis of the Performance of the Decision Tree and K-Nearest Neighbors Methods in Classifying Coffee Leaf Diseases
https://aptikom-journal.id/conferenceseries/article/view/649
<p><em><span style="font-weight: 400;">This study aimed to develop and compare classification models utilizing Decision Tree and K-Nearest Neighbors (KNN) in the detection of diseases in coffee leaf images. The dataset comprises coffee leaf images categorized into four different disease types, namely Nodisease, Miner, Phoma, and Rust. To facilitate model training and testing, the dataset was divided into training and validation data using a cross-validation approach. Both the Decision Tree and KNN models underwent meticulous parameter tuning. The experimental results reveal that the Decision Tree model achieved an accuracy rate of 98.20% on the validation data, while the KNN model achieved an accuracy rate of 75.01%. Furthermore, the Decision Tree model exhibited an AUC of 0.9879, recall of 0.9820, precision of 0.9835, and an F1-score of 0.9819 on the validation data. Conversely, the KNN model achieved an AUC of 0.9465, recall of 0.7501, precision of 0.7569, and an F1-score of 0.7485. These findings suggest that the Decision Tree model surpasses the KNN model in accurately detecting coffee leaf diseases, as demonstrated by higher accuracy and other evaluation metrics. However, the relevance of the KNN model remains contingent on application requirements and modeling preferences. These outcomes may contribute to the development of automated systems for disease detection in coffee plants, ultimately promoting more sustainable agricultural practices.</span></em></p>SuryadiMurhaban MurhabanRivansyah Suhendra
Copyright (c) 2023 Suryadi, Murhaban, Rivansyah Suhendra
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-194116517110.34306/conferenceseries.v4i1.649Implementation of the Naive Bayes Algorithm to Predict the Safety of Heart Failure Patients
https://aptikom-journal.id/conferenceseries/article/view/651
<p><em><span style="font-weight: 400;">Heart disease stands as a prominent contributor to global mortality, as indicated by data released by the World Health Organization (WHO). In 2019 alone, an estimated 17.9 million individuals succumbed to cardiovascular disease, accounting for 32% of all worldwide deaths. Of these fatalities, 85% were attributed to heart disease and stroke. Individuals harboring the potential for heart failure often persist in unhealthy lifestyles, regardless of their awareness of underlying heart conditions. To address this issue, the research explores the application of machine learning to identify an optimal method for classifying heart failure patients, employing the Naive Bayes technique. This algorithm has found extensive use in the health sector, demonstrating success in classifying various conditions such as hepatitis, stroke, respiratory infections, and more. The Naive Bayes algorithm, applied in this study, exhibited notable accuracy, precision, sensitivity, and overall classification efficacy. Specifically, the classification accuracy for heart failure patients reached 74.58%, the precision level was 97.67%, sensitivity achieved 75%, and the AUC (Area Under ROC Curve) stood at 0.857, indicating excellent classification within the 0.80 to 0.90 range. These findings can serve as an early warning system for individuals at risk of heart failure.</span></em></p>Okky Putra BarusKevil LauwrenJefri Junifer PangaribuanRomindo
Copyright (c) 2023 Okky Putra Barus, Kevil Lauwren, Jefri Junifer Pangaribuan, Romindo
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-194117217710.34306/conferenceseries.v4i1.651Integration of Transformer Model Text Summarization and Text-to-Speech in Helping Document Understanding in the Bukudio Application
https://aptikom-journal.id/conferenceseries/article/view/653
<p><em><span style="font-weight: 400;">The need for effective, accurate and precise understanding of information will provide optimization of the decision-making process, increase knowledge and quality of life. Understanding information in relation to the document summarization process, if done manually, sometimes takes quite a long time. Text summarization techniques which are useful as document summarizers have been developed and applied to various things such as summarizing important documents, news texts or customer feedback. In this article, text summarization using the text rank method and transformer modeling integrated with text to speech techniques is developed in the Bukudio application, which is an application that provides audio versions of book documents in the application database. Based on the test results, the evaluation process was carried out using the Rouge method and gave the best results in calculating the Rouge 1 overlap monogram resulting in 0.523 for the F1 Score value, 0.434 for the precision value and 0.659 for the recall value. This research will be developed using other methods so that not only files in PDF document format can be processed, but other EPUB (Electronic Publication) files.</span></em></p>Ivana Lucia KharismaKamdan KamdanAnggun FerginaTofik HidayatMoh. Abd. Aziz HidayatMuhamad MuslihAdhitia Erfina
Copyright (c) 2023 Ivana Lucia Kharisma, Kamdan, Anggun Fergina, Tofik Hidayat, Moh. Abd. Aziz Hidayat, Muhamad Muslih, Adhitia Erfina
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-194117818610.34306/conferenceseries.v4i1.653Application System for Setting Values on High Voltage Power Supply Using MCP4725 Module Based on ATmega328P Microcontroller
https://aptikom-journal.id/conferenceseries/article/view/655
<p><em><span style="font-weight: 400;">Applications of power supply systems to supply sensors that require high voltage values are widely available in the market in the form of modules. However, in general, setting the voltage value is open by providing a voltage value from the potentiometer or trimmer component which is rotated manually. This becomes less flexible because the operator must always be nearby. The solution option is to implement automatic regulation via a potentiometer attached to an interface component connected to the microcontroller via a serial communication line called I</span></em><em><span style="font-weight: 400;">2</span></em><em><span style="font-weight: 400;">C. Furthermore, the microcontroller is programmed to receive regulatory commands and monitor the desired voltage value from a computer or mobile phone. This study uses the ATmega328P microcontroller, the MCP4725 DAC module and the CA12P-5TR series HV module from EMCO products. The results of this study are the design, implementation and prototype scheme.</span></em><em><span style="font-weight: 400;"><br /></span></em></p>Mohammad AminWahyu Widji PamungkasDjoko Harsono
Copyright (c) 2023 Mohammad Amin, Wahyu Widji Pamungkas, Djoko Harsono
https://creativecommons.org/licenses/by/4.0/
2023-12-192023-12-194118719210.34306/conferenceseries.v4i1.655