IRPI Publisher Journals (Institute of Research and Publication Indonesia)
Not a member yet
1012 research outputs found
Sort by
Convolutional Neural Networks Using EfficientNetB0 Architecture and Hyperparameters on Skin Disease Classification
Full text linkSkin diseases are often caused by air temperature, environmental hygiene and personal hygiene, with symptoms such as itching, pain and redness. Contributing factors include exposure to chemicals, sunlight, infections, a weak immune system, microorganisms, and poor personal hygiene. This study uses Convolutional Neural Networks (CNN) with EfficientNetB0 model and hyperparameter optimization for skin disease classification. The dataset consists of 1158 images that have been divided into eight categories, with 80% for training data and 20% for test data. Data augmentation is applied to increase the variety of training data. Various combinations of hyperparameters such as learning rate, optimizer (Adamax and AdamW), and activation function (ReLU and LeakyReLU) were tested in 16 training scenarios. The best results was obtained from the third scenario with the original dataset, Adamax optimizer, ReLU activation function, and 0.01 learning rate, which gave a testing accuracy of 95.70%. The model also showed good generalization and low loss values. Confusion matrix analysis and classification report showed high accuracy in skin disease classification. This study concludes that EfficientNetB0 with proper hyperparameter optimization can improve the accuracy and effectiveness of skin disease diagnosis
Obesity Prediction Using Machine Learning Algorithms
Full text linkThis study aims to develop a prediction model for obesity levels by utilizing five machine learning algorithms, namely K-Nearest Neighbors (K-NN), Naïve Bayes Classifier (NBC), Decision Tree, Random Forest, and Support Vector Machine (SVM). The data used in this study were obtained from Kaggle, consisting of 2111 data with 17 attributes covering lifestyle and demographic factors. The research process involved data collection, pre-processing, data division using the Holdout Split method (70% training data and 30% testing data), and the application of machine learning algorithms. Performance evaluation used accuracy, precision, recall, and F1 score metrics. The results showed that the Random Forest algorithm had the best performance with an accuracy of 92.29%, followed by Decision Tree at 90.54%, K-NN at 83.44%, and NBC and SVM which reached 59.15% and 59.08%, respectively. Confusion matrix analysis revealed that NBC and SVM had difficulty distinguishing certain obesity classes. Based on these findings, it can be concluded that Random Forest is the most effective algorithm in predicting obesity levels. The results of this study are expected to contribute to developing a more accurate obesity prediction system that can be implemented in the real world
From Comments to Insight: Predictive Classification of Organizational Cultural Entropy Using SBERT, K-Means, and Logistic Regression
No full textThis study aims to develop a machine learning-based predictive model based on clustered data to identify cultural entropy in organizations through the analysis of open-ended comments on employee perception surveys of superiors. energy used for unproductive activities in a work environment. Entropy shows the level of conflict, friction and frustration in the environment. With a text mining approach, answers to open-ended questions in the cultural entropy survey were processed with Sentence-BERT and clustered using the K-Means algorithm into two categories, namely cultural entropy and non-cultural entropy. The dataset that already has labels from the clustering results is used to develop a classification model. The algorithms used are Random Forest, Logistic Regression, and Support Vector Machine (SVM), which are evaluated through accuracy, precision, recall, and F1-score metrics and a confusion matrix. The results show that Logistic Regression provides the best performance with an accuracy of 0.985, a precision of 1.00, and an F1-score of 0.978 without any classification errors. These findings indicate that the clustering approach followed by machine learning-based predictive is effective in identifying organizational cultural entropy. This can be used to design appropriate interventions and as an early detection system for cultural entropy in human resource managemen
Analisis Sentimen Publik di Platform X Pasca Skandal Bahan Bakar Minyak Oplosan Menggunakan Algoritma Naïve Bayes: Public Sentiment Analysis on Platform X Following the Mixed Fuel Scandal Using the Naïve Bayes Algorithm
No full textSkandal BBM oplosan yang mencuat pada awal 2025 memicu gelombang reaksi dari masyarakat yang disuarakan melalui platform X. Penelitian ini ditujukan untuk mengevaluasi sentimen publik terkait kasus tersebut dengan menggunakan algoritma Naïve Bayes sebagai metode analisis. Proses analisis dilakukan dengan teknik scraping terhadap 2.351 tweet yang relevan, dilanjutkan dengan preprocessing teks. Label sentimen ditentukan secara otomatis menggunakan metode VADER, sementara representasi fitur dilakukan dengan teknik TF-IDF untuk meningkatkan kualitas klasifikasi. Selanjutnya, data dibagi menjadi data pelatihan dan data pengujian dengan perbandingan 80:20, kemudian diklasifikasikan menggunakan algoritma Multinomial Naïve Bayes. Hasil klasifikasi menunjukkan bahwa algoritma mampu mengidentifikasi sentimen negatif dengan recall tertinggi sebesar 75%, meskipun akurasi keseluruhan hanya mencapai 57%. Temuan ini menunjukkan bahwa pendekatan ini cukup andal dalam menangkap opini kritis masyarakat, namun masih perlu pengembangan untuk mengenali sentimen positif dan netral secara akurat. Penelitian selanjutnya disarankan untuk membandingkan algoritma Naïve Bayes dengan model lain seperti SVM atau Random Forest guna meningkatkan akurasi klasifikasi
Klasifikasi Komposisi Menu Makanan Olahan Terhadap Standar Gizi Balita Menggunakan Random Forest: Classification of Processed Food Menu Compositions Against Toddler Nutrition Standards Using Random Forest
No full textPeningkatan kesadaran masyarakat akan pentingnya asupan gizi seimbang, khususnya pada anak usia dini, menjadi aspek krusial dalam upaya pencegahan malnutrisi dan masalah kesehatan terkait. Penelitian ini bertujuan untuk mengklasifikasikan komposisi menu makanan olahan terhadap standar gizi balita menggunakan pendekatan data mining dengan algoritma Random Forest. Dataset yang digunakan memuat kandungan nutrisi menu yang divalidasi terhadap standar Angka Kecukupan Gizi (AKG) untuk anak usia 1–5 tahun. Klasifikasi dilakukan ke dalam tiga kategori: seimbang, tidak seimbang, dan berlebihan. Penelitian melibatkan tahapan preprocessing data, feature selection, normalisasi, serta pelatihan model menggunakan Random Forest. Evaluasi menggunakan akurasi, presisi, recall, serta f1-score. Hasil pengujian diperoleh algoritma bahwa Random Forest menghasilkan kinerja terbaik dengan akurasi 90%. Dari 136 menu, 9 diklasifikasikan sebagai seimbang, 59 tidak seimbang, dan 68 berlebihan. Penelitian ini membuktikan jika algoritma Random Forest bisa dijadikan alat yang efektif dalam pemantauan gizi balit
Integrasi Internet of Things dan Web untuk Monitoring Kendali Irigasi Tates Secara Real Time: Internet of Things and Web Integration for Real-Time Monitoring and Control of Tates Irrigation
No full textPenelitian ini membahas pengembangan sistem irigasi tetes berbasis Internet of Things (IoT) yang terintegrasi dengan aplikasi web untuk monitoring dan kendali secara real-time. Sistem dirancang menggunakan mikrokontroler ESP32 yang terhubung dengan sensor ultrasonik untuk memantau ketinggian air dan pupuk, serta sensor soil moisture untuk mengukur kelembapan tanah. Data yang diperoleh dikirimkan ke server via protokol MQTT dan disimpan dalam basis data MySQL, kemudian ditampilkan melalui aplikasi web dalam bentuk numerik dan grafik. Hasil pengujian menunjukkan kinerja sistem yang andal, dimana sensor ultrasonik memiliki akurasi tinggi dengan error rata-rata 0.67%, sedangkan sensor soil moisture memiliki error di bawah 7%. Pompa air merespons perintah secara akurat baik secara manual maupun otomatis berdasarkan kondisi kelembapan tanah. Mode local server memungkinkan akses dashboard tanpa koneksi internet, sementara antarmuka yang sederhana dan user-friendly memudahkan pengguna dalam pemantauan. Integrasi grafik sensor memperjelas perubahan data secara visual, sehingga mempercepat proses pengambilan keputusan. Secara keseluruhan, sistem ini terbukti mampu meningkatkan efisiensi penggunaan air hingga 30% dan meminimalkan intervensi manual, sehingga menjadi solusi praktis dalam penerapan teknologi IoT untuk mendukung pertanian moder
Valuation and Action Recommendations on the Control Panel of PT Bukaka Teknik Utama Duri's Pumping Unit Using Failure Mode and Effect Analysis (FMEA) : Valuasi dan Rekomendasi Tindakan Pada Panel Kontrol Pumping Unit PT Bukaka Teknik Utama Site Duri Menggunakan Failure Mode and Effect Analysis(FMEA)
No full textPT Bukaka Teknik Utama Site Duri is a company engaged in the oil and gas equipment sector and collaborates with PT Chevron Pacific Indonesia in managing sucker rod pump type pumping units for crude oil extraction processes. The pumping units are powered by 75 HP electric motors that are controlled and monitored through a control panel. The control panel plays an important role in maintaining operational reliability and safety as it is equipped with various protection components, such as overload, over voltage, over current, and thermal protection. However, based on operational data, there are still control panel malfunctions that cause pump operations to stop and daily oil production targets to not be achieved, as well as increasing the risk of damage to the drive motor. This study aims to conduct a risk assessment and provide recommendations for improvements to the pumping unit control panel using the Failure Mode and Effect Analysis (FMEA) method. The FMEA analysis results show that the contactor and overvoltage components have the highest risk levels, while the fuse and MCB have the lowest risk levels. The recommended actions include replacing components with higher specifications and implementing preventive measures such as repairing the grounding system and adding protection against moisture and dust. The implementation of these recommendations is expected to reduce the failure rate and improve the reliability of the control panel in the next operational period.PT Bukaka Teknik Utama Site Duri adalah perusahaan yang bergerak di bidang peralatan minyak dan gas dan bekerja sama dengan PT Chevron Pacific Indonesia dalam pengelolaan pumping unit tipe sucker rod pump untuk proses ekstraksi minyak mentah. Pumping unit digerakkan oleh motor listrik berdaya 75 HP yang dikendalikan dan dimonitor melalui panel kontrol. Panel kontrol memiliki peran penting dalam menjaga keandalan dan keselamatan operasi karena dilengkapi dengan berbagai komponen proteksi, seperti overload, overvoltage, overcurrent, dan thermal protection. Namun, berdasarkan data operasional, masih terjadi kegagalan fungsi panel kontrol yang menyebabkan terhentinya operasi pompa dan tidak tercapainya target produksi minyak harian serta meningkatkan risiko kerusakan pada motor penggerak. Penelitian ini bertujuan untuk melakukan valuasi risiko dan memberikan rekomendasi tindakan perbaikan pada panel kontrol pumping unit menggunakan metode Failure Mode and Effect Analysis (FMEA). Hasil analisis FMEA menunjukkan bahwa komponen contactor dan overvoltage memiliki tingkat risiko tertinggi, sedangkan fuse dan MCB memiliki tingkat risiko terendah. Rekomendasi tindakan yang diberikan adalah meliputi penggantian komponen dan/atau penggantian dengan spesifikasi yang lebih tinggi, sedangkan rekomendasi penerapan tindakan preventif seperti perbaikan sistem grounding dan penambahan proteksi terhadap kelembaban dan debu. Implementasi rekomendasi ini diharapkan dapat menurunkan tingkat kegagalan operasi dan meningkatkan keandalan panel kontrol pada masa operasional berikutnya
Learning the Right Attitude and Skills to Grow as a Future Leader : Mempelajari Sikap dan Keterampilan yang Tepat untuk Tumbuh sebagai Pemimpin Masa Depan
No full textThis Community Service (PKM) activity aims to improve the leadership competency of prospective student council (OSIS) administrators at SMK Tzu Chi Cengkareng through the training "Learning the Right Attitude and Skills to Grow as a Future Leader." The background of the activity is based on the importance of effective leadership amidst global change and limited internal school resources for developing non-technical skills. This training focuses on instilling ethics, a sense of ownership, responsibility, teamwork, and effective communication. The implementation method involves interactive lectures, group discussions, and simulations. Pre-test and post-test evaluation results from 25 respondents showed a significant increase in knowledge comprehension (from 30% to 86% correct answers) and a positive attitude change (a 56% increase in positive attitude scores). The conclusion indicates that this PKM successfully achieved its goal of developing more reflective, collaborative, and responsible young leaders. Therefore, this training model is recommended for leadership development programs in schools
Implementation of Online-Based Marketing for MSMES in Pasirhandap and Pagerwangi Areas: Implementasi Pemasaran UMKM Berbasis Online di Kawasan Pasirhandap, Pagerwangi
No full textThis community service program was carried out as an effort to empower Micro, Small, and Medium Enterprises (MSMEs) in the Pasirhandap area, Pagerwangi Village, through digital-based marketing assistance. The main problem faced by MSME actors in this area is limited access to digital technology and a lack of understanding of modern promotional strategies. Therefore, this program was designed to provide practical and applicable training, ranging from brand identity creation, utilization of digital platforms such as Shopee and Grab Merchant, to education on the importance of business legality. The program was implemented in three stages: an initial seminar, technical training, and direct mentoring. The results of the activity showed a significant improvement in participants’ understanding and ability to implement digital marketing strategies, as well as increased awareness of the importance of innovation and technological adaptation in the development of small businesses
Introducing and Utilizing E-Reading Tools for Junior High School Students through the Read Along by Google Application : Pengenalan dan Pemanfaatan E-Reading Tools untuk Siswa SMP melalui Aplikasi Read Along by Google
Full text linkThe development of digital technology presents significant opportunities to enhance students' literacy, particularly in learning English. However, the integration of technology in school environments remains limited, and many students have not yet utilized digital tools as productive learning media. This Community Service Program (PKM) aimed to increase junior high school students’ interest and reading comprehension in English by introducing the Read Along by Google application. The program was conducted at MTs As-Syifa, West Bandung Regency, involving 50 students as participants. The method employed was the Asset-Based Community Development (ABCD) approach through interactive seminars, application simulations, and reflective discussions. The results showed high enthusiasm among students in using the Read Along application, with positive responses toward its interactive features. Besides boosting reading motivation, the activity also encouraged students to integrate technology into their daily learning habits. Therefore, the asset-based and technology-oriented approach proved effective in strengthening digital literacy and supporting English learning at the junior high school level