2 research outputs found
ANALISIS KLASTERING DAMPAK LINGKUNGAN BERDASARKAN KONSUMSI ENERGI PERUSAHAAN BERBASIS INDUSTRI 4.0 MENGGUNAKAN METODE CRISP-DM
No full textThe growth of energy consumption worldwide has experienced a significant increase in the past two decades. The increase in energy consumption in a company indicates that the company generates more carbon dioxide (CO2) emissions than usual. Excessive carbon emissions have a significant impact on human health and the environment. According to the World Health Organization (WHO), greenhouse gas emissions resulting from the extraction and combustion of fossil fuels are major contributors to climate change and air pollution. It is necessary to analyze what factors contribute to high carbon emissions. This study uses the CRISP-DM (Cross-Industry Standard Process for Data Mining) method. The K-Means algorithm will be used to cluster the features that influence high carbon emissions. The feature selection process for K-Means uses Pearson correlation. The clustering model results in good evaluation scores using the Silhouette evaluation metric. Subset data 1 obtained a Silhouette score of 0.744, and subset data 2 obtained a Silhouette score of 0.7629. The evaluation results indicate that the K-Means model works quite well in creating clusters.Pertumbuhan konsumsi energi didunia mengalami peningkatan yang cukup signifikan dalam dua dekade terakhir. Bertambahnya konsumsi energi pada suatu perusahaan, menandakan bahwa perusahaan menghasilkan emisi karbon CO2 lebih banyak dari biasanya. Emisi karbon yang berlebihan memberikan dampak yang besar terhadap kesehatan manusia dan lingkungan. Menurut World Health Organization (WHO), Emisi gas rumah kaca yang dihasilkan dari ekstraksi dan pembakaran bahan bakar fosil merupakan kontributor utama terhadap perubahan iklim dan polusi udara. Perlu untuk dilakukan analisis terkait hal apa yang menentukan jumlah emisi karbon yang tinggi. penelitian ini menggunakan metode CRISP-DM (Cross-Industry Standard Process for Data Mining). Algoritma K-Means akan digunakan untuk mengelompokkan fitur yang mempengaruhi tingginya emisi karbon. Proses penentuan fitur yang akan digunakan dalam K-Means menggunakan pearson correlation. Hasil model clustering mendapatkan nilai evaluasi yang baik menggunakan metrik evaluasi silhouette. Pada subset data 1 mendapatkan nilai silhouette 0.744 dan pada subset data 2 mendapatkan nilai silhouette 0.7629. Hasil evaluasi menunjukan bahwa model K-Means bekerja dengan cukup baik dalam membuat cluster
Perbandingan Random Forest dan Convolutional Neural Network dalam Memprediksi Peralihan Pelanggan
No full textThe rapid growth of the telecommunications industry has increased competition among companies for customers. As a result, customers often switch to other services or terminate their subscriptions. Retaining customers is very important as it is 10 times cheaper than acquiring new customers. This study compares Random Forest (RF) and Convolutional Neural Network (CNN) algorithms in predicting customer switching, using Correlation-based Feature Selection (CFS) and Recursive Feature Elimination (RFE) for data partitioning. Model evaluation using Confusion Matrix and Area Under Curve (AUC). The evaluation results show that the performance of CNN models with optimization parameters is superior. Using the CFS dataset, the test data evaluation results yielded an accuracy of 98%, AUC of 0.96, precision of 99%, recall of 92%, and F1-score of 96%. The best tuning result for CNN is achieved with three combinations of filter and kernel sizes {[64, 7], [32, 3], [16, 2]} and a pool size of 2. A limitation of this research is determining how to compare the two algorithms being evaluated effectively. Both use different approaches, namely Supervised Learning and Deep Learning
