Claim Missing Document
Check
Articles

Found 6 Documents
Search

Implementasi Algoritma K-Nearest Neighbour dalam Memprediksi Stok Sepeda Motor Desyanti, Desyanti; Wulandari, Denok
Building of Informatics, Technology and Science (BITS) Vol 4 No 3 (2022): December 2022
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v4i3.2579

Abstract

PT. Dasatama Cemerlang Motor is a company engaged in the automotive sector. With the increasingly fierce competition among the automotive industry, companies are required to be able to handle inter-industry competition. Sales system PT. Dasatama Cemerlang Motor uses a cash or credit system. For every motorcycle sale, the admin inputs sales data using Ms.Excel. Even though Ms.Excel has many features and functions that are used to process numbers, it cannot predict annual motorcycle sales for the future as a reference in marketing strategy. Because of that, forecasting is needed which will help the company to find out the trend in the number of motorcycle sales for the coming year. The KNN algorithm is one of the methods used for classification analysis, but in the last few decades the KNN method has also been used for prediction. KNN looks for the shortest distance between the data to be evaluated and its K closest neighbors. The results achieved in this study resulted in the number of motorcycles for each brand that will be sold in 2022 obtained from the addition of 5 motorcycles for each sale of each motorcycle brand. Based on the research results, the prediction accuracy rate using the KNN method is 97%.
Komparasi Algoritma Machine Learning dalam Klasifikasi Kanker Payudara Afiatuddin, Nurfadlan; Wicaksono, M Teguh; Akbar, Vitto Rezky; Rahmaddeni, Rahmaddeni; Wulandari, Denok
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 2 (2024): April 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i2.7457

Abstract

Every year, millions of women are faced with a serious global health issue: breast cancer. This research aims to improve the efficiency of breast cancer classification using machine learning. One of the main challenges encountered is the imbalance between the number of malignant and benign cases in the dataset. Therefore, this study aims to compare the performance of several machine learning algorithms in classifying breast cancer, such as Decision Tree, Naive Bayes, K-Nearest Neighbors, Logistic Regression, and Random Forest. Preprocessing data, dividing data with various ratios, and testing various classification algorithms are the techniques used in this research. The dataset used originates from the Wisconsin Breast Cancer Diagnosis dataset from the Kaggle platform. The Synthetic Minority Over-Sampling Technique (SMOTE) is used to achieve balance in the proportions of imbalanced classes. After hyperparameter tuning, Logistic Regression showed the best performance with accuracy reaching 100% in several situations. This study concludes that the use of machine learning, especially with techniques for handling class imbalance, can improve the ability to detect breast cancer early. Additionally, this research also helps understand the best algorithms to improve accuracy in classifying breast cancer, providing support for healthcare professionals in early diagnosis, and enhancing the quality of patient care.
Enhancing Multiple Linear Regression with Stacking Ensemble for Dissolved Oxygen Estimation Rahmaddeni, Rahmaddeni; Wicaksono, M. Teguh; Wulandari, Denok; Agustriono, Agustriono; Ibrahim, Sang Adji
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol 24 No 1 (2024)
Publisher : LPPM Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v24i1.4280

Abstract

Maintaining optimal dissolved oxygen levels is essential for aquatic ecosystems, yet industrial and domestic waste has led to a global decline in dissolved oxygen. Traditional measurement methods, such as oxygen meters and Winkler titration, are often costly or time-consuming. This study aims to improve the Root Mean Square Error, Mean Absolute Error, and R2 values for estimating dissolved oxygen levels. The research method uses Multiple Linear Regression with various training and testing data splits, both before and after applying polynomial features. The model is further optimized using a stacking technique, with Random Forest Regressor and Gradient Booster Regressor as base models.The results show that the best model was achieved using the stacking ensemble technique with a 90:10 data split and polynomial features, yielding a Root Mean Square Error of 1.206, Mean Absolute Error of 0.990, and R2 of 0.670. This model has also met the assumptions of linear regression, such as residual normality, homoscedasticity, and no autocorrelation of residuals. This study concluded that the ensemble stacking technique and the addition of polynomial features could improve the model in estimating dissolved oxygen values and also contribute by providing an accessible user interface using the Gradio Framework, allowing users to estimate dissolved oxygen levels effectively.
Pengabdian Sebagai Juri Dalam Lomba Memasak Pada Pekan Event Az Zuhra Spektakuler Hafsah, Hafni; Suwarty, Suwarty; Afwan, Zul; Wulandari, Denok; Willyansyah, Willyansyah; Azis, Syarfi; Syahrul, Syahrul
Dedikasi: Jurnal Pengabdian Pendidikan dan Teknologi Masyarakat Vol. 1 No. 2 (2023): Dedikasi 2023
Publisher : Institut Teknologi Pendidikan Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/dedikasi.v1i2.16

Abstract

Kegiatan Lomba memasak wali murid yang diselenggarakan di sekolah Brilliant Islamic School merupakan bagian dari acara Pekan Event Azzuhra Group Spektakuler . Event ini merupakan kegiatan pengabdian masyarakat dimana Amik (Akademi Manajemen Ilmu Komputer) Tri Dharma berpartisipasi dalam melakukan penjurian dalam lomba. Lomba memasak ini diikuti oleh wali murid dari 18 (delapan) kelas atau kelompok, dan setiap kelompok terdiri dari 5 (lima) orang. Adapun kriteria penilaian didasarkan pada beberapa unsur yaitu antara lain kebersihan, team work, plating dan rasa yang merupakan poin tertinggi dalam lomba memasak. Secara keseluruhan event berjalan dengan lancar. Kemampuan peserta wali murid secara bersama-sama dalam sebuah kelompok atau tim dalam mahami apa yang lebih dan apa yang kurang dalam suatu masakan cukup baik. Kemudian, bagi pihak sekolah terbangun kepercayaan dengan AMIK Tri Dharma karena mengundang pihak diluar sekolah untuk melakukan penilaian. Terkait penilaian secara rata-rata, menunjukkan bahwa peserta mempunyai kreativitas yang lumayan bagus, hanya terkadang terbentur dengan dua unsur lainnya yaitu kebersihan dan tampilan makanan. Kesesuaian tampilan dengan rasa membuat makanan akan terasa lebih nikmat, serta dapat menggugah selera untuk segera menikmati makanan tersebut. Dilihat dari persiapan peserta yang belum maksimal, pada umumnya terjadi hal yang stagnan di dalam tampilan dan kebersihan. Tidak adanya variasi tampilan makanan membuat hasil makanan menjadi kurang variatif. Namun demikian, event lomba memasak ini dimaksudkan untuk menjalin silaturrahmi baik itu antara sesama wali murid, maupun dengan pihak sekolah maupun AMIK Tri Dharma. Disamping itu juga, melalui penilaian bagi peserta merupakan koreksi bagaimana tindak lanjut untuk mengembangkan potensi yang ada dalam diri dan kerjasama tim.
ANALISIS PERFORMA NAIVE BAYES DAN SVM TERHADAP SENTIMEN TEKS MEDIA SOSIAL DENGAN WORD2VEC DAN SMOTE Saputra, Juliandri; Maryani, Lily; Rahmaddeni; Wulandari, Denok; Eka, Wisnu
Jurnal INSTEK (Informatika Sains dan Teknologi) Vol 10 No 1 (2025): APRIL
Publisher : Department of Informatics Engineering, Faculty of Science and Technology, Universitas Islam Negeri Alauddin, Makassar, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/instek.v10i1.54889

Abstract

Penelitian ini membandingkan performa algoritma Naive Bayes dan Support Vector Machine (SVM) dalam klasifikasi sentimen teks dari media sosial. Dataset berisi 736 unggahan dari Facebook, Instagram, dan Twitter yang telah dilabeli sebagai positif, netral, atau negatif. Proses prapemrosesan mencakup pembersihan teks, normalisasi, tokenisasi, penghapusan kata umum, dan stemming. Fitur diekstraksi menggunakan Word2Vec, sedangkan ketidakseimbangan kelas diatasi dengan Synthetic Minority Oversampling Technique (SMOTE). Model dilatih dan dievaluasi menggunakan metrik akurasi, presisi, recall, dan F1-score, serta divalidasi melalui K-Fold Cross-Validation. Hasil menunjukkan bahwa algoritma SVM mencapai akurasi 88,85% dan F1-score 88,86%, lebih unggul dibandingkan Naive Bayes dengan akurasi 72,64% dan F1-score 72,26%. SVM juga menunjukkan konsistensi dalam memprediksi sentimen netral, yang menjadi kelemahan Naive Bayes. Temuan ini memperkuat posisi SVM sebagai algoritma yang lebih efektif untuk analisis sentimen teks media sosial.
Enhancing Multiple Linear Regression with Stacking Ensemble for Dissolved Oxygen Estimation Rahmaddeni, Rahmaddeni; Wicaksono, M. Teguh; Wulandari, Denok; Agustriono, Agustriono; Ibrahim, Sang Adji
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 24 No. 1 (2024)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v24i1.4280

Abstract

Maintaining optimal dissolved oxygen levels is essential for aquatic ecosystems, yet industrial and domestic waste has led to a global decline in dissolved oxygen. Traditional measurement methods, such as oxygen meters and Winkler titration, are often costly or time-consuming. This study aims to improve the Root Mean Square Error, Mean Absolute Error, and R2 values for estimating dissolved oxygen levels. The research method uses Multiple Linear Regression with various training and testing data splits, both before and after applying polynomial features. The model is further optimized using a stacking technique, with Random Forest Regressor and Gradient Booster Regressor as base models.The results show that the best model was achieved using the stacking ensemble technique with a 90:10 data split and polynomial features, yielding a Root Mean Square Error of 1.206, Mean Absolute Error of 0.990, and R2 of 0.670. This model has also met the assumptions of linear regression, such as residual normality, homoscedasticity, and no autocorrelation of residuals. This study concluded that the ensemble stacking technique and the addition of polynomial features could improve the model in estimating dissolved oxygen values and also contribute by providing an accessible user interface using the Gradio Framework, allowing users to estimate dissolved oxygen levels effectively.