Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : International Journal for Applied Information Management

Enhancing Minority Class Prediction in Wearable Sensor-Based Activity Recognition Using SMOTE Oversampling Sarmini; Widiawati, Chyntia Raras Ajeng; Yunita, Ika Romadoni
International Journal for Applied Information Management Vol. 5 No. 1 (2025): Regular Issue: April 2025
Publisher : Bright Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/ijaim.v5i1.95

Abstract

Wearable sensor-based activity recognition has become increasingly important in various domains, particularly healthcare and sports. However, a significant challenge in this field is the issue of class imbalance, where minority activity classes are underrepresented compared to majority classes in datasets. This imbalance leads to biased classifiers that struggle to accurately identify rare but critical activities, which is especially problematic in health monitoring scenarios. This study evaluates the effectiveness of the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance in the mHealth dataset, which contains multi-sensor data from wearable devices placed on the chest, left ankle, and right lower arm. We employ the XGBoost classifier combined with SMOTE oversampling to improve recognition performance for minority classes. Model evaluation is conducted using precision, recall, F1-score, Area Under the Precision-Recall Curve (AUC-PR), ROC curve, and calibration analysis. The results demonstrate that applying SMOTE improves minority class recall from 0.75 to 0.85 and F1-score from 0.796 to 0.865, despite a slight decrease in overall accuracy from 97% to 96.5%. The AUC-PR also increases from 0.81 to 0.88, indicating a better balance in detecting minority and majority classes. Calibration curves reveal that probability estimates still require refinement to be more reliable for decision-making. This study confirms the efficacy of SMOTE in mitigating class imbalance in wearable sensor-based activity recognition and provides valuable insights for developing more accurate and fair health monitoring systems.
Co-Authors Abdul Azis Abdul Khamid Agung Dwi Bahtiar El Rizaq Agus Suprijono Agus Suprijono AINUN NAFISAH Aminkun Imam Rafii Anita, Nur ANNA NOORDIA Ariningrum, Desrina Aris Rakhmadi Asnira Astika AyuningTyas, Astika Aswar Aswar BAYU SEGARA PUTRA, GEDE Budi Santosa Budiarto, Mochamad Kamil Budiman, Kholiq Catur Ambyah Budiono Cevy Amelia Chablullah Wibisono Chyntia Raras Ajeng Widiawati DEVI ANITA SARI Dilla Putri Liktaf DISCA AYU PANCA RISTNA Dominggas Talaksoru ENI FITRIA ENY ZUBAIDAH Fadila Kurniawati Fadratul Sharly Faturama, Rafi Fitri Sukmawati Gading Gamaputra Iman Pasu Marganda Hardianto Purba Indradewa, Rhian Javadi, Milad Jefferi bin Haji Mat Lazim , Mohamed Katon Galih Setyawan Khalid, Ferdila Khalimatus Sadiyah Kusmanto, Hari Lailatin Rohmatun Nisa Liza Rickiany Marzuqi, Muhammad Ilyas MAYA MUSTIKA KARTIKA SARI, MAYA Maya Richmayati Mufid, M. Khoirul Annas Waladul Muhammad Hilman Fikri Muhammad Ilyas Marzuqi Muhammad Sa’dii Fathir Muhammad Turhan Yani Mustika, Ita Na'imah, Zaidatun Naila Mubarokah Nandawati, Almania NASUTION Ngaliman, Ngaliman NOFA ARIYANTI Nuansa Bayu Segara Nur Aisyah Nurpadila, Nurpadila Oksiana Jatiningsih Putri Hardina Pratiwi Putri, Angga Rahmanda, Lovita Rahmanu Wijaya Rani Safitri Manullang Ratih Tyas Arini Ratna Dewi Silalahi Rayessandi Raymond Raymond RISKHA PRISTIANA Rochmadi, Tri Rujianto Eko Saputro Satriawan, Bambang Septia Asri Silvia Mona Siti Maizul Habibah SLAMET SETIAWAN Sri Nuraeni Suci Ulamatullah, Tri Sugianto, Dwi Sukma Perdana Prasetya Sunarmi SUPRAPTO Suprijono , Agus Tinambunan, Hezron Sabar Rotua Tri Suci Ulamatullah ULTHUFNA KAUSARUL FITRIYA Wahyusari, Retno Warsono Wayan Catra Y Winda Oriza Safira Windayati, Diana Titik Yuanita Sidabutar Yunita, Ika Romadoni