Analysis and Preprocessing of Accelerometer Sensor Data

Rahmat Dongka, Ulfatun Nadifa, Ade Irawaty Tolago, Wildan .

Abstract


Accelerometer sensor data obtained directly from a device is generally still raw data that may contain missing values, differences in feature scale, time-format errors, and extreme values (outliers). This study aims to analyze and preprocess an accelerometer dataset consisting of 27,937 observations of acceleration along the X, Y, and Z axes together with the recording date and time. The analysis was carried out using the Pipeline method from the Scikit-learn library to clean, process, and transform the data in a structured manner, starting from converting the date and time format, extracting time-based features, standardizing the numerical data with a StandardScaler, and detecting and handling outliers with the Interquartile Range (IQR) method and a capping technique. The inspection results show that the dataset has no missing values, so imputation is not required, and the transformation process produces 11 features. The Pearson correlation heatmap visualization shows that the three acceleration axes have a weak and relatively independent relationship with one another, so all three still need to be retained as separate features. As a result, the dataset becomes cleaner, more stable, and ready to be used for further analysis such as activity classification and sensor-based machine learning modeling.


Keywords


Accelerometer; Correlation Analysis; Pipeline Method; Outlier; Data Preprocessing;

Full Text:

PDF

References


Arifien, Z., Bachtiar, F. A., & Yudistira, N. (2022). Pengenalan aktivitas manusia menggunakan sensor akselerometer dan giroskop pada smartphone dengan metode K-Nearest Neighbor [Human activity recognition using accelerometer and gyroscope sensors on a smartphone with the K-Nearest Neighbor method]. Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), 9(1), 173–180. https://doi.org/10.25126/jtiik.202295593

Arduino Indonesia. (2022, December). Accelerometer: Pengertian, cara kerja, dan jenis-jenisnya [Accelerometer: Definition, working principle, and types]. https://www.arduinoindonesia.id/2022/12/accelerometer-pengertian-cara-kerja-dan-jenis-jenisnya.html

Han, J., Kamber, M., & Pei, J. (2012). Data mining: Concepts and techniques (3rd ed.). Morgan Kaufmann.

Witten, I. H., Frank, E., Hall, M. A., & Pal, C. J. (2016). Data mining: Practical machine learning tools and techniques (4th ed.). Morgan Kaufmann.

Januaji, D. (2022, August 22). Data preprocessing: Pengertian, manfaat, dan tahapan kerjanya [Data preprocessing: Definition, benefits, and work stages]. Accurate. https://accurate.id/teknologi/data-preprocessing/

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.

sanjanchaudhari. (n.d.). Accelerometer case study dataset [Data set]. Kaggle. https://www.kaggle.com/datasets/sanjanchaudhari/accelerometer-casestudy-dataset

Géron, A. (2019). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow (2nd ed.). O’Reilly Media.

McKinney, W. (2010). Data structures for statistical computing in Python. Proceedings of the 9th Python in Science Conference, 56–61. https://doi.org/10.25080/Majora-92bf1922-00a

Boukerche, A., Zheng, L., & Alfandi, O. (2020). Outlier detection: Methods, models, and classification. ACM Computing Surveys, 53(3), 1–37. https://doi.org/10.1145/3381028

Ramadhani, J. W., & Susanto. (2026). Perbandingan metode IQR vs Isolation Forest dalam deteksi outlier pada data klaim asuransi di PT Askrindo Cabang Semarang [Comparison of the IQR and Isolation Forest methods for outlier detection in insurance claim data at PT Askrindo Semarang Branch]. Jurnal Transformatika, 23(2), 268–277. https://doi.org/10.26623/transformatika.v23i2.13726

Accurate. (n.d.). Koefisien korelasi [Correlation coefficient]. https://accurate.id/akuntansi/koefisien-korelasi/

Sugiyono. (2016). Statistika untuk penelitian [Statistics for research] (Cet. 27). Alfabeta.

Ambarwari, A., Adrian, Q. J., & Herdiyeni, Y. (2020). Analisis pengaruh data scaling terhadap performa algoritma machine learning untuk identifikasi tanaman [Analysis of the effect of data scaling on machine learning algorithm performance for plant identification]. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 4(1), 117–122. https://doi.org/10.29207/resti.v4i1.1517

Tukey, J. W. (1977). Exploratory data analysis. Addison-Wesley.


Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 International Journal of Embedded Computer Engineering

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.