BSBusono Soerowirdjo

Busono Soerowirdjo

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Busono Soerowirdjo has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Hybrid neural network classification of knee osteoporosis using X-ray images and clinical features

    by Nurfadjri Akbar Rizqi Basuki, Busono Soerowirdjo, Hustinawaty Hustinawaty, Iffatul Mardhiyah

    Osteoporosis is a degenerative disease marked by decreased bone density and increased fracture risk, particularly in the knee. Early detection is crucial, but conventional diagnostic methods are often subjective and require specialized skills. This study developed an artificial intelligence (AI) model for automatic osteoporosis classification using a hybrid method combining knee X-ray images and clinical data, integrating a convolutional neural network (CNN) for image features with an artificial neural network (ANN) for tabular data. The dataset comprised 239 patients with knee X-ray images and 27 clinical parameters. Pre-processing included handling missing values, encoding, and selecting the 20 best features via the analysis of variance (ANOVA) F-test, with T-score as the most influential parameter. Contrast-limited adaptive histogram equalization (CLAHE) improved image quality, while the synthetic minority oversampling technique (SMOTE) and image augmentation produced a balanced dataset of 462 samples. The hybrid model achieved 97.87% accuracy in classifying normal, osteopenia, and osteoporosis cases. Benchmarked against five alternative backbones (residual network (ResNet) 50V2, densely connected convolutional network (DenseNet) 121, mobile network (MobileNet) V2, vision transformer (ViT), and swin transformer) under the same framework, only the swin transformer matched this performance, while the others reached 74.47–82.98% accuracy, confirming the proposed backbone's contribution. These results show that combining imaging and clinical data improves diagnostic accuracy and supports AI-based early detection in orthopedics.

  • Open Access

    Integration of strain gauge sensor in biceps muscle movement detection using LabView

    by Desy Kristyawati, Busono Soerowirdjo, Erma Triawati Christina, Robby Kurniawan Harahap

    Muscle injuries caused by sports can have a serious impact on sportsmen, to avoid injuries during sports can be prevented by detecting the wrong movement using a strain gauge sensor attached to the muscle which in this study is devoted to the biceps muscle. The strain gauge will detect muscle movement, and the output generated at the strain gauge will be converted into the form of voltage and current which will be used to be processed using machine learning to get data patterns so that they can be grouped into data patterns of wrong movements and correct movements. The strain gauge movement pattern here is simulated using LabView by using a gauge resistance of 120 Ω, strain configuration Quarter Bridge 1, gauge factor 2.05, Vex is the excitation voltage given to the Wheatstone bridge is 5 V and the initial voltage -180.08 µV, the strain gauge output pattern is obtained in the form of Excel and with this data can be converted into voltage and current.

  • Open Access

    Utilize the Prediction Results from the Neural Network Gate Recurrent Unit (GRU) Model to Optimize Reactive Power Usage in High-Rise Buildings

    by Ahmad Rofii, Busono Soerowirdjo, Rudi Irawan, Wahyu Caesarendra

    The growing urbanization and the construction sector, efficient use of electric energy becomes important, especially the use of reactive power. If excessive use causes decreased efficiency and increased operational costs. Decreased efficiency contributes to increasing exhaust gas volumes and greenhouse emissions. Efficient energy can achieved if planning and predictions are correct. This research applies the GRU neural network method with grid search initialization as a novelty predictive model for energy-use high-rise buildings in form fast training without multiple iterations because optimal hyperparameters are obtained. Experimental show the MAE and RMSE performance metrics of the GRU better than LSTM in predicting energy consumption data peak loads, off-peak loads and reactive power. The accuracy of GRU predictions can optimize the use of energy to contribute to saving the environment from exhaust emissions and the greenhouse effect in urban systems. Experimental results demonstrate the superiority of GRU over LSTM, proof of the much lower MAE and RMSE values. This metric shows the accuracy of GRU in generalizing data both during peak and off-peak hours, as well as in reactive power usage. By Utilizing GRU's capabilities, building management can manage reactive power usage effectively, allocate reactive power resources appropriately, and mitigate peak load times and the power factor within the threshold, thus avoiding additional costs and electrical system efficiency and contributing to reducing the carbon footprint and gas emissions greenhouse. Research on GRU is widely open in the high-rise building sector, including its integration with sensors to automatically control energy use.