Air quality conditions are now more severe in the Jakarta area that is among the world’s top eight worst cities according to the 2022 Air Quality Index (AQI) report. In particular, the data from the Meteorological, Climatological, and Geophysical Agency (BMKG) of the Republic of Indonesia, the latest outcomes in air quality conditions in Jakarta and surrounding areas, says that PM2.5 concentrations have increased and peaked at 148μ g/m3 in 2022. While a classification system for this pollution is necessary and critical, the observation of PM2.5 concentrations measured through the BMKG Kemayoran station, Jakarta, turns out to be identified as an unbalanced data class. Thus, in this work, we perform boosting algorithm supervised learning to handle such an unbalanced classification toward PM2.5 concentration levels by observing meteorological patterns in Jakarta during 1 January 2015 to 7 July 2022. The boosting algorithms considered in this research include Adaptive Boosting (AdaBoost), Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), and Light Gradient Boosting Machine (LightGBM). Our simulations have proven that boosting classification can significantly reduce bias in combination with variance reduction with unbalanced within-class coefficients, with the classification of PM2.5 class values: good 62%, moderate 34%, and unhealthy 59%, respectively.

Particulate matter forecasting is fundamental for early warning and controlling air pollution, especially PM _2.5 . The increase in this level of concentration will lead to a negative impact on public health. This study develops a hybrid model of CNN-LSTM and CONV-LSTM by combining a convolutional neural network (CNN) with an LSTM network to forecast PM _2.5 concentration for the next few hours in Kemayoran DKI Jakarta, which is known as a busy area. We discovered the advantages of CNN in effectively extracting features and LSTM in learning long-term historical data from PM _2.5 concentration time series data. The predictive model of CNN-LSTM is carried out in a different architecture where the CNN process is carried out first to become the input of LSTM. For CONV-LSTM, it is carried out in one architecture where the multiplication in the LSTM architecture is coupled with the convolution process. This research will explain how the method of developing hybrid CNN-LSTM and CONV-LSTM in predicting PM _2.5 concentrations. Based on metric evaluation, the two models are compared to find the best model. Both predictive models produce MAPE values that fall into the good enough category with values <20%. Results were obtained for CONV-LSTM with MAE worth 6.52, RMSE 8.55, and MAPE 16.39%. As a result, the CONV-LSTM model performs better than CNN-LSTM in nowcasting PM _2.5 .

COVID-19 is the disease that has spread over the world since December 2019. This disease has a negative impact on individuals, governments, and even the global economy, which has caused the WHO to declare COVID-19 as a PHEIC (Public Health Emergency of International Concern). Until now, there has been no medicine that can completely cure COVID-19. Therefore, to prevent the spread and reduce the negative impact of COVID-19, an accurate and fast test is needed. The use of chest radiography imaging technology, such as CXR and CT-scan, plays a significant role in the diagnosis of COVID-19. In this study, CT-scan segmentation will be carried out using the 3D version of the most recommended segmentation algorithm for bio-medical images, namely 3D UNet, and three other architectures from the 3D UNet modifications, namely 3D ResUNet, 3D VGGUNet, and 3D DenseUNet. These four architectures will be used in two cases of segmentation: binary-class segmentation, where each architecture will segment the lung area from a CT scan; and multi-class segmentation, where each architecture will segment the lung and infection area from a CT scan. Before entering the model, the dataset is preprocessed first by applying a minmax scaler to scale the pixel value to a range of zero to one, and the CLAHE method is also applied to eliminate intensity in homogeneity and noise from the data. Of the four models tested in this study, surprisingly, the original 3D UNet produced the most satisfactory results compared to the other three architectures, although it requires more iterations to obtain the maximum results. For the binary-class segmentation case, 3D UNet produced IoU scores, Dice scores, and accuracy of 94.32%, 97.05%, and 99.37%, respectively. For the case of multi-class segmentation, 3D UNet produced IoU scores, Dice scores, and accuracy of 81.58%, 88.61%, and 98.78%, respectively. The use of 3D segmentation architecture will be very helpful for medical personnel because, apart from helping the process of diagnosing someone with COVID-19, they can also find out the severity of the disease through 3D infection projections.

Brain tumors are one of the most fatal disorders owing to the uncontrolled proliferation of abnormal cells inside the brain. Digital images are obtained using Magnetic Resonance Imaging (MRI), which is a medical instrument that can assist doctors and other medical personnel in assessing and diagnosing the presence and type of brain tumors. However, manual and subjective classification is time-consuming and error prone. Hence, an objective, automatic, and more reliable method is needed to classify MRI images of brain tumors. Artificial intelligence is considered appropriate to determine the type of brain tumor via MRI images to overcome the constraints of conventional testing methods. One method for performing automatic classification is the Convolutional Neural Network (CNN). This work demonstrates how the Inception Resnet v2 architecture in CNN is utilized to classify MRI brain tumors into four categories via transfer learning, namely glioma tumors, meningioma tumors, no tumors, and pituitary tumors. The accuracy value of the generated model reached 93.4% after running for 20 epochs. It infers that artificial intelligence is beneficial in identifying a brain tumor objectively to help doctors and radiologists in the medical field.

Accurate lung segmentation plays a vital role in generating 3D projections of lung infections, which contribute to the diagnosis and treatment planning of various lung diseases, including cases like COVID-19. This study capitalizes on the capabilities of deep learning techniques to reconstruct 3D lung projections from CT-scans. In this pursuit, we employ well-established 2D architectural frameworks like UNet, LinkNet, Attention UNet, UNet 3+, and TransUNet. The dataset used comprises 20 3D CT-scans from COVID-19 patients, resulting in over 2900 raw 2D slices. Following preprocessing, the dataset is refined to encompass 2560 2D slices tailored for modeling. Preprocessing procedures involve mask refinement, image resizing, contrast limited adaptive histogram equalization (CLAHE), and image augmentation to enhance the data quality and diversity. Evaluation metrics, including Intersection over Union (IoU) and dice scores, are used to assess the models’ performance. Among the models tested, Attention UNet stands out, demonstrating the highest performance. Its key trait of harnessing attention mechanisms enhances its ability to focus on crucial features. This translates to exceptional results, with an IoU score of 85.36% and dice score of 91.49%. These findings provide valuable insights into guiding the selection of an appropriate architecture tailored to specific requirements, considering factors such as segmentation accuracy and computational resources, in the context of 3D lung projection reconstruction.