The lungs are two of the most crucial organs in the human body because they are connected to the respiratory and circulatory systems. Lung cancer, COVID-19, pneumonia, and other severe diseases are just a few of the many threats. The patient is subjected to an X-ray examination to evaluate the health of their lungs. A radiologist must interpret the X-ray results. The rapid advancement of technology today can help people in many different ways. One use of deep learning in the health industry is in the detection of diseases, which can decrease the amount of money, time, and energy needed while increasing effectiveness and efficiency. There are other methods that can be used, but in this research, the convolutional neural network (CNN) method is only used with three architectures, namely ResNet-50, ResNet-101, and ResNet-152, to aid radiologists in identifying lung diseases in patients. The 21,885 images that make up the dataset for this study are split into four groups: COVID-19, pneumonia, lung opacity, and normal. The three algorithms have fairly high evaluation scores per the experiment results. F1 scores of 91%, 93%, and 94% are assigned to the ResNet-50, ResNet-101, and ResNet-152 architectures, respectively. Therefore, it is advised to use the ResNet-152 architecture, which has better performance values than the other two designs in this study, to categorize lung diseases experienced by patients.

In the era of big data and ubiquitous internet connectivity, user feedback data plays a crucial role in product development and improvement. However, extracting valuable insights from the vast pool of unstructured text data found in user feedback presents significant challenges. In this paper, we propose an innovative approach to tackle this challenge by combining the Contextualized Topic Model (CTM) and the Masked and Permuted Pre-training for Language Understanding (MPNet) model. Our approach aims to create a more accurate and context-aware topic model that enhances the understanding of user experiences and opinions. To achieve this, we first search for the optimal number of topics, focusing on generating distinguishable, general, and unique topics. Next, we perform hyperparameter optimization to fine-tune the model and maximize coherence metrics. The result is an exceptionally effective model that outperforms established topic modeling methods, including LSI, NMF, LDA, HDP, NeuralLDA, ProdLDA, ETM, and the default CTM, achieving the highest coherence CV score of 0.7091. In this study, the combination of CTM and MPNet has proven highly effective in the context of user feedback topic modeling. This model excels in generating coherent, distinguishable, and highly relevant user feedback topics, capturing the nuanced nature of user feedback data. The topics generated from this model include ’Music and Audio Streaming,’ ’Application Performance,’ ’Banking, Financial Services, and Customer Support,’ ’User Experience,’ ’Other Topics,’ ’Application Content,’ and ’Application Features.’ Our contributions include a powerful tool for developers to gain deeper insights, prioritize actions, and enhance user satisfaction by incorporating feedback into future product iterations. Furthermore, we introduce a new dataset as an open-source resource for further exploration and validation of user feedback analysis techniques and general natural language processing applications. With our proposed approach, we strive to drive business success, improve user experiences, and inform data-driven decision-making processes, ultimately benefiting both developers and users alike.

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.

Natural Language Processing has experienced significant advancements in recent years, leading to the widespread adoption of Large Language Model-based chatbots. These chatbots are popular due to their ability to engage in context-aware conversations. However, deploying LLM-based chatbots can be re-source-intensive, making them less suitable for smaller applications or focused tasks. To address this issue, we propose a robust and flexible approach to intent classification for chatbots using STraVEns (Sentence Transformer Voting Ensemble), which includes both hard voting and soft voting ensembles of sentence transformers. Our proposed method aims to improve accuracy and versatility in intent-based chatbots model. We use five sentence transformer models for this ensemble framework: RoBERTa, DistilRoBERTa, MPNet, MiniLM L6, and MiniLM L12, and evaluated our approach by training and testing using four distinct datasets: ATIS, IDE, Small Talk, and CLINC150 which cover a range of scenarios from general conversation to specific tasks and out-of-scope intent classification. The results demonstrate that the STraVEns approach is a promising solution for intent classification-based chatbot model. Results show that our ensemble models outperformed previous benchmarks, achieving the highest accuracy and F1-scores across all datasets. The soft voting method provided flexibility and robustness, while hard voting ensured stability in specific contexts. Overall, our study suggests that ensemble-based approaches can enhance the performance of intent classification chatbots model, providing a scalable solution for various applications.

COVID-19 statistics in Indonesia show more than 4.2 million active confirmed cases with more than 140 thousand deaths. The Indonesian government has made several policies to reduce the number of COVID-19 cases, one of them is by implementing the PeduliLindungi application. The government has socialized and recommended this application as an effort to fulfill the tracking, tracing, and fencing program. Various kinds of responses appear in the community to this application, therefore sentiment analysis is needed to find out public trends so that the government can evaluate the policies that have been made. This study aims to determine the best model from the comparison of the Naïve Bayes algorithm and the Support Vector Machine, besides that this study will also see whether a simpler model such as Naive Bayes is still good in handling binary sentiment for PeduliLindungi data reviews. The data was obtained by web scraping from the PeduliLindungi application review on the Google Play Store. The Naïve Bayes accuracy value is 81%, smaller than the Support Vector Machine which has an accuracy of 84%, although the Support Vector Machine is the best model we have, Naive Bayes itself can still be used to handle binary sentiment data because the difference in accuracy values is not too far.

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.