Examining topic-level variability in modeling Twitter data can potentially yield more comprehensive insights into public perception during critical periods, thereby enhancing natural disaster mitigation and surveillan...
详细信息
Examining topic-level variability in modeling Twitter data can potentially yield more comprehensive insights into public perception during critical periods, thereby enhancing natural disaster mitigation and surveillance efforts. In this study, we utilized generalized linear mixed models (GLMMs) to illustrate the variability in tweet counts related to specific topics in Indonesia during the flood events that occurred in February 2021. The glmmTMB library in R was employed for this purpose. The data were assumed to follow two distinct exponential distributions: Poisson and Negative Binomial. To incorporate random effects, random intercepts and random slopes were introduced, allowing them to vary randomly across topics in the initial two models. Additionally, the final model addressed issues related to dispersion and zero-inflation. By evaluating the Akaike Information Criteria scores, we determined that a model based on the Negative Binomial distribution with random zero-inflation intercepts best fit the data. The chosen model formulation and the estimated parameters have the potential to forecast topic-specific trends in Indonesian flood-related Twitter data.
Symbolic computation for systems of differential equations is often computationally expensive. Many practical differential models have a form of polynomial or rational ODE system with specified outputs. A basic symbol...
详细信息
Oil palm fruit farming is one of the most leading agriculture industries in the South East Asia region. Unfortunately, most of the harvesting method is still done through manual labor. Multiple research has been condu...
详细信息
In real world applications of multiclass classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., no parking). Thus, it is crucial...
详细信息
Gastrointestinal diseases are significant health concerns that mostly affect the digestive and biliary tracts. These can only be observed internally through endoscopy, or a modern approach named Wireless Capsule Endos...
详细信息
ISBN:
(数字)9798331510732
ISBN:
(纸本)9798331510749
Gastrointestinal diseases are significant health concerns that mostly affect the digestive and biliary tracts. These can only be observed internally through endoscopy, or a modern approach named Wireless Capsule Endoscopy. Though the approach has proven to work, the process relies heavily on medical experts, which is prone to error when given a considerably large load. The use of deep learning in detecting diseases with images has been proven to work in various cases and can be implemented for gastrointestinal diseases. This study compared four deep learning models based on Convolutional Neural Network architectures consisting of the VGG16, ResNet152V2, InceptionV3, and Xception for classifying colon disease images. The experiment showed that the ResNet152V2 performed the best, compared to the other three with a testing accuracy score of 0.9837. On the other hand, the VGG16 had the lowest performance with around accuracy score of 0.89 while the Xception and InceptionV3models yielded similar accuracy scores of 0.9587 and 0.9549, respectively. The results highlight the effectiveness of ResNet152V2 in handling the complexity of colon disease detection
Despite their drawbacks, multiple-choice questions (MCQ) have been widely used to assess the students' understanding of lectures through examinations. The development of automatic MCQ generation is beneficial, esp...
详细信息
ISBN:
(数字)9798331510732
ISBN:
(纸本)9798331510749
Despite their drawbacks, multiple-choice questions (MCQ) have been widely used to assess the students' understanding of lectures through examinations. The development of automatic MCQ generation is beneficial, especially for educators. As a starting point for further development, a Systematic Literature Review (SLR) is conducted to uncover current trends, future challenges, and opportunities in automatic MCQ generation. Previously, an SLR was conducted, but it lacks coverage of the utilization of transformer-based models. This SLR covers the development of automatic MCQ generation using either traditional or advanced approaches such as Transformers. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework was used to gather the data from Scopus, IEEE Xplore, SpringerLink, arXiv, and Semantic Scholar. The included articles must be open-access computerscience conference papers or journal articles and written in English less than five years ago. Four independent reviewers analyzed the research workflow, evaluation metric, and dataset used in each study. There are 18 included studies, where 17% (n = 3) studies are from 2024, 33% (n = 6) studies are from 2023, 22% (n = 4) studies are from 2022, 11% (n = 2) studies are from 2021, and 17% (n = 3) studies are from 2020. There are 33% (n = 6) of the studies used the traditional feature-based engineering approach, 39% (n = 7) of the studies used the Transformer-based model fine-tuning approach, and the remaining used novel approaches. The study found that BERT variants are the most utilized Transformer-based model in automatic MCQ. The research notes some challenges, but also open various opportunities for further research, including Large Language Model (LLM) utilization for automatic MCQ generation, the utilization BERT-based models for standardized machine-learned evaluation metrics, and the initiative for the creation of an MCQ dataset benchmark.
Kidney stones are primarily crystals formed from ion oversaturation in urine. Currently, the diagnosis of kidney stones involves experienced professionals manually interpreting images of urinary crystals under a micro...
详细信息
Typhoid fever is an endemic disease that burdens Indonesia and has a potentially fatal infection multisystem. Salmonella typhi bacterium is responsible for typhoid fever disease. Poor sanitation, crowding, and slums a...
详细信息
Several studies suggest that sleep quality is associated with physical activities. Moreover, deep sleep time can be used to determine the sleep quality of an individual. In this work, we aim to find the association be...
详细信息
Several studies suggest that sleep quality is associated with physical activities. Moreover, deep sleep time can be used to determine the sleep quality of an individual. In this work, we aim to find the association between physical activities and deep sleep time by modeling the time series data such as heart rate and a number of steps captured from a commercial wearable device. Our previous study demonstrates that deep learning-based time series modeling is well suited for our problem since the temporal patterns in the two physical parameters need to be captured to obtain more accurate results. We first preprocess our series data to have a time-step size of 10 minutes. To improve our previous effort in this modeling, we compare four different variants of Long Short-Term Memory (LSTM)-based models, ranging from single input to dual input models. Our result shows that the simple stacked LSTM model performs better for our data because the remaining models suffer from overfitting due to a larger number of the trained parameters.
Predicting the best-quality of rice phenotypes is the priority among agricultural researchers to fulfill worldwide food security. Trend development of predictive models from statistics to machine learning is the subje...
详细信息
Predicting the best-quality of rice phenotypes is the priority among agricultural researchers to fulfill worldwide food security. Trend development of predictive models from statistics to machine learning is the subject of this review. Gathered from the Google Scholar database, 14 appropriate papers (2016-2020) related to the rice phenotypes prediction were selected through title and abstract content filtering. The outputs show that Support Vector Machine, Multi-layer Perceptron, and regression are the most used models, while yield is the priority prediction point besides tiller, panicle, and 1000-grain weight of rice. However, finding the accurate predictor is invariably challenging due to distinct rice varieties in the world and high confounding factors. Thus, developing an advanced deep learning model that accommodates these needs is worth considering further.
暂无评论