Vietnam Journal of Computer Science

Sentiment analysis (SA) involves utilizing natural language processing (NLP) methods to identify the sentiment conveyed by a given text. This study is grounded on the dataset sourced from the internet movie database (IMDB), encompassing evaluations of films and their corresponding positive or negative classifications. Our research experiment aims to ascertain the model with the highest accuracy and generality. Our research utilizes diverse classifiers, comprising unsupervised learning approaches such as Valence Aware Dictionary and sEntiment Reasoner (VADER) and Text Blob, alongside Supervised Learning methods like Naïve Bayes, which encompasses both the Bernoulli NB and Multinomial NB. Several methodologies have been utilized, including the Count Vectorizer, and the Term Frequency-Inverse Document Frequency model (TFIDF) Vectorizer. Subsequently, word embedding and bidirectional LSTM are executed, utilizing various embeddings such as the Long Short-Term Memory (LSTM) base model. Finally, GloVe embeddings achieve the best performance with an accuracy of 90.64% and a sensitivity of 91.07%.

Many fall detection systems are being used to provide real-time responses to fall occurrences. Automated fall detection is challenging because it requires very high accuracy to be clinically acceptable. Recent research has tried to improve sensitivity while reducing the high rate of false positives. Nevertheless, there are still limitations in terms of having efficient learning approaches and proper datasets to train. To reduce false alarms, one approach is to add more nonfall data as negative samples to train the deep learning model. However, this approach increases class imbalance in the training set. To tackle this problem, we propose a multi-task deep learning approach that divides datasets into multiple training sets for multiple tasks. We prove this approach gives better results than a single-task model trained on all datasets. Many experiments are conducted to find the best combination of tasks for multi-task model training for fall detection.

The paper proposes a robust and efficient model designed for multi-label abdominal organ segmentation, featuring a substantially reduced number of parameters. The model focuses on the effectiveness of edge guidance in segmentation and leverages a 3D-Unet architecture with deep supervision, incorporating the robust deep thinking gate (DTG) architecture. Our DTG-incorporated model architecture excels in both efficiency and effectiveness, demonstrating notable enhancements in multi-label abdominal organ segmentation performance. A comprehensive evaluation of the model employed on two datasets of MRI scan of BTCV and FLARE 2022, comparing its performance against state-of-the-art counterparts. The outcomes revealed that the proposed model achieved the highest dice score in the esophagus (0.795), gallbladder (0.945), and pancreas (0.87) while maintaining a most significantly reduced parameter count (13.3 million parameters count). This achievement underscores the model’s efficiency and its suitability for seamless integration into real-world applications, offering promising prospects for enhanced medical image analysis.

Background Subtraction (BgS) is a widely researched technique to develop online Change Detection algorithms for static video cameras. Many BgS methods have employed the unsupervised, adaptive approach of Gaussian Mixture Model (GMM) to produce decent backgrounds, but they lack proper consideration of scene semantics to produce better foregrounds. On the other hand, with considerable computational expenses, BgS with Deep Neural Networks (DNN) is able to produce accurate background and foreground segments. In our research, we blend both approaches for the best. First, we formulated a network called Convolutional Density Approximation (CDA) for direct density estimation of background models. Then, we propose a self-supervised training strategy for CDA to adaptively capture high-frequency color distributions for the corresponding backgrounds. Finally, we show that background models can indeed assist foreground extraction by an efficient Neural Motion Subtraction (NeMos) network. Our experiments verify competitive results in the balance between effectiveness and efficiency.

Indoor localization for livestock is important as it facilitates effective monitoring and management of animals within confined spaces, such as barns or stables. By accurately tracking the position of individual animals, farmers and livestock managers can gain valuable insights into their behavior, health, and welfare. This information enables the early detection of potential issues, such as diseases or injuries, allowing for prompt intervention and treatment. While GPS sensors offer global position estimation, they are limited to outdoor environments and inherently exhibit inaccuracies of several meters. In indoor spaces, alternative sensors like lasers and cameras can estimate positions, but they necessitate maps and substantial computational resources to process complex algorithms. Presently, Wireless Networks (WN) are extensively accessible in indoor environments, providing efficient global localization with relatively low cost and computing demands. This paper presents a novel approach to estimate the location of cows in a given area using Deep Neural Networks (DNNs) applied to LQI data. This method aims to improve the efficiency of livestock management, particularly in large-scale farming operations, by enabling precise tracking and monitoring of individual animals. Our proposed model leverages data from wireless sensor networks (WSNs) and demonstrates promising results in terms of accuracy and computational efficiency. This study contributes to the ongoing research in smart agriculture and the application of advanced technologies in the livestock industry.

This research undertakes an exhaustive exploration of the Auto Machine Learning-based approach (AutoML) to ascertain the source printer for microscopic printed image forensics. The primary focus is on enhancing precision and efficacy in a scenario with limited sample data, achieved by integrating traditional image processing methods with diverse AutoML representatives. The investigation involves a meticulous evaluation and comparative analysis of classical Machine Learning (ML) models and AutoML models in microscopic printed image forensics. Through extensive experiments, we highlight the inherent limitations of traditional models and underscore the compelling advantages offered by AutoML. Notably, we recognize AutoML’s unique capability to discern varying degrees of uncertainty within printed patterns. The outcomes emphasize the prowess of Auto Machine Learning in improving the accuracy of printed image forensics, making it particularly promising for future research, especially given the tabular nature of the data and the imperative for a lightweight model suitable for embedded systems.