This is a single portfolio entry
Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa. Cum sociis natoque penatibus et magnis dis parturient montes, nascetur ridiculus mus. Donec quam felis, ultricies nec, pellentesque eu, pretium quis, sem. Nulla consequat massa quis enim.
Donec pede justo, fringilla vel, aliquet nec, vulputate eget, arcu. In enim justo, rhoncus ut, imperdiet a, venenatis vitae, justo. Nullam dictum felis eu pede mollis pretium. Integer tincidunt. Cras dapibus. Vivamus elementum semper nisi. Aenean vulputate eleifend tellus. Aeneaellus.
Recent Entries
A120315011225
Sentiment analysis of short text has posed a significant challenge in natural language processing, particularly for context rich and low-resource languages such as Vietnamese. User generated texts are usually brief; therefore, they do not explicitly express their sentiments. Consequently, traditional models struggle to process those reviews. This paper introduces a new approach that leverages the strengths of large language models to address the gap in context scarcity. The method works primarily in two ways: a) by feeding in structured metadata, such as restaurant name and location, directly into the model input, and b) using large language models to automatically generate likely contextual sentences so that short reviews become long informative statements. Results from comprehensive experiments carried out on a newly assembled Vietnamese food review dataset show improved sentiment analysis output based on this kind of context enrichment, beating several strong baselines, including the state of-the-art monolingual PhoBERT model, particularly when it came to resolving semantic vagueness typical of ultra-short word reviews or even short reviews with implicit subjects. This work offers a strong, flexible approach to addressing the problem of missing context in low-resource languages. This will bring value to both the commercial world and academic study.
B120615020126
This article is based on an analysis of communication protocols used in industrial solutions. It presents a brief description of Ethernet communication protocols, specifically ISO on TCP (described as a mechanism that enables ISO applications to be ported to the TCP/IP network), UDP (User Datagram Protocol), Profinet IO, and S7-connection. Based on these characteristics, four industrial network models were configured, and individual protocols were implemented in the controller. The publication presents several Ethernet protocols that were configured on Siemens S7-1200 family controllers in the TIA Portal environment. The purpose of this publication is to present and analyse commonly used industrial Ethernet networks. The possibility of data exchange between individual controllers has been verified, with relevant instructions provided. Detailed differences between the industrial networks in question have been highlighted. Profinet IO is the most versatile network in terms of control process selection, integration with other networks, and ease of configuration. On the other hand, the cheapest solution is to choose the S7-connection protocol. In addition, the authors presented the types of instructions introduced for bit and byte exchange, such as TCON, TSEND, PUT, and TDISCON. Chapter 4 provides a descriptive analysis of the advantages and disadvantages of the communication protocols discussed, as well as a table summarising the topology and integration of each protocol. There are many different protocols to choose from in industrial automation. It should be noted that the selection of individual devices depends not only on data transfer speed but also on hardware and software configuration. After analysis, the authors pointed out that the choice is often driven by selecting an easier data exchange application.
A120515011225
This study presents the construction of a credit risk prediction model to improve the effectiveness of risk management at credit institutions. The urgency of the study is underscored by the internal bad-debt ratio of the Vietnamese banking system increasing by nearly 3.4 times by the end of 2023, while the cost of credit risk provisioning rose by 40% compared to 2022. The key challenge is to address a severe data imbalance (bad-debt accounts for 1-5%). Advanced data preprocessing techniques are applied, including handling missing values with the miceforest library and feature selection using Mutual Information combined with Correlation. The key experimental solution is the Mixture of Experts (MoE) Model, using Stratified K-Fold to train experts on 1:1-balanced data. The results show that the MoE model achieves the highest performance with a Recall of 0.87 and an F1-score of 0.79, outperforming the classical Machine Learning models. Applying the model achieves 85-90% forecasting accuracy, optimises the credit process, reduces appraisal time by 25-30%, and supports the sustainable development of the financial system.
A120415011225
The facility for laser technology offers significant research opportunities for scientists and researchers working in fibre lasers, quantum lasers, ultrafast lasers, 3D laser printing, miniaturisation, and laser-related two-dimensional materials. The field of research using lasers encompasses holography, optical information/data storage, processing, telecommunications, manufacturing, health care, space exploration, and computing, among others. The introduction of intelligent software solutions and emerging technologies into laser systems enhances real-time process optimisation, predictive maintenance, and monitoring, thereby improving accuracy, efficiency, and quality. The role of emerging software like artificial intelligence (AI), machine learning (ML), augmented reality (AR) interface, and digital twins, with the emergence of innovative technologies like robotics, computer-aided design (CAD), and smart sensors in laser processing and advanced modelling and simulation techniques driven by these technologies, will be given special attention.
