The proposed algorithm

This study proposes to test a combination model between CNN network and XGBoost algorithm for weather image classification problem. The proposed model uses deep learning network, namely CNN for feature extraction, then feeds the features into the XGBoost classifier to recognize the images.

6p vithomson 02-07-2024 0 0   Download

In this paper, we build a quadcopter for target tracking by integrating a embedded computer Raspberry Pi (RPI) with a Pixhawk flight controller. This article also proposes a lightweight Tracking algorithm that can be deployed on Raspberry Pi, this algorithm harnesses advanced image processing and computing capabilities to significantly enhance target tracking performance, thereby reducing the need for human intervention control in unmanned flights.

9p vithomson 02-07-2024 0 0   Download

This study proposes a new approach for diagnosing pediatric sepsis that utilizes a convolutional neural network and a combination of 7 immune-related genes (IRGs), including CD24, TTK, PRG2, CLEC7A, CCL3, TNFAIP3, and CCRL2. A three-layer gene selection process involves a sequential procedure that combines differential gene expression analysis, selection of immune-related genes, and gene score calculation using the F-score algorithm.

8p vithomson 02-07-2024 0 0   Download

To address this issue, this article proposes a solution that combines Enhanced GA with a comprehensive framework for considering environmental factors in traffic signal optimization. By optimizing traffic signal timings and minimizing emissions, the proposed solution aims to reduce congestion and improve urban transportation networks' efficiency while protecting the environment.

13p vithomson 02-07-2024 0 0   Download

In this paper, we evaluate the performance of the SHM damage identification tool using a novel metaheuristic algorithm called the Artificial Hummingbird Algorithm (AHA). The proposed approach is evaluated by two case studies of different bridge structures in Vietnam with different simulated damage scenarios.

15p viwalton 02-07-2024 1 1   Download

This study proposes an algorithm that includes both PNC frequency and sequence information to identify the predominant provider and estimates the percentage of identified predominant providers. Additionally, differences in travel distances to the predominant and nearest provider are compared.

9p vishanshan 27-06-2024 1 1   Download

The paper proposes a type of block cipher algorithm based on cryptographic hash function and public key cryptography. The algorithm proposed here is capable of verifying the origin and integrity of the encrypted message. On the other hand, establishing a shared secret key between the sender/encryptor and the receiver/decryptor can be done for each message separately.

11p visergeyne 18-06-2024 3 0   Download

This article proposes an approach to solve that equilibrium problem based on analyzing population distribution during the evolutionary process to identify empty regions in which no solutions are selected. After that, information about empty regions with the most significant area will be combined with the current reference point to create a new reference point to prioritize choosing solutions in those regions.

12p visergeyne 18-06-2024 0 0   Download

The paper presents an overview of underwater traffic management systems utilizing sonar principles. Based on the evaluation of the current situation both domestically and internationally, the research team has proposed the development of a underwater signal processing algorithm based on an adaptive threshold in the Ultra-short Baseline System (USBL).

9p visergeyne 18-06-2024 0 0   Download

This paper addresses the challenges of translating pivotal military symbols like double arrows onto 2D digital maps, particularly when automation is essential. It proposes a comprehensive method integrating data structure, user workflow, and algorithms to generate tactically aligned, balanced, and visually appealing double arrows for military 2D digital maps.

10p viambani 18-06-2024 2 1   Download

Positron emission tomography (PET) is a type of nuclear medicine procedure that measures the metabolic activity of cells in body tissues that is well suited for detecting, staging and monitoring malignant tumours. In this paper, the authors have successfully developed the application based on the algorithm that they proposed.

10p viambani 18-06-2024 2 1   Download

This article presents an efficient hybrid approach based on Brotli and LZ4 compression algorithms to compress terrain data for deployment on resource-limited devices. Experimental results show that the proposed method significantly reduces the volume of terrain data compared to using each component algorithm independently while still ensuring quality.

9p viambani 18-06-2024 3 1   Download

Anomaly detection for Internet of things (IoT) networks is a challenging issue due to the huge number of devices that connect to each other and generate huge amounts of data. In this study, we propose a model combining Autoencoder (AE) with classification algorithms to build an endto-end architecture for processing, feature extraction and data classification.

13p viambani 18-06-2024 7 1   Download

The paper proposes an enhanced solution for improving the accuracy of underwater object positioning based on the Ultra-Short Baseline (USBL) sonar principle. In shallow water regions, complex hydrological phenomena affect the quality of underwater acoustic signal transmission and reception, making it essential to enhance the processing of these signal groups.

9p viambani 18-06-2024 3 1   Download

The present paper considers the composite plate resting on an elastic pinned subjected to harmonic loads. The plate element model with high-order shear deformation theory and finite element algorithm is proposed in order to buckling analysis of the plate. As a result, the buckling domain is determined. Moreover, the effect of geometric parameters, elastic pins, and materials on the buckling of the plate is comprehensively investigated.

10p dathienlang1012 03-05-2024 1 0   Download

The authors propose a novel BCMO-DNN algorithm for vibration optimization of functionally graded porous microplates. The theory is based on a unified framework of higher-order shear deformation theory and modified strain gradient theory. A hybrid combination of deep learning neural network and balancing composite motion optimization is developed to solve the optimization problems and predict stochastic vibration behaviors of functionally graded porous microplates with uncertainties of material properties.

12p dathienlang1012 03-05-2024 3 0   Download

The article "Static behavior of FGP half-annular nanoplates resting on elastic foundation using nonlocal elasticity theory" presents an algorithm finite element for static bending analysis of the functionally graded porous (FGP) half-annular nanoplate resting on the elastic foundation (EF) using nonlocal elasticity theory. The FGP materials with two-parameter are the volume fraction index (k) and the porosity volume fraction (5) in two cases of even and uneven porosity. The EF includes Winkler-stiffness (k₁) and Pasternak- stiffness (k₂).

9p dathienlang1012 03-05-2024 5 0   Download

This paper proposes an efficient method to determine entire reducts of incomplete decision tables according to the relational database approach. In the complex case, this algorithm has exponential computational complexity. However, this algorithm has polynomial computational complexity in the different cases of databases.

9p dianmotminh02 03-05-2024 3 1   Download

As part of the research related to the improvement of the portfolio theory of H. Markowitz, J. Tobin, and W. Sharpe for use in established as well as developing modern stock markets, the authors proposed a concept and a numerical algorithm to choose the priority sequence of financial portfolios of non-institutional investors, taking into account their preferences and projected changes in the parameters included in financial portfolios assets.

8p longtimenosee10 26-04-2024 3 1   Download

In this research, the problems were divided into three small, medium and large groups, and for each of the solving methods the evaluation criteria was calculated. The results of this comparison indicated that non-dominated optimization algorithm outperforms the exact solving method. Therefore, it was concluded that this algorithm should be used to solve the model of real data.

22p longtimenosee10 26-04-2024 3 1   Download