Bài viết nghiên cứu phân loại mức độ nghiêm trọng vết nứt đường nhựa bằng LightGBM và xử lý ảnh. Đạt độ chính xác >98%, F1 >0.95. Ứng dụng SF, PI, LTP, CSQP.

Study on isolation and identification of two new Scenedesmus microalgae strains from Can Gio by 18S rRNA sequencing. Morphological and phylogenetic analysis showed differences from known strains.

The internet has become an indispensable part of daily life. However, excessive use of the internet can lead to internet addiction, a recognized mental health condition included in the International Classification of Diseases-11 Revision (ICD-11).

Lesson "Machine Vision" Chapter 7 - Object Recognition, compiled including the following main contents: Introduction; Pattern Matching; Feature-based Methods; Artificial Neural Networks.

Bài thuyết trình Ứng dụng khai thác dữ liệu (Data Mining and Application): Artificial Neural Network for Classification tập trung vào ứng dụng của mạng nơ-ron nhân tạo trong bài toán phân loại. Nội dung thuyết trình đề cập đến cấu trúc, cách hoạt động của mạng nơ-ron, các ưu điểm, thách thức và một số ứng dụng thực tiễn. Đây là nền tảng quan trọng trong các hệ thống học sâu hiện đại. Mời các bạn cùng tham khảo để biết thêm chi tiết!

Bài thuyết trình Ứng dụng khai thác dữ liệu (Data Mining and Application): Multi-label classification of enzyme substrates trình bày ứng dụng kỹ thuật phân loại đa nhãn trong nhận diện cơ chất của enzyme. Bài thuyết trình trình bày tổng quan bài toán, xây dựng mô hình và đánh giá kết quả. Đây là một ứng dụng tiềm năng trong nghiên cứu sinh học và hóa sinh. Mời các bạn cùng tham khảo để biết thêm chi tiết!

This study presents a new proposal for gemstone color classification and integrates hardware to enable gemstone color assessment based on this new system. This allows for a quantified measurement of gemstone color, providing a visual description.

This study presents the RAS-OESHG device, which utilizes advanced machine learning algorithms to automatically differentiate between glass bead jewelry from the Oc Eo and Sa Huynh cultures through SEM gemological analysis. This device is specifically designed for experts, archaeologists, and individuals in the field of archaeology.

The research focuses on applying deep learning to automate the fruit recognition and classification process, meeting the development needs of modern agriculture. Applying this technology helps improve efficiency and classification quality and reduces labor costs, resulting in lower product prices. The research team used two deep learning models, SSD300 and YOLOv10s, to recognize and classify six types of fruits: apples, bananas, kiwis, lemons, oranges, and strawberries.

In this study, we utilized the YOLO (You Only Look Once) model to evaluate the performance of real-time vehicle detection and classification. Additionally, we adjusted the learning rate parameter to achieve optimal performance.

Artificial intelligence is gradually emerging as a method for optimizing various tasks, offering cost-saving and highly efficient solutions. Nowadays, Al is used as a general term for diverse tasks performed by computers. Fields like machine learning, deep learning, and data science, among others within this scope, are considered part of Al as long as they exhibit the characteristics of artificial intelligence.

Lecture "Machine learning: An introduction to data classification" includes content: Introduction, common techniques in data classification, handing different data types, variations on data classification.

This paper proposes an intelligent plastic waste detection and classification system based on the Deep Learning model and Delta robot. This system includes a Delta robot, a camera, a conveyor, a control cabinet, and a personal computer.

This paper presents a lightweight deep learning-based product object classification scheme designed for deployment on edge servers. Leveraging the ImageNet Large Scale Visual Recognition Challenge 2012 (ILSVRC2012) dataset, six classes relevant to product objects are selected for model training and evaluation.

This article presents a semisupervised fuzzy c-means clustering algorithm based on the collaborative clustering model (CSFCM) on distributed systems applied to the problem of land cover classification from remote sensing data.

Blur image classification is essential for computer vision applications, including image quality assessment, surveillance and medical imaging systems. This study proposes a method to classify different types of blur: sharp, Gaussian blur, motion blur, and defocus blur, using the DenseNet121 architecture.

Rabies manifests is a zoonotic ailment affecting both humans and carnivorous animals. The administration of rabies vaccination, particularly to domesticated animals such as dogs and cats, is an efficacious prophylactic measure for safeguarding the optimal health of both animal and human populations.

ASA classification has been applied all over the world in premedication. The 2019 Amended ASA-PS was modified by new definitions, approved examples, especially definition for emergent patients. In Vietnam, there has not any independent study on ASA- PS classification up to now. The addition of “E” denotes emergency surgery.

The aim of this study is to (1) Describe the ultrasound characteristics of ovarian tumors according to the O-RADS classification. (2) Investigate the signs predicting malignancy in the O-RADS 3, 4, and 5 categories.

To determine the prevalence of suicidal ideation among adolescents whose parents are separated/divorced; and to explore the factors associated with suicidal ideation and describe adverse experiences among adolescents.