Engineering Proceedings

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Other

7 pages, 557 KiB

Open AccessProceeding Paper

The Application and Performance Comparison of Different Versions of YOLO Image Recognition Systems

by You-Shyang Chen and Yi-Xuan Chen

Eng. Proc. 2025, 98(1), 1; https://doi.org/10.3390/engproc2025098001 - 30 May 2025

Viewed by 185

Abstract

With advancements in computational power and artificial intelligence (AI), image recognition has become more efficient and widely used. You Only Look Once (YOLO) stands out for its fast and accurate object detection, making it popular among researchers. The technology enhances daily life, from smartphone facial recognition improving security to thermal imaging aiding public health during the pandemic. However, identifying the right image recognition system for varied image types remains challenging. By evaluating the performance of YOLO’s versions (e.g., YOLOv3 and YOLOv4) regarding structure, speed, accuracy, and adaptability, we identified appropriate algorithms for specific tasks, recommending optimal image recognition techniques for different applications. Full article

(This article belongs to the Proceedings of 2024 4th International Conference on Social Sciences and Intelligence Management (SSIM 2024))

► Show Figures

Figure 1

6 pages, 362 KiB

Open AccessProceeding Paper

An Integrated Fuzzy Convolutional Neural Network Model for Stock Price Prediction

by Jia-Wen Wang and Jr-Shian Chen

Eng. Proc. 2025, 98(1), 3; https://doi.org/10.3390/engproc2025098003 - 30 May 2025

Viewed by 131

Abstract

Stock market forecasting has always been researched extensively in Social Sciences. In this research, Fuzzy time series with deep learning is widely adopted to create a fuzzy convolutional neural network integration model as this model enhances the fuzzification of values to enhance feature characteristics using two-dimensional input data in convolutional neural networks (CNNs). This allows the model to retain complete feature information. The fuzzy convolutional neural network (FCNN) model autonomously learns and extracts crucial features by integrating stock market data, resulting in improved forecasting accuracy. In this study, the model was tested for forecasting the Taiwan Weighted Stock Index and metrics such as the mean squared error (MSE) and mean absolute error (MAE), and the results were compared with the real data. The results showed that the model provided accurate predictions. Full article

(This article belongs to the Proceedings of 2024 4th International Conference on Social Sciences and Intelligence Management (SSIM 2024))

► Show Figures

Figure 1

8 pages, 502 KiB

Open AccessProceeding Paper

Adaptive Frequency and Assignment Algorithm for Context-Based Arithmetic Compression Codes for H.264 Video Intraframe Encoding

by Huang-Chun Hsu and Jian-Jiun Ding

Eng. Proc. 2025, 98(1), 4; https://doi.org/10.3390/engproc2025098004 - 4 Jun 2025

Viewed by 4

Abstract

In modern communication technology, short videos are increasingly used on social media platforms. The advancement of video codecs is pivotal in communication. In this study, we developed a new scheme to encode the residue of intraframes. For the H.264 baseline profile, we used context-based arithmetic variable-length coding (CAVLC) to encode the residue of integer transforms in a block-wise manner. In the developed method, the DC and AC coefficients are separated. In addition, context assignment, adaptive scanning, range increment, and mutual learning are adopted in a mixture of fixed-length and variable-length schemes, and block-wise compressions of the frequency table are applied to obtain improved compression rates. Compressing the frequency prevents CAVLC from being hindered by horizontally/vertically dominated blocks. The developed method outperforms CAVLC, with average reductions of 7.81, 8.58, and 7.88% in quarter common intermediate format (QCIF), common intermediate format (CIF), and full high-definition (FHD) inputs. Full article

(This article belongs to the Proceedings of 2024 4th International Conference on Social Sciences and Intelligence Management (SSIM 2024))

► Show Figures

Figure 1

701 KiB

Open AccessProceeding Paper

Development of Artificial Urine Using Commonly Available Ingredients for Ultraviolet–Visible Spectroscopy

by Patryk Sokołowski and Maria Babińska

Eng. Proc. 2025, 98(1), 5; https://doi.org/10.3390/engproc2025098005 - 5 Jun 2025

Abstract

A simple urine phantom was developed to replicate the ultraviolet–visible (UV–Vis) spectrum of healthy human urine. Made from four safe and widely available ingredients, it addresses the challenges of biological samples, including safety risks and storage issues. The spectroscopic analysis results confirmed strong similarity to natural urine, making the phantom appropriate for testing spectroscopic methods, calibrating optical devices, and evaluating diagnostic sensors. It can also serve as a starting point for advanced phantoms tailored to specific patient needs or diseases. This reliable alternative facilitates research in optical diagnostics or biosensor development by simplifying preliminary sensor testing. Full article

(This article belongs to the Proceedings of 2024 4th International Conference on Social Sciences and Intelligence Management (SSIM 2024))

► Show Figures

Journal Menu

Journal Browser

Eng. Proc., 2025, SSIM 2024

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI