The proceedings contain 43 papers. The topics discussed include: deep learning-based license plate information recognition in harsh environments;research on quality prediction of resistance spot welding based on knowl...
ISBN:
(纸本)9781510682283
The proceedings contain 43 papers. The topics discussed include: deep learning-based license plate information recognition in harsh environments;research on quality prediction of resistance spot welding based on knowledge graph;deep learning-based recognition of autism using facial datasets;HRPD: a lightweight high-resolution projector deblurring network;3D visualization of large scale point clouds on transmission lines;model reconstruction and digital exhibition based on photogrammetry: a case study of bronze cultural relics in Hubei provincial museum;enhancing small object detection in UAV images with DSD-YOLO;machine vision based sorting method for precision industrial components;and the optimal control of automated sorting robot movements based on PLC logic controller.
Wildfires have devastating impacts on the environment, economy and public health. Early detection can help mitigate damage but detection can be challenging in remote and inaccessible areas. Wireless sensor networks pr...
详细信息
ISBN:
(数字)9798331533816
ISBN:
(纸本)9798331533823
Wildfires have devastating impacts on the environment, economy and public health. Early detection can help mitigate damage but detection can be challenging in remote and inaccessible areas. Wireless sensor networks provide an effective solution. These networks consist of inexpensive nodes that monitor the environment and transmit the sensed data over wireless links to a base state. Sensor nodes are usually randomly distributed via air and must self-organize to create the network. This paper proposes a new self-organizing method that forms a hierarchical sensor network suitable for wildfire detection. Clusters are formed without a predefined structure or the need for localization. Shapley values are used to select cluster heads as new clusters are dynamically created during self-organization. Routing paths for aggregated data are naturally defined as clusters are created. Simulation results are presented to show the effectiveness of this approach.
The proceedings contain 641 papers. The topics discussed include: engineering safety early warning platform based on BIM and Internet of things;harmless treatment and comprehensive utilization of dairy farming waste b...
The proceedings contain 641 papers. The topics discussed include: engineering safety early warning platform based on BIM and Internet of things;harmless treatment and comprehensive utilization of dairy farming waste based on artificial intelligence;research on intelligent management of campus water supply system under the background of big data;research on intelligent control system of high power soft starter based on discrete frequency conversion technology;design of digital business center of enterprise project management system based on information technology;digital watermarking algorithm for multi-sampling compressed sensing in measurement domain;analysis of the influence of big data background on the spread of large-scale sports events;construction of college English teaching resource database under the background of big data;research on the medical English teaching under the condition of medical literacy based on computer-aided technology;and research on the development path of Russian teaching innovation in newly-elevated undergraduate colleges in contemporary old industrial bases based on the analysis of big data.
The proceedings contain 641 papers. The topics discussed include: engineering safety early warning platform based on BIM and Internet of things;harmless treatment and comprehensive utilization of dairy farming waste b...
The proceedings contain 641 papers. The topics discussed include: engineering safety early warning platform based on BIM and Internet of things;harmless treatment and comprehensive utilization of dairy farming waste based on artificial intelligence;research on intelligent management of campus water supply system under the background of big data;research on intelligent control system of high power soft starter based on discrete frequency conversion technology;design of digital business center of enterprise project management system based on information technology;digital watermarking algorithm for multi-sampling compressed sensing in measurement domain;analysis of the influence of big data background on the spread of large-scale sports events;construction of college English teaching resource database under the background of big data;research on the medical English teaching under the condition of medical literacy based on computer-aided technology;and research on the development path of Russian teaching innovation in newly-elevated undergraduate colleges in contemporary old industrial bases based on the analysis of big data.
This paper introduces a Multi-Factor Authentication System for enhancing data security in IoT healthcare devices. The system comprises the Multi-Factor Authentication Algorithm (MFAA), Biometric Template Protection Al...
详细信息
ISBN:
(数字)9798331533816
ISBN:
(纸本)9798331533823
This paper introduces a Multi-Factor Authentication System for enhancing data security in IoT healthcare devices. The system comprises the Multi-Factor Authentication Algorithm (MFAA), Biometric Template Protection Algorithm (BTPA), Dynamic Risk-Based Authentication Algorithm (DRBAA), Adaptive Biometric Fusion Algorithm (ABFA), and Context-Aware Access Control Algorithm (CAACA). Through a comparative analysis, the proposed system consistently outperforms existing methods, demonstrating its potential for robust, context-aware, and adaptive user authentication. The ablation study delves into the individual contributions of each algorithm, emphasizing their collective strength in creating a secure and versatile authentication framework. The proposed system stands as a promising solution for addressing the evolving challenges of data security in the dynamic landscape of IoT healthcare.
Bitter melon (Momordica charantia), also known locally as Ampalaya, holds significant economic and medicinal value, but its size classification remains a challenge due to its irregular morphology. Proper size classifi...
详细信息
ISBN:
(数字)9798331533816
ISBN:
(纸本)9798331533823
Bitter melon (Momordica charantia), also known locally as Ampalaya, holds significant economic and medicinal value, but its size classification remains a challenge due to its irregular morphology. Proper size classification is essential for maintaining packaging standards and ensuring efficient market distribution. Thus, this study presents a deep learning-based approach for automated bitter melon size classification using the Mask R-CNN model for instance segmentation, the Harris Corner Detection algorithm for contour detection, and the Douglas-Peuker algorithm for contour simplification. A hardware prototype was developed using a Raspberry Pi 4 Model B and a camera module to capture images for real-time processing. The system achieved an overall accuracy of $\mathbf{9 7. 9 1 \%}$ in classifying the sizes of bitter melons. The model displayed a high classification accuracy, demonstrating its potential for improving agricultural automation and postharvest processes.
This study presents an IoT-based water quality monitoring and automatic feeding system for indoor mud crab aquaculture. The system integrates an ESP8266 micro controller with dedicated sensors to continuously measure ...
详细信息
ISBN:
(数字)9798331533816
ISBN:
(纸本)9798331533823
This study presents an IoT-based water quality monitoring and automatic feeding system for indoor mud crab aquaculture. The system integrates an ESP8266 micro controller with dedicated sensors to continuously measure pH, salinity, temperature, and water levels while implementing an automated feeding mechanism. The accuracy and reliability of the system were improved through sensor calibration techniques and proactive measures, such as sensor drift mitigation and keeping spare sensors for replacements. The results show improved crab growth rates, reduced crab mortality, and reduced manual labor due to the system's implementation. In addition, the study shows that IoT-based aquaculture improves the sustainability and efficiency of an indoor crab farm.
Wildfires are increasingly severe global challenges, driven by environmental, economic, and health impacts. This study investigates the use of weather forecasts into machine learning models to predict wildfire charact...
详细信息
ISBN:
(数字)9798331533816
ISBN:
(纸本)9798331533823
Wildfires are increasingly severe global challenges, driven by environmental, economic, and health impacts. This study investigates the use of weather forecasts into machine learning models to predict wildfire characteristics across seven Australian regions. Various machine learning models were evaluated for their ability to predict wildfire attributes, including fire area, brightness, and radiative power. Results show that mean fire brightness predictions achieved moderate success nationally ( $\mathbf{R}^{2}$ : 0.504), while fire area and radiative power remained challenging due to their complexity. Region-specific analysis revealed better predictive performance in New South Wales and Queensland, with lower accuracy in regions like Northern Territory and Tasmania, emphasizing the need for region-specific approaches. This study highlights the potential of integrating real-time weather data into predictive frameworks and calls for enhanced feature engineering and regional modeling to improve accuracy, and wildfire management strategies.
This research involves the creation and evaluation of a system that allows for text extraction and automatic question generation (AQG) using a T5 and TrOCR pipeline. With the use of a Raspberry Pi 5, web camera, and a...
详细信息
ISBN:
(数字)9798331533816
ISBN:
(纸本)9798331533823
This research involves the creation and evaluation of a system that allows for text extraction and automatic question generation (AQG) using a T5 and TrOCR pipeline. With the use of a Raspberry Pi 5, web camera, and a touchscreen display, factoid- type questions are created from image captures of single-column handwritten notes that only contain textual information. The T5 large language model (LLM) used was finetuned using the Stanford Question Answering Dataset (SQuAD) for facilitating question generation. The system had a word error rate (WER) of 0.40, a ROUGE-1 score of 0.358, and a question validity rate of 68%. This research helps to promote the ease of creation of learning materials in learner education.
Image synthesis, once considered a distant fantasy, has emerged as a rapidly evolving field, driven by advancements in generative models and computational power. Many researchers in academia and corporations have tack...
详细信息
ISBN:
(数字)9798331533816
ISBN:
(纸本)9798331533823
Image synthesis, once considered a distant fantasy, has emerged as a rapidly evolving field, driven by advancements in generative models and computational power. Many researchers in academia and corporations have tackled this problem and achieved impressive results. Among the widely adopted models in this domain is the Generative Adversarial Network (GAN). In this work, we integrate Binary Segmentation with GANs to enhance the quality of the object of interest in generated images. The binary segmentation model guides the generative model to focus on the region of interest within the image rather than the background producing more detailed representations of the target object. Our approach was trained and validated using labeled samples from the well-known CUB dataset. For testing, we generated images corresponding to text descriptions from the dataset. Evaluation of these images demonstrated the effectiveness of our model, achieving a comparable Inception Score of $5.243\pm 0.090$ with significantly fewer training epochs (200 epochs).
暂无评论