检索结果-内蒙古大学图书馆

Development of a Deep Learning-Based Model for Canine Skin Disease Diagnosis Using RandAugment and Patterned-GridMask

引用

Transactions of the Korean Institute of Electrical Engineers 2025年第1期74卷 142-148页

作者： Kim, Min-Jun Park, Jae-Beom Cho, Hyun-Chong Dept. of Electronics Engineering Interdisciplinary Graduate Program for BIT Medical Convergence Dept. of Data Science Kangwon National University Korea Republic of Dept. of Interdisciplinary Graduate Program for BIT Medical Convergence Kangwon National University Korea Republic of

In contemporary society, pets are increasingly regarded as integral family members, contributing significantly to human quality of life. The growing prevalence of dog ownership has concurrently escalated the economic burden associated with veterinary care, particularly in managing common conditions like skin diseases. This study introduces an advanced deep learning-based diagnostic system for canine skin diseases, designed for practical application in home environments. We employed RandAugment to enhance data augmentation, thereby increasing the diversity of the training dataset. Furthermore, the implementation of Patterned-GridMask significantly improved the model's generalization capabilities. The use of the AdamW optimization algorithm was instrumental in mitigating overfitting, thus enhancing the model's overall learning efficiency. The proposed Transformer-based model, ViT/B-16, achieved an accuracy of 78.65% with the original dataset. With the integration of RandAugment and Patterned-GridMask techniques, the model's accuracy improved to 84.33%, underscoring its potential effectiveness for practical veterinary applications. Copyright © The Korean Institute of Electrical Engineers.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

A Study on Optimization and Augmentation Techniques for Improving the Performance of CADx System for Cat Skin Disease

引用

Transactions of the Korean Institute of Electrical Engineers 2025年第1期74卷 135-141页

作者： Won, Hyeong-Sik Park, Jae-Beom Cho, Hyun-Chong Dept. of Electronics Engineering Interdisciplinary Graduate Program for BIT Medical Convergence Dept. of Data Science Kangwon National University Korea Republic of Dept. of Interdisciplinary Graduate Program for BIT Medical Convergence Kangwon National University Korea Republic of

In modern society, the number of households raising pets is increasing. As pet ownership increases, the cost of treating companion cats is also rising, with a significant portion of these costs going toward the treatment of skin diseases. Skin diseases are among the common ailments in pets, and swift action is required if they occur in cats. However, early lesions lack distinctive characteristics, making accurate diagnosis difficult. Therefore, this study proposes a CADx(Computer-Aided Diagnosis) system that classifies images of cat skin conditions into inflammatory lesions, non-inflammatory lesions, and normal images using a dataset of cat skin diseases. We selected the ConvNeXt model, based on CNN, which can learn regional information and features. To learn various patterns of skin lesions, we applied Mixup, an image augmentation technique. When Mixup was applied, the model accuracy was 0.8679, showing a 3.35% improvement compared to the original dataset. Additionally, Lookahead Optimizer was applied to ensure stable learning of Mixup. When both Mixup and Lookahead Optimizer were applied, the model accuracy was 0.8741, showing a high improvement of 3.97% compared to the original dataset. Therefore, the Lookahead Optimizer helps with the stable training of mixup, which can improve the performance of the model. Copyright © The Korean Institute of Electrical Engineers.

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

Development of a Deep Learning-Based System for Cat Skin Disease Classification and Grad-CAM Visualization

引用

Transactions of the Korean Institute of Electrical Engineers 2025年第2期74卷 339-344页

作者： Won, Hyeong-Sik Cho, Hyun-Chong Dept. of Interdisciplinary Graduate Program for BIT Medical Convergence Kangwon National University Korea Republic of Dept. of Electronics Engineering and Interdisciplinary Graduate Program for BIT Medical Convergence Dept. of Data Science Kangwon National University Korea Republic of

Skin diseases in companion cats can worsen if not treated promptly, and this can increase the financial burden on pet owners. To prevent this, early and accurate diagnosis is essential. This study introduces a deep learning-based Computer-Aided Diagnosis (CADx) system designed to classify cat skin diseases into non-inflammatory and inflammatory lesions by comparing them with normal images. The system employs the EfficientNetV2 model and incorporates image augmentation techniques like AutoAugment and AugMix to enhance classification performance. The study results indicate that the developed model achieved an 84.68% accuracy for non-inflammatory lesions, reflecting a 10.06% improvement, and a 97.19% accuracy for inflammatory lesions, reflecting a 2.45% improvement. Furthermore, we applied Grad-CAM to visualize the regions of interest in the images, offering veterinarians critical insights into the location and characteristics of the lesions. This system has the potential to significantly improve the precision of diagnosing skin diseases in companion cats, thereby supporting better veterinary care. Copyright © The Korean Institute of Electrical Engineers.

关键词： Veterinary medicine

来源：评论

学校读者我要写书评

暂无评论

A STUDY ON DYNAMIC RESPONSE DISPLACEMENT MEASURING METHODS FOR BUILDING UNDER EARTHQUAKE USING SATELLITE TECHNOLOGY WITH TWO MOVABLE VIBRATION TABLES

引用

AIJ Journal of Technology and Design 2024年第74期30卷 65-70页

作者： Hashimoto, Akihiro Mukai, Tomohisa Tajima, Kazuyuki Nakamura, Akihiro Ariki, Katsuyoshi Kinugasa, Hideyuki Dept. of Architecture Graduate School of Science and Technology Tokyo Univ. of Science Japan Building Dept. National Institute for Land and Infrastructure Management Program Management Division Ground Facilities Dept. The Japan Aerospace Exploration Agency Dept. of Structural Engineering Building Research Institute Dept. of Structural Engineering Building Research Institute Urban Renaissance Agency Japan Dept. of Architecture Faculty of Science and Technology Tokyo Univ. of Science Japan

In recent years, research has been conducted to establish a method for quickly and appropriately determining damage to buildings during an earthquake using sensors, and it’s useful to appropriately evaluate the maximum and residual displacement during an earthquake. The purpose of this study is to propose a disaster assessment method using a satellite positioning system that directly measures the response displacement of a building from satellite positioning information. In this paper, the positioning accuracy is verified when calculating the relative displacement using two movable vibration tables that assume the top floor of a building and the ground surface under earthquake. © 2024 Architectural Institute of Japan. All rights reserved.

关键词： Earthquakes

来源：评论

学校读者我要写书评

暂无评论

A Pulse Width Modulation-Based Spike Generator to Eliminate Timing Errors in Spiking Neural Networks

A Pulse Width Modulation-Based Spike Generator to Eliminate ...

引用

2025 International Conference on Electronics, Information, and Communication, ICEIC 2025

作者： Jo, Jungkook Sim, Keonhee Sim, Sangwoong Jun, Jaehoon Inha University Dept. of electrical and computer engineering and program in semiconductor convergence Incheon Korea Republic of Inha University Dept. of electrical engineering Incheon Korea Republic of

ISBN: (纸本)9798331510756

This paper proposes a novel spike generator for processing in memory (PIM) technology. Most of the electronics today utilize a von Neumann architecture. The von Neumann architecture suffers from the separation of memory and processor. This architecture delays data transfer between memory and processor. To overcome the issues, we utilize the spiking neural network (SNN) that combines memory and processor. SNN can be classified into voltage-based, current-based, and time-based architectures, each with its own pros and cons. Time-based SNN suffers from timing issues. To address the timing sensitivity of time-based neuron SNN, this paper proposes a PWM-based SNN. The PWM-based SNN utilizes pulse width-based logic to overcome timing sensitivity. © 2025 IEEE.

关键词： Pulse width modulation

来源：评论

学校读者我要写书评

暂无评论

Training Swinging Door Trending Compression Algorithm for IoT devices 10

Training Swinging Door Trending Compression Algorithm for Io...

引用

10th IEEE World Forum on Internet of Things, WF-IoT 2024

作者： Correa, Juan David Arias Pinto, Alex Sandro Roschildt Montez, Carlos Post-graduate Program of Automation Systems Engineering Florianópolis Brazil Dept. of Informatics and Statistic Dept. of Automation and Systems Engineering Florianópolis Brazil Dept. of Automation and Systems Engineering Florianópolis Brazil

ISBN: (纸本)9798350373011

The communication system is essential for the devices used in IoT. Nevertheless, the consumption caused by transmitting and receiving data is a concern in many scenarios. That is due to these devices commonly having limited energy and computational capacities. Transmission of redundant or irrelevant samples frequently wastes the device's resources. Furthermore, Storing a large amount of redundant data could consume storage space and not offer any benefit. Data Compression (DC) methods are a potential solution. DC could reduce communication usage and storage demand. This research proposes the Training Swing Door Trending (TSDT) for being implemented in IoT Devices. TSDT is a new algorithm that improves the classic Swing Door Trending (STD). They represent the data by trend lines and have a constant computational complexity. TSDT has a training step for the automatic configuration of its parameters. This article additionally presents the Compression Factor (C-Score), a new quality metric to analyze the compression results in lossy DC methods. C-Score takes as a basis the F-Score, a measure of predictive performance. The C-Score uses the Compression and Error metrics to evaluate the compression performance in Lossy Algorithms. © 2024 IEEE.

关键词： Data compression ratio

来源：评论

学校读者我要写书评

暂无评论

Innovative Portable Quantitative EEG Data Acquisition Based Cyton Biosensing Board using PSD Analysis 10

Innovative Portable Quantitative EEG Data Acquisition Based ...

引用

10th International Conference on Smart Computing and Communication, ICSCC 2024

作者： Melinda, Melinda Purnamasari, Prima Dewi Fahmi, Fahmi Sinulingga, Emerson Muliyadi, Muliyadi Yamin, Imam Ashabul Universitas syiah kuala Dept. electrical and computer engineering Banda Aceh Indonesia Universitas Indonesia Dept. electrical engineering Depok Indonesia Universitas sumatera utara Dept. electrical engineering Medan Indonesia Medan Indonesia Universitas syiah kuala Doctoral program in engineering dept. electrical engineering Banda Aceh Indonesia

ISBN: (纸本)9798350363104

Electroencephalography (EEG) is a non-invasive brain imaging technique essential for neuroscience research and clinical applications. Conventional EEG devices are often expensive and impractical for use outside clinical or laboratory settings. This study reports the experience of acquiring EEG data using the Cyton board biosensing, an open-source and portable biosensor device. Detailed procedures for subject preparation, electrode placement, device configuration, and EEG data acquisition are provided. A Butterworth filter was used to eliminate noise from the EEG signals, with results visualized using the Fast Fourier Transform (FFT). Quantitative EEG (qEEG) analysis was conducted using the Power Spectral Density (PSD) method. The highest PSD values were 428.04 μV2/Hz at 5.9 Hz on channel C4 for subject 1,329.77 μV2/Hz at 5.9 Hz on channel C4 for subject 2, and 385.65 μ V2/Hz at 5.9 Hz on channel Fp1 for subject 3, all indicating increased brain activity in the theta wave range. This study provides insights for researchers and practitioners using the Cyton board for EEG data acquisition and contributes to developing portable, affordable EEG methods. © 2024 IEEE.

关键词： Butterworth filters

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Heart Rate Conditions in Autistic Children Using IoT-Based Systems 4

Early Detection of Heart Rate Conditions in Autistic Childre...

引用

4th International Conference on Electrical engineering and Computer Science, ICECOS 2024

作者： Albar, Nizam Melinda, Melinda Away, Yuwaldi Universitas Syiah Kuala Dept. Electrical Engineering Master of Electrical Engineering Study Program Banda Aceh Indonesia Universitas Syiah Kuala Engineering Faculty Dept. Electrical Engineering and Computer Banda Aceh Indonesia

ISBN: (纸本)9798350368253

Early detection of heart rate conditions in autistic children is crucial for anticipating tantrum reactions and providing prompt medical intervention. Previous research designed a prototype for acquiring Electrocardiogram (ECG) signals using the AD8232 sensor, but it required a long time to identify heart rate conditions. This study aims to develop the previous prototype using Internet of Things (IoT) implementation to acquire and identify the heart rate conditions of autistic children in real time. The ECG signal data is analyzed using Butterworth Filter and Artificial Neural Network (ANN) integrated into Raspberry Pi and results are transmitted to the Blynk App. Testing over 20 minutes showed that in the first 10 minutes, the system identified a normal heart rate at 105.19 BPM with 67% accuracy, while in the second 10 minutes, the heart rate rose to 117.19 BPM with tantrum symptoms and 75% accuracy. This system helps medical personnel provide immediate intervention during tantrums. © 2024 IEEE.

关键词： Butterworth filters

来源：评论

学校读者我要写书评

暂无评论

Hysteresis Model of Permafrost Thermal State Variation with Air Temperature in Utqiaġvik, Alaska, Based on Distributed Temperature Sensing

Hysteresis Model of Permafrost Thermal State Variation with ...

引用

Geotechnical Frontiers 2025: Geotechnics of Natural Hazards

作者： Ji, Xiaohang Xiao, Ming Martin, Eileen Dept. of Civil and Environmental Engineering Pennsylvania State Univ. University ParkPA United States Dept. of Geophysics Dept. of Applied Math and Statistics Hydrologic Science and Engineering Program Colorado School of Mines GoldenCO United States

ISBN: (数字)9780784485996

Increasing air temperatures are driving permafrost warming across the Arctic and sub-Arctic. This in turn degrades the geomechanical properties of soils, disrupts the natural environment and infrastructure systems, and results in long-lasting societal impacts. Understanding the thermal state of degrading permafrost in the Arctic is crucial for maintaining resilient infrastructure in the changing Arctic. This study employs Distributed Temperature Sensing (DTS) to monitor permafrost temperature near Utqiaġvik, Alaska, from 2021 to 2024. Fiber-optic DTS sensors have unique and attractive characteristics that allow their deployment in the Arctic for low-maintenance, cost-effective, and high-resolution data. This paper presents the temperature recordings of a 2-km DTS system on the tundra near Utqiaġvik, Alaska, by the Elson Lagoon. A hysteresis model is developed to link permafrost temperature with air temperature, incorporating meteorological data and ground surface conditions. The study also explores the impact of civil infrastructure on permafrost thermal dynamics. © ASCE.

关键词： Permafrost

来源：评论

学校读者我要写书评

暂无评论

Preparation and Characterization of Nypa Fruit Pulp Extraction as a Natural Material for Scaffold Fabrication using 3D Printing Method 9

Preparation and Characterization of Nypa Fruit Pulp Extracti...

引用

9th International Conference on Applying New Technology in Green Buildings, ATiGB 2024

作者： Irwansyah, Irwansyah Hendri, Darwin Maulana, Muhammad Rizki Indriani, Aulia Saputra, Maidi University of Teuku Umar Dept. of Mechanical Engineering Aceh Indonesia University of Syiah Kuala Dept. of Mechanical and Industrial Eng. Aceh Indonesia University of Syiah Kuala Dept. of Mechanical Engineering Graduate Program Aceh Indonesia

ISBN: (纸本)9798331505042

The aim of this study is to investigate the extracted Nypa fruticans as an alternative biomaterial used for 3D printing application in the biomedical and pharmaceutical. An important substances that was extracted from nipa palm fruit is galactomannan, a water-soluble heteropolysaccharide. It was considered to the polysaccharide-based polymer material used to fabricate scaffold tissue by 3D printing approach for medical purposes. Emphasis was placed on the synthesis and characterization of extracted nypa fruticans as the primary material, along with glycerol and sorbitol serving as polimerization agents. Extracted nypa with 3%, 5% and 10% amout of variation glycerol and sorbitol was evaluated. The experimental procedures conducted in the laboratory facilitated the isolation, production, purification, and fabrication of the extracted nypa polymer gels. Various properties of the nypa compounds and chemical composition through Fourier-transform infrared (FTIR) Spectrometry were analyzed. Findings indicated that extracted nypa refer to ether bonds (CH2-O- CH2) observed at 875.04 cm-1, identifying compound is galactomannan. This substance is classified within the polysaccharide category due to the appearance of peaks within the range of 900 to 1200cm-1. The incorporation of different amount percentage of glycerol and sorbitol, resulted in distinct impacts on the geometry of 3D printing scaffold material laying down. © 2024 IEEE.

关键词： Glycerol

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：