检索结果-内蒙古大学图书馆

2nd International Conference on Intelligent Cyber Physical Systems and Internet of Things (ICoICI)

作者： Sundar, Koushik Manohar, Eashaan Vijay, K. Ravikumar, S. Citibank NA Jersey City NJ 07310 USA Rajalakshmi Engn Coll Dept Comp Sci & Engn Chennai Tamil Nadu India Dr Sagunthala R&D Inst Sci & Technol Dept Comp Sci & Engn Chennai Tamil Nadu India

ISBN: (纸本)9798331540661;9798331540678

Globally, liver tumors and the third major cancer killer and sixth common disease. They occur mostly in people who take tobacco or alcohol very often. These factors are responsible for around 75-85 percent of cases of primary liver cancer. Nonetheless, manual diagnosis of liver tumors is known to be a challenging task due to tumor heterogeneity, diverse shapes and sizes as well as many types of imaging artifacts that can occur with relatively limited annotated data. Diagnosis and treatment planning of liver tumors are highly affected by the critical task of segmenting tumor in medical images. Further, for identifying stages, precision and make a doctor treatment-level understanding of learning characteristics tumor Since the knowledge that has been many feature extraction techniques formulated some frameworks onset detection tumors begun its course which could be fully transformed into applications targeted response type against size as well volume based However, this is an error-prone and time-consuming process. Thus, a solution to overcome these challenges is introduced by using deep learning (DL) with the TransUNet model which belongs to Convolutional Network architecture for instant image processing. Doctors use this system to conveniently detect and segment tumors from images, it is a way of approximating tumor size and stage so that more accurate treatment can be given. To sum up, liver tumors as a worldwide health problem are largely related to alcohol and tobacco consumption. Manual diagnosis is tough however with the help of advanced deep learning methods such as TransUNet we can detect tumors at an early stage and accurately providing better treatment to patients by doctors.

关键词： deep learning Liver Tumor Segmentation TransUNet Tumor Size Estimation

来源：评论

学校读者我要写书评

暂无评论

Automated Immune Cell Classification using image processing Techniques 6

Automated Immune Cell Classification using Image Processing ...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Sathiyaprasad, B. Reddy, Arva Hari Vardhan Abdurrahman, Usama Micheal, A. Annie Department of Computer Science and Engineering Sathyabama institute of science and technology Chennai India

ISBN: (纸本)9798331522667

Advances in immunological research are essential for elucidating immune responses and developing targeted therapeutic approaches. This study proposes an automated method for immune cell classification leveraging machine learning and image processing techniques. A novel framework is introduced, combining high-resolution imaging with computational algorithms to accurately classify various immune cell types from biological samples. The methodology incorporated preprocessing steps, like normalization and noise reduction. Then, deep learning models, such as CNNs and SVMs, will be applied for feature extraction and classification. These models were trained on annotated datasets derived from flow cytometry and microscopy, demonstrating better accuracy and reliability. Results demonstrate an improvement in processing speed and accuracy of classification over traditional approaches, which underlines the importance of automation in immunological diagnostics. The data obtained can be used in high-throughput immunotherapy and disease diagnostic screening;it allows for the identification of immune cell populations within a short period and therefore improves research efficiency. The work provides a basis for real-time analysis and incorporation of multiscale datasets that will help to better understand immunity and its associated disorders. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on the Construction of image Similarity Calculation Model Based on Convolutional Neural Network

Research on the Construction of Image Similarity Calculation...

引用

2024 International Conference on Remote Sensing, Mapping, and image processing, RSMIP 2024

作者： Liu, Qingxiu Yu, Yijia Guo, Yaqin Chongqing College of Architecture and Technology Chongqing401331 China

ISBN: (纸本)9781510680012

With the update iteration of deep learning technology, the necessity of image similarity calculation in image retrieval, target detection and tracking has become more and more prominent, and it has become an important force to promote the development of computer vision and artificial intelligence. In the face of increasingly complex and diverse application scenarios, the traditional image similarity detection technology has obvious shortcomings in calculation accuracy, and the image feature extraction needs manual assistance in the calculation process, so that the overall robustness of the technology is poor and cannot meet the practical application requirements. In view of this, this paper integrates the powerful image feature extraction ability of convolutional neural network, and constructs an image similarity calculation model based on VGG16-Siamese neural network, aiming at improving the accuracy of image similarity calculation and providing data support for the next technical application. Practice has proved that the VGG16 part of the model is used as the backbone feature extraction network to obtain the feature vector of the image. The Siamese neural network can use the feature vectors of two images to construct the distance similarity function at the same time, so as to calculate the similarity of the two images. The final experimental results show that the image similarity calculation model of VGG16-Siamese neural network has a precision of 90.84% and a recall rate of 91.88%, which meets the design expectation and has certain application and promotion value. © 2024 SPIE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Depthwise channel attention network (DWCAN): An efficient and lightweight model for single image super-resolution and metaverse gaming

引用

EXPERT SYSTEMS 2024年第4期41卷 e13516-e13516页

作者： Yasir, Muhammad Ullah, Inam Choi, Chang Gachon Univ Dept Comp Engn Seongnam Si South Korea Gachon Univ Dept Comp Engn Seongnam Si Gyeonggi Do South Korea

Single image super-resolution (SISR) has gained significant attention in image processing and computer vision, driven by deep learning-based models like convolutional neural networks (CNN). Yet, the resource-intensive nature of these models poses challenges when deploying them on edge devices. To address this issue, resource-constrained models need to be developed. While recent models like the information distillation network (IDN), the information multi-distillation network (IMDN), the residual feature distillation network (RFDN), and so on, have attempted to reduce parameters and computational complexity, further optimization remains vital. Therefore, this paper presents an approach to enhancing the efficiency and lightweight nature of the SISR. We introduce a novel lightweight SR model by building upon the RFDN architecture, the winner of the AIM2020 and NTIRE2022 SR challenges. The proposed depthwise channel attention network (DWCAN) model makes some key changes to RFDN. First, it replaces the main residual feature distillation block (RFDB) with a depthwise channel attention block (DWCAB). Additionally, DWCAN includes a shallow residual block (SRB) with depthwise separable convolution (DW) and a channel attention (CA) block. The primary goal of our work is to significantly reduce model parameters, computational operations, inference time, and memory size while maintaining or improving a peak signal-to-noise ratio (PSNR) of 29 dB. The experimental results demonstrate the effectiveness of the proposed model. By applying our modifications, we achieve a notable reduction in model complexity, leading to an improved PSNR of 29.07 dB, up from RFDN's 29.04 dB on a diverse 2 K resolution (DIV2K) dataset. This underscores the potential of our lightweight model to balance computational efficiency and SR quality. Additionally, the proposed work is essential for the metaverse for two key reasons: (1) Enhancing visual quality by adding complex details to textures and objects,

关键词： channel attention depthwise separable convolution lightweight model image reconstruction single image super-resolution super-resolution

来源：评论

学校读者我要写书评

暂无评论

An Efficient YOLOv5n Based Object Detection Heterogeneous SoC Implementation for Remote Sensing images 5

An Efficient YOLOv5n Based Object Detection Heterogeneous So...

引用

5th International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2024

作者： Liu, Heming Yao, Bowen Xu, Rong Peng, Yu Liu, Liansheng School of Electronics and Information Engineering Harbin Institute of Technology Harbin China Shanghai Institute of Satellite Engineering Shanghai China School of Electronics and Information Engineering Harbin Institute of Technology Yantai China

ISBN: (纸本)9798331529192

Convolutional neural networks (CNNs) are widely used in the field of remote sensing image object detection due to their high accuracy. However, the large number of parameters and high computational complexity of CNNs make it challenging to deploy them in real-time on embedded devices with limited computational and storage resources. This significantly restricts their practical application. To address this challenge, lightweight YOLOv5n model is chosen to realize object detection. The model is further optimized by activation function modification and parameter quantization to be more hardware-friendly. In addition, deploying a deep learning processing Unit (DPU) on the Zynq heterogeneous SoC by hardware-software co-design to significantly accelerate the YOLOv5n based remote sensing object detection. Experimental results show that the optimized YOLOv5n model reaches a lossless accuracy at 61.4% on the DIOR dataset when implemented on an embedded platform based on Zynq. The experimental platform achieves an image throughput of 232.1 FPS with a power consumption of 19.4W. Performance per watt (FPS/W) is 9.0× and 1.8× higher than that of i7-12700H CPU and RTX 3070Ti GPU respectively. © 2024 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Studies on the New deep learning Models-Based Higher Education System 5th

Studies on the New Deep Learning Models-Based Higher Educati...

引用

5th International Conference on 3D Imaging Technologies-Multidimensional Signal processing and deep learning, 3DIT-MSP and DL 2023

作者： Peng, Zhuzhang Duan, Yucheng Qinghai Normal University Qinghai Xining China

ISBN: (纸本)9789819751839

The main goal of this study is to enhance the attractiveness of university classroom teaching and students’ learning efficiency. A prediction module is constructed through deep learning techniques using Gesture Recognition Algorithm (GRA) and Long Short-Term Memory (LSTM) network, thus shaping a novel human–computer interaction system. deep learning techniques, the core of this study, provide the system with highly intelligent capabilities, especially in GRA, which successfully improves the gesture recognition accuracy of previous image segmentation and pattern matching methods. Specifically, the accuracies of the gestures "hold", "pinch", and "point" reached an impressive 98.66%, 99.52%, and 99.46%, respectively. In addition, the LSTM network model also performs well with a small amount of data, and its prediction accuracy can reach about 70% stably. This stability provides a reliable performance guarantee for the practical application of the system. The constructed human–computer interaction system is not only a technological innovation, but also a highly intelligent educational tool. The system effectively optimises the interactive teaching method between the teacher and the computer by more accurately interpreting the teacher’s gesture intentions and implementing the corresponding commands. It also inherently has the qualities of gamified teaching, which increases students’ interest and participation in the educational process, and at the same time has an important practical value in improving the teaching efficiency of general higher education. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of yOLO Architectures for Automated Detection of Liver Disease in Histopathological images 24

Comparative Analysis of yOLO Architectures for Automated Det...

引用

9th International Conference on Biomedical Imaging Signal processing

作者： Zou, Junting Arshad, Mohd Rizal Wang, Ziyan Univ Sains Malaysia George Town Malaysia Osaka Metropolitan Univ Osaka Japan

ISBN: (纸本)9798400717499

Liver disease is one of the major health problems worldwide and usually leads to serious complications if not diagnosed accurately and in time. Effective detection and classification of liver pathology at early stages is crucial, in which histopathologic examination of liver tissue plays a key role. However, manual analysis of histopathological images is easily affected by inter-observer variability. Recent advances in deep learning, on the other hand, have introduced methods to significantly improve the accuracy and efficiency of image-based diagnosis. This study focuses on the application of the You Only Look Once (YOLO) object detection model, specifically YOLOv4, v5, v7, v8, and v9, for automated detection of liver diseases from stained microscopic liver slices. We perform a comprehensive comparative analysis to evaluate the detection accuracy of these models across four common liver conditions: ballooning, fibrosis, inflammation, and steatosis. The results of the study show that the latest versions, in particular YOLOv9, show significant improvements in accuracy and computational efficiency compared to other versions. In this paper, the performance of each model is evaluated in detail, and our results emphasize the potential of the advanced YOLO architecture to enhance medical diagnostics by facilitating faster and more reliable detection of liver disease.

关键词： Liver disease Histopathologic deep learning YOLO Detection

来源：评论

学校读者我要写书评

暂无评论

deep learning Model for Option Pricing - Review 8

Deep Learning Model for Option Pricing - Review

引用

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Premsundar, Sangeetha Vishalakshi Prabhu, H. Bahadurdesai, Vikram N. Rv College of Engineering Bangaluru India Rv College of Engineering Bangaluru India

ISBN: (纸本)9798331505462

The Indian options market and in particular, the National Stock Exchange (NSE) segment of this marketspace poses a number of challenges when it comes to pricing option trades under high volatility regimes, low liquidity environments as driven by retail volume traders/ long positions and also rapidly changing regulatory ecosystems amongst others. These dynamics are often not captured by traditional pricing models such as the Black-Scholes model, therefore leading to inefficiencies in their prices. deep learning, which can capture the non-linearities in data and handle quite a large set of features backed by parallel processing power promises to fill that void. There are several factors that any valid pricing model will have to take into account. These factors are underlying asset, strike price, time to expiration, volatility, interest rates, expected dividends and still there is a lot need in order to be able simulate option prices. which then encompass their significance when pricing an option. Furthermore, given their ability to integrate real-time market data (incorporating the India VIX), liquidity measures and economic indicators, these models can tackle some of the shortcomings that plague conventional methodologies. The other ultimate tools to achieve this goal are Option Greeks which plays a very important role in Options Pricing & Risk Management. This paper presents a detailed literature review of latest deep learning architectures applied on option pricing. This study addresses these issues while also bringing novel contributions to an important area of research that has not received attention yet, e.g., market specific models nuanced with the Indian scenario and necessity for a hybrid deep learning approach combining state-of-the-art volatility forecasting alongside data driven methods. © 2024 IEEE.

关键词： Derivatives Option Pricing Volatility Index

来源：评论

学校读者我要写书评

暂无评论

CNN Modeling for Recognizing Rice Leaf Diseases 15

CNN Modeling for Recognizing Rice Leaf Diseases

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Ghosh, Urmi Rokoni, Sakib Rahman, Md.Ataur Rahman, Md. Sadekur Habib, Md. Tarek Iub Independent University Bangladesh Fab Lab Dhaka Bangladesh

ISBN: (纸本)9798350370249

This study explores the application of deep learning techniques to the identification of diseases affecting rice leaf tissue. Among the most crucial staple crops farmed worldwide is rice. However, its health is in jeopardy due to several illnesses that harm both its productivity and its quality. The detection of these illnesses by manual means can be a time-consuming process that is also prone to mistakes. As a result, the current study presents an automated method that makes use of deep learning algorithms to reliably diagnose and categorize rice leaf illnesses based on photographs. The research makes use of a sizable collection of annotated photographs of rice leaf patterns. These photographs are fed into convolutional neural networks (CNNs) to be trained and evaluated. The results of the experiments show that the approach that was presented was successful. They illustrate that it is possible to get a high level of accuracy when diagnosing and classifying diseases. The model that was built offers a potentially useful approach for the early and accurate identification of rice leaf diseases. This opens the door for prompt intervention and effective management techniques that can reduce crop losses and assure food security. © 2024 IEEE.

关键词： CNN image processing Rice Leaf Disease Transfer learning

来源：评论

学校读者我要写书评

暂无评论

deep learning for real-time Drowsiness Onset Detection 2

Deep Learning for Real-Time Drowsiness Onset Detection

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Govindaraj, M. Asha, V. Katingeri, Mohammed Mazil Manvanth, L.J. Ch, Mouli Raghavendra Prashanth Mathew, Jincy C New Horizon College of Engineering Master of Computer Applications Bengaluru India

ISBN: (纸本)9798350317558

Drowsiness detection is a pivotal element in ensuring the well-being of both drivers' and passengers safety, as it helps prevent accidents caused by tired or drowsy individuals behind the wheel. This research introduces an advanced hybrid model to effectively and swiftly identify drowsiness in real-time. The process commences with data pre-processing, involving the capture and examination of facial images of the driver for analysis. These images go through different pre-processing stages, including resizing, converting to grayscale, and reducing noise through a blend of filters, such as Weiner and Median filters. Our model similar to ResNet, is meticulously fine-tuned and optimized using sophisticated techniques, including Aquila optimization, to enhance its performance. The primary objective of this model is to ascertain whether the driver is in a drowsy or alert state. The model's performance is rigorously assessed and benchmarked against previous research in the field. The attained outcomes by our proposed drowsiness detection model are truly impressive, boasting an F1 score of 98.98%, an accuracy rate of 99.2%, a sensitivity rate of 98.9%, a specificity rate of 99.1%, and a precision rate of 99%. These exceptional metrics underscore the model's effectiveness in accurately identifying drowsiness, underscoring its importance in promoting road safety. © 2024 IEEE.

关键词： Accident prevention Convolutional Neural Networks Eye tracking Onset Detection real-time Detection time cumulative effect

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：