检索结果-内蒙古大学图书馆

4th International Conference on Power, Energy, Control and Transmission Systems, ICPECTS 2024

作者： Vaithiyanathan, M. Bala, K. Bharath Institute of Higher Education and Research Department of Computer Science and Engineering Tamil Nadu Chennai600073 India School of Computing Bharath Institute of Higher Education and Research Department or Computer Science and Engineering Tamil Nadu Chennai600073 India

ISBN: (纸本)9798331508845

Neural stem cells are a specific type of stem cells that are unique in their capacity to self-renew and differentiate into neurons and glial cells, including neurons, oligodendrocytes and astrocytes the latter contributing to the developmental process of the nervous system. In a bid to implement this approach in identifying imaging features related to neural stem cells, this study aims at using deep convolutional neural networks (CNNs) at a middle level. In the study, the primary focus is laid on the consideration of the distribution of the number of CD133+ neural stem cells as well as their possible migration in rat brain areas. Absolute quantification studies delineated marked qualitative differences in the localization of these cells across distinct regions of the brain. Most importantly, we found out that CD133+ neural stem cells could move from subventricular zone (SVZ) to almost near different parts of the brain including ganglia, corpus callosum and cerebral cortex. Before undergoing surgery, the activity of the rats was trained through water maze learning, respectively recording their escape latency (EL) at the time point of one week, two weeks, and one month. The findings clearly showed that EL was longer in the cerebral ischemia-reperfusion as compared with the sham-operated control group. Nevertheless, a significant decrease in EL was seen in the group treated with electroacupuncture after ischemia-reperfusion. From this it could be extrapolated that electroacupuncture may improve the viability and differentiation of newly generated neural stem cells into both glial and neuronal lineages. In extension, electroacupuncture promoted new neuron formation and a subset was found to be functional when they secreted acetylcholine. Taken together, the present study showed that electroacupuncture facilitated neurological recovery in cerebral ischemia-reperfusion rats. © 2024 IEEE.

关键词： Stem cells

来源：评论

学校读者我要写书评

暂无评论

deep learning, Machine learning - Digital Signal and image processing: From Theory to Application

arXiv

引用

arXiv 2024年

作者： Hsieh, Weiche Bi, Ziqian Liu, Junyu Peng, Benji Zhang, Sen Pan, Xuanhe Xu, Jiawei Wang, Jinlang Chen, Keyu Yin, Caitlyn Heqi Feng, Pohsun Wen, Yizhu Wang, Tianyang Li, Ming Ren, Jintao Niu, Qian Chen, Silin Liu, Ming National Tsing Hua University Taiwan Indiana University United States Kyoto University Japan AppCubic Rutgers University United States University of Wisconsin-Madison United States Purdue University United States Georgia Institute of Technology United States National Taiwan Normal University Taiwan University of Hawaii United States Xi’an Jiaotong-Liverpool University China Aarhus University Denmark Zhejiang University China

Digital Signal processing (DSP) and Digital image processing (DIP) with Machine learning (ML) and deep learning (DL) are popular research areas in Computer Vision and related fields. We highlight transformative applications in image enhancement, filtering techniques, and pattern recognition. By integrating frameworks like the Discrete Fourier Transform (DFT), Z-Transform, and Fourier Transform methods, we enable robust data manipulation and feature extraction essential for AI-driven tasks. Using Python, we implement algorithms that optimize real-time data processing, forming a foundation for scalable, high-performance solutions in computer vision. This work illustrates the potential of ML and DL to advance DSP and DIP methodologies, contributing to artificial intelligence, automated feature extraction, and applications across diverse domains. Copyright © 2024, The Authors. All rights reserved.

关键词： Discrete Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

TPU Based deep learning image Enhancement for real-time Point-of-Care Ultrasound

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING

引用

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 2024年 10卷 461-468页

作者： Huang, Ouwen Palmeri, Mark L. Duke Univ Dept Biomed Engn Durham NC 27708 USA

Handheld ultrasound devices are becoming more prevalent in point-of-care ultrasound workflows. However, these devices are computationally constrained which challenges the advances in deep learning methodology for real-time use on mobile Point-of-care ultrasound (POCUS) devices. In this work, we explore the feasibility of running MimickNet, a deep learning clinical post-processing model, on Tensor processing Units (TPUs), hardware designed for deep learning operations capable of running on only 2 watts of power at 1.8 V with a form factor of 10 mm x 15 mm. We show that real-time deep learning based post-processing is feasible at 20 - 120 FPS for 1472x160 to 224x224 axial sample x B-mode scan line configurations. We refer to the TPU based model as MimickNet Mobile. MimickNet Mobile achieves outputs nearly identical to the original MimickNet with a structural similarity index measurement (SSIM) of 0.98 +/- 0.001 and a mean squared error (MSE) of 0.0001 +/- 0.0 over our test set of 588 frames consisting of 168 phantom frames and 420 prospectively acquired human liver frames. We investigate the latency of other common mobile architectures such as separable convolution. Finally, we investigate the distribution of model parameter error when quantizing MimickNet float32 weights to MimickNet Mobile int8 weights. This work demonstrates that real-time POCUS deep learning image enhancement is feasible using TPUs. Future ultrasound device manufacturers can consider incorporating a TPU for the added flexibility of supporting several deep learning architectures without compromising on power management and form factor.

关键词： Clinical ultrasound deep learning image enhancement MimickNet real-time processing TPU

来源：评论

学校读者我要写书评

暂无评论

Dental Periapical Lesion Detection with Retinex image processing and an Efficient deep learning Model

Dental Periapical Lesion Detection with Retinex Image Proces...

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： C.A. Aslin Christo Julia Punitha Malar Dhas Deva Priya Computer Science and Engineering Karunya University Coimbatore India

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

Dental periapical lesions help doctors understand your oral health needs and must be found accurately to deliver proper treatment. The research introduces a new way to find dental periapical lesions by combining Retinex image processing with YOLOv8 object detection. The Retinex method lets the model detect periapical lesions more accurately because it enhances image details while removing picture noise. Test outcomes show enhanced lesion detection that performs well with precise accuracy in tough image scenarios. The research demonstrates how advanced image processing helps medical imaging deep learning systems work better. The Objective of this work is to improve visibility of periapical lesions by Retinex based enhancement and fast detection through YOLOv8.

关键词： deep learning Radiography Visualization Object detection real-time systems Skin Dentistry Lesions X-ray imaging Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Empirical Assessment of Identifying Human Blood Group Based on image processing Assisted deep learning Principles

Empirical Assessment of Identifying Human Blood Group Based ...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： G. Ramkumar N. Janardhana Rao V. Nanammal SK. Shaphiya J Giri Ahmad Abdelhafiz Ali Samhan Dept of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai Department of MBA QIS College of Engineering and Technology Ongole Andhra Pradesh Department of Electronics and Communication Engineering Jeppiaar Engineering College Chennai Department of S&H QIS College of Engineering and Technology Ongole AndhraPradesh Department of Mechanical Engineering Yeshwantrao Chavan College of Engineering Nagpur India Division of Research and Development Lovely Professional University Phagwara India Department of Software Engineering Faculty of Information Technology Zarqa University Zarqa Jordan University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

This study presents an empirical assessment of identifying human blood groups using image processing assisted by deep learning principles, specifically employing a cascaded Convolutional Neural Network (CNN) and Light Gradient Boosting Machine (LightGBM). Traditional methods of blood group identification are time-consuming and prone to errors, prompting the need for automated, more efficient systems. In this work, a CNN model was initially used to extract deep features from blood sample images, followed by a LightGBM classifier for final blood group classification. A comprehensive dataset, representing all major blood groups (A, B, AB, O, and Rh types), was collected and preprocessed for training and testing. The cascaded CNN-LightGBM approach achieved an accuracy of 92.4%, significantly outperforming baseline models, including standalone CNN (88.2%) and Random Forest (83.5%). The model also demonstrated high precision (92.1%), recall (92.0%), and F1-score (92.1%). real-world testing was conducted to validate its robustness in clinical settings. The results indicate that the proposed model is well-suited for accurate and efficient blood group identification, with low inference time, making it ideal for real-time applications. This approach has the potential to transform blood diagnostics by providing an automated, scalable, and accurate solution.

关键词： deep learning Training Accuracy Transforms Feature extraction Robustness real-time systems Convolutional neural networks Blood Testing

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of image processing and deep learning Techniques for License Plate Recognition in Difficult Environments

A Comparative Analysis of Image Processing and Deep Learning...

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： Tejaswi S Tina Babu Tejaswi K Department of Computer Science Seshadripuram Degree College Mysuru India Department of Computer Science and Engineering School of Engineering Alliance University Bengaluru India Department of Computer Applications JSS Science and Technology University Mysuru India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

License plate recognition is one of the challenging tasks and it belongs to ITS, due to backgrounds, variation of illumination, occlusion the recognition is became the challenging task. These challenges enabled a comparison between the conventional image enhancement and the deep learning scheme for license plate recognition. We analyze and compare multiple techniques that we consider significant, including, the Edge detection, Morphological operations and template matching and also deep learning models like CNNs and R-CNNs. In this framework of experiment scenarios, we scale out a comprehensive evaluation of the methods given different datasets and compare their accuracy, speed as well as stability in conditions that may be hostile. In the experiments, we see that Naive Bayes and SVM outperform in low-resource conditions, but deep learning methods are significantly more accurate and more flexible in accommodating complicated cases and trends, which makes deep learning methods the method of choice for contemporary applications. This work provides an understanding of the strengths and weaknesses of both approaches to serve as a guideline in choosing the most effective detection techniques in relation to certain environmental conditions.

关键词： deep learning Support vector machines YOLO Accuracy Lighting Computer architecture real-time systems Vectors License plate recognition Meteorology

来源：评论

学校读者我要写书评

暂无评论

Understanding Satellite image processing and Black Box Models with Ante-Hoc and Post-Hoc Explanations in deep learning

Understanding Satellite Image Processing and Black Box Model...

引用

International Conference on Communications and Signal processing

作者： Sai Bhargav Kasetty K Rajakumar School of Computer Science & Engineering V. I. T Vellore Tamilnadu India

ISBN: (数字)9798350353068

ISBN: (纸本)9798350353075

This research aims to investigate the challenges of using black box models in deep learning and analyzing satellite images through a thorough meta-analysis. The main goal of the study is to improve transparency and interpretability, with a focus on providing explanations both before and after model training. Transparency elements are integrated into models during the initial stages to enhance their clarity. Following the completion of training for complex models, explanations are utilized to comprehend how decisions are made. The research focuses on using both of these approaches to tackle the issues linked with deep learning models in satellite image processing. Through the use of design-time and post-modeling methods, AI can be used for analyzing satellite images in a way that is easier to understand and accountable.

关键词： deep learning Training Analytical models Satellites Signal processing algorithms Signal processing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Underwater image processing and Target Detection Algorithm Based on deep learning

Underwater Image Processing and Target Detection Algorithm B...

引用

作者： Zheng, Yangning Yang, Yang School of Medicine Nanchang Institute of Technology Jiangxi Nanchang China School of Electronics and Information Nanchang Institute of Technology Jiangxi Nanchang China

With the growth of the earth’s population, people’s demand for space and resources continues to grow, making marine environmental research and exploration a new field that human development needs. The composition of the marine environment is unique to humans, and the application of intelligent underwater vehicle equipment with the ability to autonomously detect and recognize the environment can expand the scope of human research in the ocean. This article focuses on the research of underwater image processing and target detection algorithms based onDL, and understands the relevant theories of underwater image processing and target detection based on the literature, and then the underwater image processing and target detection algorithms based on DL In the design, in order to improve the accuracy of target detection, the DL model is optimized, and the optimized model is tested. The test result shows that if the Atrous convolution operation is added, the calculation amount of the network model will increase, resulting in *** speed drops to 50FPS. But after adding Atrous processing, the detection accuracy will be improved accordingly. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

Cotton Plant Disease Detection and Prevention Using deep learning and image processing

Cotton Plant Disease Detection and Prevention Using Deep Lea...

引用

International Conference on Reliability, Infocom Technologies and Optimization (ICRITO) (Trends and Future Directions)

作者： Ruthvija Kesani Jaya Prakash Sunkavalli Mahamamad Rafi Shaik Kusuma Yadala Dept. of Information Technology Velagapudi Ramakrishna Siddhartha Engineering College Vijayawada India

ISBN: (数字)9798350350357

ISBN: (纸本)9798350350364

One of the most important aspects of the agricultural economy is the production of cotton, which is threatened by diseases that lower crop quality and yield. Conventional techniques for diagnosing diseases are frequently subjective and labor-intensive. This paper presents a novel method for the automatic detection and prevention of cotton plant diseases that makes use of deep learning techniques. A convolutional neural network (CNN) model is trained using a dataset that includes various photos of both healthy and sick cotton plants. The suggested model offers a dependable and time-efficient solution by exhibiting high accuracy in differentiating between different diseases. Moreover, proactive disease detection is made possible by the integration of real-time monitoring systems, such as drones fitted with high-resolution cameras. Early detection lessens the need for broadspectrum antibiotics by enabling the prompt application of preventive measures, such as targeted therapies. Finally, we conduct a comprehensive computational analysis of eight cutting-edge object detection algorithms on the cotton plant dataset to identify diseases on the leaves and seven cutting-edge classification algorithms on the cotton plant datasets to determine if a leaf has a disease or not. computed results indicate that it has a high degree of object detection accuracy.

关键词： deep learning Plant diseases image processing Plants (biology) Transfer learning Object detection Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

License Plate reader with PUC Details using image processing and deep learning 2

License Plate reader with PUC Details using Image Processing...

引用

2nd International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2023

作者： Patil, R.S. Deshpande, Sakshi Khan, Hassan Mhatre, Prajakta Bharati Vidyapeeth College of Engineering Department of Electronics and Telecommunication Engineering Maharashtra Mumbai India

ISBN: (纸本)9798350348002

As each vehicle is uniquely acknowledged by its license plate, the Transport System places a high priority on finding and recognizing of license plates. The news is constantly reporting on accidents and missing cars. Authorities must acknowledge all of these unlawful acts. As a result, research into the identification and recognition of vehicle number plates is ongoing. However, identifying a vehicle's number plate has always been difficult for a number of reasons, such as brightness changes, shadows cast by moving vehicles, erratic license plate character types, different plate styles, and color effects caused by the surroundings. In this system, Number plate of vehicle is detected from a live video or an image. There is image preprocessing and segmentation done on the live video or number plate image. deep learning model methods are used, the characters from it are separated and then each character gets recognized. This helps to collect the vehicle overall project then the capabilities of different techniques into one integrated automatic system are summarized. This kind of systems can be implemented on the roadside and makes a real time comparison between passing car and list of stolen cars. This detected license plate number could also be used in car parking systems. PUC which stands for Pollution Under Control, where emission levels of vehicles and the regular renovation of the PUC certificate is done or not is verified and the details are shown. This will help in keeping an overall check on vehicles and the task which most of the places do manually to check the PUC certificate for checking status, can be verified quickly and the fine can be implemented as per so. © 2023 IEEE.

关键词： Optical character recognition

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：