检索结果-内蒙古大学图书馆

Chromosome analysis using a hybrid deep CNN and structural feature-based grouping model

Multimedia Tools and applications 2025年 1-30页

作者： Isfahani, Farahnaz Peiravi Pourghassem, Hossein Mahdavi-Nasab, Homayoun Naghsh, Alireza Department of Electrical Engineering Najafabad Branch Islamic Azad University Najafabad Iran Digital Processing and Machine Vision Research Center Najafabad Branch Islamic Azad University Najafabad Iran

Chromosome analysis and classification are essential in clinical applications to diagnose various structural and numerical abnormalities. Recently, karyotype analysis using intelligent image processing methods, especially deep learning, has attracted significant attention as a genetic abnormality test. This paper presents a novel chromosome classification algorithm that uses high-level features extracted from deep convolutional neural networks (DCNN) along with morphological features designed to identify and modify the classes of misclassified chromosomes. Initially, chromosomes are classified using a DCNN. Some structural features, such as centromere and banding profile, are then extracted to group chromosomes again. Based on the results of the two preceding methods, a decision strategy is utilized to identify misclassified chromosomes. Here, a final DCNN-based strategy is introduced to assign misclassified chromosomes to the associated classes. The proposed method can be used in parallel with other chromosome classification methods to modify misclassified chromosomes and promote the accuracy of the classification. Evaluation results show that the proposed algorithm outperforms relevant state-of-the-art algorithms regarding the classification precision and accuracy of 99.66 and 96.52%, respectively. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

The Background Also Matters: Background-Aware Motion-Guided Objects Discovery

The Background Also Matters: Background-Aware Motion-Guided ...

引用

IEEE/CVF Winter Conference on applications of Computer vision (WACV)

作者： Kara, Sandra Ammar, Hejer Chabot, Florian Quoc-Cuong Pham Univ Paris Saclay CEA List F-91120 Palaiseau France

ISBN: (纸本)9798350318920;9798350318937

Recent works have shown that objects discovery can largely benefit from the inherent motion information in video data. However, these methods lack a proper background processing, resulting in an over-segmentation of the non-object regions into random segments. This is a critical limitation given the unsupervised setting, where object segments and noise are not distinguishable. To address this limitation we propose BMOD, a Background-aware Motion-guided Objects Discovery method. Concretely, we leverage masks of moving objects extracted from optical flow and design a learning mechanism to extend them to the true foreground composed of both moving and static objects. The background, a complementary concept of the learned foreground class, is then isolated in the object discovery process. This enables a joint learning of the objects discovery task and the object/non-object separation. The conducted experiments on synthetic and real-world datasets show that integrating our background handling with various cutting-edge methods brings each time a considerable improvement. Specifically, we improve the objects discovery performance with a large margin, while establishing a strong baseline for object/non-object separation.

关键词： Algorithms Algorithms Algorithms and algorithms formulations image recognition and understanding machine learning architectures Video recognition and understanding

来源：评论

学校读者我要写书评

暂无评论

FPGA-Based Implementation of Real-Time Cardiologist-Level Arrhythmia Detection and Classification in Electrocardiograms Using Novel Deep Learning

引用

INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND applications 2024年第0期

作者： Chandrasekaran, Saravanakumar Chandran, Srinivasan Selvam, Immaculate Joy SRM Valliammai Engn Coll ECE Chennai Tamil Nadu India Rajalakshmi Engn Coll EEE Chennai Tamil Nadu India Saveetha Engn Coll ECE Chennai Tamil Nadu India

Cardiac arrhythmia refers to irregular heartbeats caused by anomalies in electrical transmission in the heart muscle, and it is an important threat to cardiovascular health. Conventional monitoring and diagnosis still depend on the laborious visual examination of electrocardiogram (ECG) devices, even though ECG signals are dynamic and complex. This paper discusses the need for an automated system to assist clinicians in efficiently recognizing arrhythmias. The existing machine-learning (ML) algorithms have extensive training cycles and require manual feature selection;to eliminate this, we present a novel deep learning (DL) architecture. Our research introduces a novel approach to ECG classification by combining the vision transformer (ViT) and the capsule network (CapsNet) into a hybrid model named ViT-Cap. We conduct necessary preprocessing operations, including noise removal and signal-to-image conversion using short-time Fourier transform (SIFT) and continuous wavelet transform (CWT) algorithms, on both normal and abnormal ECG data obtained from the MIT-BIH database. The proposed model intelligently focuses on crucial features by leveraging global and local attention to explore spectrogram and scalogram image data. Initially, the model divides the images into smaller patches and linearly embeds each patch. Features are then extracted using a transformer encoder, followed by classification using the capsule module with feature vectors from the ViT module. Comparisons with existing conventional models show that our proposed model outperforms the original ViT and CapsNet in terms of classification accuracy for both binary and multi-class ECG classification. The experimental findings demonstrate an accuracy of 99% on both scalogram and spectrogram images. Comparative analysis with state-of-the-art methodologies confirms the superiority of our framework. Additionally, we configure a field-programmable gate array (FPGA) to implement the proposed model for real-time ar

关键词： accuracy arrhythmia capsule network deep learning electrocardiogram field-programmable gate array power processing time vision transformer

来源：评论

学校读者我要写书评

暂无评论

DeepMesh: Differentiable Iso-Surface Extraction

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND machine INTELLIGENCE 2024年第11期46卷 7072-7087页

作者： Guillard, Benoit Remelli, Edoardo Lukoianov, Artem Yvernay, Pierre Richter, Stephan R. Bagautdinov, Timur Baque, Pierre Fua, Pascal Ecole Polytech Fed Lausanne Comp Vis Lab CH-1015 Lausanne Switzerland MIT Grp Geometr Data Proc Cambridge MA 02139 USA Neural Concept CH-1015 Lausanne Switzerland Intel Labs Hillsboro OR 97124 USA Meta Real Labs Menlo Pk CA 94025 USA

Geometric Deep Learning has recently made striking progress with the advent of continuous deep implicit fields. They allow for detailed modeling of watertight surfaces of arbitrary topology while not relying on a 3D euclidean grid, resulting in a learnable parameterization that is unlimited in resolution. Unfortunately, these methods are often unsuitable for applications that require an explicit mesh-based surface representation because converting an implicit field to such a representation relies on the Marching Cubes algorithm, which cannot be differentiated with respect to the underlying implicit field. In this work, we remove this limitation and introduce a differentiable way to produce explicit surface mesh representations from Deep Implicit Fields. Our key insight is that by reasoning on how implicit field perturbations impact local surface geometry, one can ultimately differentiate the 3D location of surface samples with respect to the underlying deep implicit field. We exploit this to define DeepMesh - an end-to-end differentiable mesh representation that can vary its topology. We validate our theoretical insight through several applications: Single view 3D Reconstruction via Differentiable Rendering, Physically-Driven Shape Optimization, Full Scene 3D Reconstruction from Scans and End-to-End Training. In all cases our end-to-end differentiable parameterization gives us an edge over state-of-the-art algorithms.

关键词： Three-dimensional displays Topology Task analysis Surface reconstruction Shape Mesh generation Surface treatment Computational and artificial intelligence neural networks electronic design automation and methodology design methodology graphics shape computers and information processing image processing machine vision object recognition mathematics geometry computational geometry geometric modeling mathematics numerical analysis surface fitting systems engineering and theory systems, man, and cybernetics user interfaces data visualization isosurfaces

来源：评论

学校读者我要写书评

暂无评论

LEHA: A novel lightweight efficient and highly accurate lane departure warning system

引用

MULTIMEDIA TOOLS AND applications 2024年第9期83卷 26307-26332页

作者： Chen, Yue Sun, Peng Boukerche, Azzedine Univ Ottawa PARADISE Res Lab 800 King Edward Ave Ottawa ON K1N6N5 Canada Duke Kunshan Univ Dept Data Sci 8 Duke Ave Kunshan 215316 Jiangsu Peoples R China Gulf Univ Sci & Technol Ctr Appl Math & Bioinformat CAMB Hawally Kuwait

As one of the most indispensable means of transportation in modern society, vehicles guarantee our daily commuting and logistics transportation. However, with the increasing number of vehicles, vehicles have also caused increasingly serious traffic safety problems while providing convenience to our lives. One of the most common of these is traffic accidents caused by vehicle yaw due to driver distraction. As a potential solution to this problem, lane departure warning systems (LDWS) focus on detecting and determining whether the vehicle is deviating from the driveway, considered an essential part of autonomous driving technology, and have received significant attention in recent years. A large number of different types of LDWS systems have been developed, especially in recent years, with the development of artificial intelligence technology, many methods based on deep learning and machine vision have been proposed. However, it is well known that due to the complexity of the network structure in deep learning-based object detection algorithms, the operation of such methods relies on a large amount of computing power support. However, due to the limitation of the overall energy supply of the vehicle, it is usually unable to support computing power similar to the laboratory level. Therefore, how to realize efficient lane departure warnings under the condition of limited computing power is a critical problem to be solved. Accordingly, in this paper, we propose a novel lightweight LDWS model. Different from deep learning methods of LDWS, our LDWS model LEHA can achieve high accuracy and efficiency by relying only on simple hardware. The proposed LEHA consists of three modules: the image processing module, the lane detection module, and the lane departure recognition module. The image pre-processing module is applied to pre-process the original road image, which can improve the accuracy and efficiency of the following lane detection module. After obtaining the processed i

关键词： Land departure warning system image preprocessing Lane detection Lane departure recognition

来源：评论

学校读者我要写书评

暂无评论

Wild Animal Detection System on a Farm Using image processing

Wild Animal Detection System on a Farm Using Image Processin...

引用

International Conference on Advances and applications of Artificial Intelligence and machine Learning, ICAAAIML 2023

作者： Barhate, Madhuri Gulhane, Nandini Gunjal, Tanvi Gudi, Swaroop Gulhane, Vedant Wagade, Prasad Gude, Ayush Vishwakarma Institute of Technology Maharashtra Pune411037 India

ISBN: (纸本)9789819795062

Human civilization is based on agriculture, and one of the biggest threats to agricultural productivity is the existence of wild animals on farmlands. Animals are taking over some farmlands, causing significant crop losses, property damage, and livestock risks. As a result, suitable solutions must be developed. A system to support farmers is necessary because the conventional method of constant guard monitoring is impractical. Modern technologies like machine learning, computer vision, and image processing are used by this wild animal detection system to effectively manage conflicts between humans and wildlife. machine learning and computer vision rely on the integration of particular algorithms to guarantee the accuracy and effectiveness of the system. With an emphasis on sustainability, the technology protects property and crops while also aiding in the conservation of wildlife. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Livestock

来源：评论

学校读者我要写书评

暂无评论

Authentication and Verification in Human-Robot Cooperative Robotic Cells using Stereo vision and Gesture Control 6

Authentication and Verification in Human-Robot Cooperative R...

引用

6th IEEE International Conference on image processing, applications and Systems, IPAS 2025

作者： Kovacs, Gabor Sziranyi, Tamas HUN-REN Institute for Computer Science and Control Machine Perception Research Laboratory Budapest Hungary

ISBN: (纸本)9798331506520

The integration of human-robot interaction (HRI) technologies with industrial automation has become increasingly essential for enhancing productivity and safety in manufacturing environments. In this paper, we propose a novel approach to address these challenges by using stereo vision and gesture control in cooperative robotic cells. Our system enables seamless authentication of operators and real-time verification of task execution, ensuring compliance with established protocols and safety *** features of our system include its gesture-based operation with gesture recognition algorithms, allowing operators to interact with robotic systems intuitively and efficiently. By leveraging stereo vision, our system accurately tracks the operators' movement within the workspace, facilitating precise task execution and object *** present a detailed description of our system architecture, experimental configuration, and real-world performance assessment. Our results demonstrate the effectiveness and feasibility of our approach in enhancing operational efficiency, ensuring quality, and improving the overall user experience in industrial automation. © 2025 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Deep Representation Learning: Fundamentals, Technologies, applications, and Open Challenges

引用

IEEE ACCESS 2023年 11卷 137621-137659页

作者： Payandeh, Amirreza Baghaei, Kourosh T. Fayyazsanavi, Pooya Ramezani, Somayeh Bakhtiari Chen, Zhiqian Rahimi, Shahram George Mason Univ Dept Comp Sci Fairfax VA 22030 USA Mississippi State Univ Dept Comp Sci Mississippi State MS 39762 USA

machine learning algorithms have had a profound impact on the field of computer science over the past few decades. The performance of these algorithms heavily depends on the representations derived from the data during the learning process. Successful learning processes aim to produce concise, discrete, meaningful representations that can be effectively applied to various tasks. Recent advancements in deep learning models have proven to be highly effective in capturing high-dimensional, non-linear, and multi-modal characteristics. In this work, we provide a comprehensive overview of the current state-of-the-art in deep representation learning and the principles and developments made in the process of representation learning. Our study encompasses both supervised and unsupervised methods, including popular techniques such as autoencoders, self-supervised methods, and deep neural networks. Furthermore, we explore a wide range of applications, including image recognition and natural language processing. In addition, we discuss recent trends, key issues, and open challenges in the field. This survey endeavors to make a significant contribution to the field of deep representation learning, fostering its understanding and facilitating further advancements.

关键词： Representation learning deep learning feature extraction transfer learning natural language processing computer vision

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Techniques for the effective diagnosis of Alzheimer's Disease: A Review

引用

MULTIMEDIA TOOLS AND applications 2023年第13期83卷 40057页

作者： Shastry, K. Aditya Sanjay, H. A. Nitte Meenakshi Inst Technol Bangalore 560064 Karnataka India M S Ramaiah Inst Technol Dept Biotechnol Bangalore 560054 Karnataka India

Alzheimer's disease (AD) is a progressive and irreversible neurological disorder that leads to memory loss and cognitive decline. It is a prevalent form of dementia among individuals aged 65 and above. Accurate and early diagnosis of AD is of utmost importance. Diagnostic neuroimaging and software techniques have emerged as crucial tools for assessing early-stage dementia. The aim of this study is to provide a comprehensive review of recent research that employs deep learning (DL) techniques for the assessment of dementia, particularly the early stages of AD. The objective is to analyze the current state of research and explore the future directions of this field. The study involves a systematic review of literature that focuses on the utilization of DL techniques in the assessment of dementia and early AD diagnosis. Various datasets commonly used for AD prediction are examined. The study encompasses the discussion of different applications of contemporary AI algorithms in AD detection, as well as their merits, limitations, and performance. The review reveals that DL techniques have shown promise in the detection and diagnosis of AD. The use of DL, particularly in image classification and natural language processing, has demonstrated significant advancements in the field of AI. The study also highlights the potential of AI in AD genetic studies, providing valuable insights into the broad scope of this research..

关键词： Artificial Intelligence Alzheimer's Disease machine Learning applications

来源：评论

学校读者我要写书评

暂无评论

Research and Implementation of Material image Subject Segmentation Method Based on machine vision 5

Research and Implementation of Material Image Subject Segmen...

引用

5th International Conference on Advances in Electrical Engineering and Computer applications, AEECA 2024

作者： Wang, Lu Qingdao University of Science and Technology Chinesisch-Deutsche Technische Fakultat Qingdao China

ISBN: (纸本)9798350355253

This article proposes a simple and effective method for image subject segmentation. Our research mainly focuses on the characteristics of material images in the experimental platform. Through in-depth research, we have found that using edge detection, morphological operations, and fill truncation can form an efficient subject segmentation technique. To verify the effectiveness of our proposed method, we conducted a series of experiments. The results indicate that our method only takes 0.238 seconds to process a single image. This speed is very impressive and demonstrates the potential application of this method on embedded devices. Our method is very suitable for embedded devices such as experimental benches. Embedded devices often have limited computing power and resources, thus requiring an efficient and lightweight subject segmentation method. Our proposed method precisely meets these requirements because it is simple and effective, and can quickly perform image subject segmentation in resource limited environments. In summary, our method has significant advantages in image subject segmentation problems. It is not only simple and easy to understand, but also efficient and fast, making it very suitable for use on embedded devices such as experimental benches. We believe that this method will have a positive impact on the field of image processing and bring more possibilities for related application areas. © 2024 IEEE.

关键词： machine vision

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：