检索结果-内蒙古大学图书馆

An Automatic Framework for Detecting Autism Spectrum Disorder From EEG Signals Using TFD

IEEE SENSORS JOURNAL 2024年第7期24卷 10632-10639页

作者： Lalawat, Rajveer Singh Bajaj, Varun Indian Inst Informat Technol Design & Mfg Jabalpur Dept Elect & Commun Engn Jabalpur 482005 India Maulana Azad Natl Inst Technol Bhopal Dept Elect & Commun Bhopal 462003 India

Autism spectrum disorder (ASD) is an intricate neurodevelopmental disorder with many neurological problems. Social interaction and communication issues, repetitive behaviors, and limited interests are its main symptoms. Manual ASD diagnosis testing is prone to human error, time-consuming, and difficult owing to contamination from a number of factors. Electroencephalogram (EEG) signals are extensively utilized to identify ASD as they represent brain abnormalities. This study employed a novel method that included pre-processing, segmentation, and time-frequency distribution (TFD) of various algorithms such as short-time Fourier transformation (STFT), continuous wavelet transformation (CWT), and smoothed pseudo-Wigner-Ville distribution (SPWVD), which produced corresponding spectrograms, scalograms, and SPWVD-TFD. These TFDs are introduced into the DenseNet-121 and ResNet-101 pre-trained (imageNet dataset) models, and then subsequently fed into the proposed ASD-Net. deep learning networks (DLMs) models were utilized to identify ASD and Normal subject using these TFD images. We acquired a 97.35% mean accuracy utilizing the SPWVD-based TFD and ASD-Net model. When compared to the benchmark DenseNet-121 and ResNet-101, the developed convolution neural network (CNN) model with five convolution layers (CLs) not only needs less learnable parameters but is also computationally efficient and quick.

关键词： Electroencephalography Continuous wavelet transforms Variable speed drives time-frequency analysis Brain modeling image segmentation IIR filters Autism spectrum disorder (ASD) convolution neural network (CNN) electroencephalogram (EEG) smoothed pseudo-Wigner-Ville distribution (SPWVD) time-frequency distribution (TFD)

来源：评论

学校读者我要写书评

暂无评论

Advancing Event Recognition in Videos Using Hybrid deep learning Model

Advancing Event Recognition in Videos Using Hybrid Deep Lear...

引用

2024 IEEE International Conference on Recent Advances in Science and Engineering Technology, ICRASET 2024

作者： Jyothi, H. Komala, M. Mallikarjunaswamy, S. Sjb Institute of Technology Dept of Electronics and Communication Engineering Bengaluru India Jss Academy of Technical Eduction Dept of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350388602

Event recognition in videos plays a critical role in various applications such as surveillance, security, and human-computer interaction. Conventional methods like Hidden Markov Models (HMM) and Support Vector Machines (SVM) have been extensively used, but they often struggle with handling complex data patterns and large-scale video datasets, leading to limited accuracy and inefficiency in real-time scenarios. These approaches fail to capture intricate temporal dependencies and suffer from high computational costs, making them less effective for dynamic event detection. To address these limitations, we propose a Hybrid deep learning Event Recognition Model (HDL-ERM), which combines the strengths of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks. CNN is used for feature extraction, while LSTM effectively captures temporal sequences in video data. The HDL-ERM model significantly improves event recognition accuracy by 0.25%, while reducing computational load by 0.18% compared to conventional methods. By leveraging deep learning techniques, our proposed model enhances performance across various parameters such as processing speed, detection accuracy, and adaptability to different video environments. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

GAN And Semi-supervised learning-Based Indoor Visible Light Localization System for image Sensors

GAN And Semi-supervised Learning-Based Indoor Visible Light ...

引用

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

作者： Chen, Duiqiang Cui, Lizhen Qin, Ling Wang, Fengying College of Information Engineering Inner Mongolia University of Science and Technology Inner Mongolia Baotou China

ISBN: (纸本)9781510680012

Aiming at the visible light localization system in the fingerprint acquisition link, which is time-consuming and inefficient, this paper proposes a visible light localization system based on generative adversarial network and semi-supervised learning to realize high-efficiency fingerprint acquisition and high-precision localization. Firstly, the image of the lamp is captured using a CMOS smartphone, and the fingerprint database is constructed by feature extraction of the feature image of the lamp using image processing technology, which can increase the diversity and richness of the fingerprint database;secondly, the unlabeled pseudo-fingerprint data is generated by GAN network, which expands the dataset, thus reduces the cumbersomeness of fingerprint acquisition and improves the efficiency of fingerprint acquisition;lastly, the real fingerprint data and pseudo-fingerprint data are mixed with semi-supervised training of CNN models for location prediction. The experimental results show that in the experimental space of 2.25m×1.65m×3m, only 1564 labeled fingerprint data are collected in this paper, and the achieved average error of localization is 2.48cm. among them, the probability of error less than 5cm accounts for 90%, which meets the indoor localization requirements. © 2024 SPIE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Decentralized Multi-layer Vehicular Edge Computing Framework for time-Efficient Task Coordination 19

Decentralized Multi-layer Vehicular Edge Computing Framework...

引用

19th IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Fardad, Mohammad Muntean, Gabriel-Miro Tal, Irina Dublin City Univ Sch Comp Dublin Ireland Dublin City Univ Sch Elect Engn Dublin Ireland

ISBN: (纸本)9798350364279;9798350364262

Vehicle edge computing (VEC) offers substantial potential to enhance real-time applications in the connected autonomous vehicle (CAV) sector by positioning edge servers near CAVs. The need to balance real-time application demands and the diversity of tasks underscores the criticality of carefully deciding whether to process these tasks locally or to offload them for remote processing. This decision is pivotal in achieving efficient resource management, particularly in dynamic vehicular environments, emphasizing the requirement of exquisite policies to optimize VEC systems' performance within the CAV ecosystem. While centralized policies face limitations in managing large-scale deployments, decentralized approaches often fail to foster effective collaboration and coordination among CAVs. This paper proposes a novel multi-layered, decentralized framework designed for time-efficient task management and optimized network resource utilization in dynamic vehicular scenarios to address these limitations. This framework incorporates a novel multi-agent deep reinforcement learning (MADRL) algorithm to enable intelligent decision-making for efficient task execution. The proposed algorithm considers the diverse computing capabilities of network entities, aiming to reduce latency without compromising task completion rates. Simulation results demonstrate that our proposed algorithm has superior performance in latency reduction while improving task completion rates compared to existing algorithms.

关键词： Vehicular edge computing Task coordination Multi-agent deep-reinforcement learning latency

来源：评论

学校读者我要写书评

暂无评论

Pick-and-Place Transform learning for Fast Multi-View Clustering

引用

IEEE TRANSACTIONS ON image processing 2024年 33卷 1272-1284页

作者： Shen, Qiangqiang Chen, Yongyong Zhang, Changqing Tian, Yonghong Liang, Yongsheng Harbin Inst Technol Shenzhen Sch Elect & Informat Engn Shenzhen 518055 Guangdong Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Shenzhen 518055 Peoples R China Guangdong Prov Key Lab Novel Secur Intelligence Te Shenzhen 518055 Peoples R China Tianjin Univ Tianjin Key Lab Machine Learning Tianjin 300350 Peoples R China Tianjin Univ Coll Intelligence & Comp Tianjin 300350 Peoples R China Peking Univ Sch Comp Sci Beijing 100871 Peoples R China

To manipulate large-scale data, anchor-based multi-view clustering methods have grown in popularity owing to their linear complexity in terms of the number of samples. However, these existing approaches pay less attention to two aspects. 1) They target at learning a shared affinity matrix by using the local information from every single view, yet ignoring the global information from all views, which may weaken the ability to capture complementary information. 2) They do not consider the removal of feature redundancy, which may affect the ability to depict the real sample relationships. To this end, we propose a novel fast multi-view clustering method via pick-and-place transform learning named PPTL, which could capture insightful global features to characterize the sample relationships quickly. Specifically, PPTL first concatenates all the views along the feature direction to produce a global matrix. Considering the redundancy of the global matrix, we design a pick-and-place transform with & ell;(2,p) -norm regularization to abandon the poor features and consequently construct a compact global representation matrix. Thus, by conducting anchor-based subspace clustering on the compact global representation matrix, PPTL can learn a consensus skinny affinity matrix with a discriminative clustering structure. Numerous experiments performed on small-scale to large-scale datasets demonstrate that our method is not only faster but also achieves superior clustering performance over state-of-the-art methods across a majority of the datasets.

关键词： Transforms Matrix decomposition Dictionaries Clustering methods time complexity Sparse matrices Security Multi-view clustering subspace clustering large-scale clustering feature selection

来源：评论

学校读者我要写书评

暂无评论

Optimizing Brain Tumor Detection with Multi-head deep Convolutional Neural Network: An Effective Framework for MRI based Classification and Analysis 2

Optimizing Brain Tumor Detection with Multi-head Deep Convol...

引用

2nd IEEE International Conference on Integrated Intelligence and Communication Systems, ICIICS 2024

作者： Biradar, Shivaprasad Virupakshappa Department of Computer Science & Engineering Sharnbasva University Kalaburagi Kalaburagi India

ISBN: (纸本)9798331504960

Various detection techniques are used to find brain tumors, but MRI is the most reliable because of its high image resolution. However, classifying brain tumors manually takes a lot of time. This study suggests a novel method for classifying brain tumors called the Multi-head deep Convolutional Neural Network (MHDCovNet) Algorithm in order to overcome these difficulties. The Data Pre-processing phase includes improvements like noise reduction, image sharpening, and the removal of non-brain tissues (skull stripping) to guarantee the images are of high quality appropriate for analysis. The above steps are essential for getting images ready for further examination. Important attributes, such as statistical and texture-based features, are extracted from the pre-processed MRI scans in the Feature Extraction phase in order to obtain the information required for classification. A complex Multi-head deep Convolutional Neural Network (MHDCovNet), which makes use of cutting-edge deep learning features like multi-head attention and global average pooling, is used to achieve the final phase, tumor classification. The effectiveness of the developed technique in classifying brain tumors is then demonstrated by comparing the results with state of the art methods. © 2024 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 image style transfer algorithm based on semantic perception 3

Research on image style transfer algorithm based on semantic...

引用

3rd International Conference on Electronic Information Engineering, Big Data, and Computer Technology, EIBDCT 2024

作者： Jia, Lu Dai, Hongbing Zhang, Liguo Yunnan Sports Vocational and Technical College Yunnan Kunming650228 China

ISBN: (纸本)9781510680449

image style transfer has been widely concerned in the field of computer vision, and has important application value in cultural heritage, social media and public security case detection. At present, the mainstream style transfer algorithm is based on deep learning, which is fast and can achieve real-time effect. However, the generated stylized image has some problems such as texture deformation and edge blurring. In this paper, the arbitrary style transfer algorithm is studied. The arbitrary style transfer method is not limited by style types, and it does not need to retrain the model when transferring new styles. However, the stylized images generated by the existing algorithm are prone to fuzzy texture and inconsistent color distribution with semantic information. To solve these problems, a framework for semantic perceptual style transfer based on identity loss is proposed. Firstly, the adaptive attention normalization model is adopted to comprehensively consider shallow features and deep features to carry out stylistic attention weighting. Secondly, an image is input into the network as both style image and content image to measure the loss. At the same time, the semantic local mapping and global statistics between content features and style features are considered. Finally, by learning the same features between content and style, richer and more accurate semantic and style expressions can be obtained. The experimental results show that the texture features of the stylized image obtained by this method are clearer, the color is more vivid, and the effect is better. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Transformation learning for Equivariant Representations 38

Self-supervised Transformation Learning for Equivariant Repr...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Yu, Jaemyung Choi, Jaehyun Lee, Dong-Jae Hong, HyeongGwon Kim, Junmo Korea Republic of

Unsupervised representation learning has significantly advanced various machine learning tasks. In the computer vision domain, state-of-the-art approaches utilize transformations like random crop and color jitter to achieve invariant representations, embedding semantically the same inputs despite transformations. However, this can degrade performance in tasks requiring precise features, such as localization or flower classification. To address this, recent research incorporates equivariant representation learning, which captures transformation-sensitive information. However, current methods depend on transformation labels and thus struggle with interdependency and complex transformations. We propose Self-supervised Transformation learning (STL), replacing transformation labels with transformation representations derived from image pairs. The proposed method ensures transformation representation is image-invariant and learns corresponding equivariant transformations, enhancing performance without increased batch complexity. We demonstrate the approach's effectiveness across diverse classification and detection tasks, outperforming existing methods in 7 out of 11 benchmarks and excelling in detection. By integrating complex transformations like AugMix, unusable by prior equivariant methods, this approach enhances performance across tasks, underscoring its adaptability and resilience. Additionally, its compatibility with various base models highlights its flexibility and broad applicability. The code is available at https://***/jaemyung-u/stl. © 2024 Neural information processing systems foundation. All rights reserved.

关键词： Equivariant learning Self-supervised Transformation learning Transformation Representation

来源：评论

学校读者我要写书评

暂无评论

deep learning Based Mobile Platform for Predicting Passenger Congestion in Public Transportation 8

Deep Learning Based Mobile Platform for Predicting Passenger...

引用

8th International Artificial Intelligence and Data processing Symposium, IDAP 2024

作者： Kavanoz, Abdulkerim Kosak, Halil Ibrahim Aksakalli, Isil Karabey Bayindir, Levent Erzurum Technical University Department of Computer Engineering Erzurum Turkey Kocaeli University Department of Software Engineering İzmit Turkey

ISBN: (纸本)9798331531492

Population growth in Turkey has led to significant congestion in transportation systems. This congestion results in delays for individuals using public transportation, often causing them to arrive hours early to ensure punctuality at their destinations. Passengers frequently lack real-time information about the current occupancy of public transportation vehicles, leading to uncertainty and potential inefficiencies as they wait at bus stops. In some cases, public transportation vehicles reach full capacity, leaving passengers at the stop unserved. Moreover, it is crucial for passengers to be aware of the crowd levels at various stops, as this affects their ability to efficiently board and travel, particularly on smaller vehicles such as minibuses where stop density is a key consideration. As a result, passengers must make informed decisions based on both vehicle and stop density, as well as the estimated vehicle arrival time. To address these challenges, we propose a deep learning-based mobile platform designed to detect crowd density at bus stops and within public transportation vehicles. This platform will notify both the transit manager and the passengers about real-time density information. Our approach involves analyzing 20 -minute video footage from Mersin Municipality, Turkey, using Mask-RCNN,YOLOv5, YOLOv8, and YOLOv9 models to count passengers boarding and alighting. The models were evaluated on accuracy, precision, sensitivity, F1 score, Frame Per Second (FPS), and Intersection Over Union (IOU) metrics. The experimental results indicated that the YOLOv9 model significantly outperformed the other models, achieving 88 % accuracy, 86.2 % precision, 89 % recall, 15.2 fps, and 0.78 IoU. © 2024 IEEE.

关键词： Mass transportation

来源：评论

学校读者我要写书评

暂无评论

Synthesizing human brain CT images from MRI with deep learning

引用

INTERNATIONAL JOURNAL OF MODELING SIMULATION AND SCIENTIFIC COMPUTING 2024年第1期15卷

作者： Zhou, Longfei Pu, Chenghan Lu, Yuyang Zhang, Ying Han, Ke Jin, YiRui Zhang, Shengquan Liu, Kaihua Duke Univ Durham NC 27705 USA Nanjing Univ Aeronaut & Astronaut Nanjing Jiangsu 210000 Peoples R China Jiangnan Univ Wuxi 214000 Jiangsu Peoples R China Nanjing Univ Informat Sci & Technol Nanjing Jiangsu 210000 Peoples R China Univ Queensland Brisbane Qld 4072 Australia Harbin Inst Technol Weihai Weihai 264209 Shandong Peoples R China

Rapid development of artificial intelligence techniques significantly promotes important medical imaging applications such as disease diagnosis, medical image analysis and cross-modality synthesis. It is valuable to synthesize Computed Tomography (CT) scans of human brains from Magnetic Resonance Imaging (MRI) scans because CT images contain particular information for diseases such as malignant tumors, cerebrovascular malformations and aneurysms. Although there has been many studies trying to apply machine learning methods (e.g., fully convolutional neural networks and generative adversarial networks) to predict CT images based on MRI, there are still opportunities to increase the quality of synthesized CT images using the latest machine learning algorithms. In this study, we aim to synthesize high-credibility human brain CT images from MRI images using machine learning approaches. We build a dataset of both CT and MRI images of 41 patients from The Cancer Imaging Archive. A data pre-processing pipeline is designed to guarantee that the processed images are suitable as inputs to machine learning algorithms. The pipeline includes (1) pairing MRI and CT scans according to a certain time interval between CT and MRI exams of the same patient, (2) registering all MRI images to a standard MRI template, (3) registering all CT images to paired MRI images, (4) intensity normalization and (5) extracting 2D slices from 3D CT and MRI volumes. Three deep neural networks with encoder-decoder structure are selected and implemented including U-Net, U-Net++ and pix2pix to synthesize human brain CT images from MRI images. Experimental results illustrate that U-Net++ shows better performance than U-Net and pix2pix in synthesizing CT images from MRI by achieving a Mean Squared Error of 0.025, a Mean Absolute Error of 0.082 and a Peak Signal-to-Noise Ratio of 67.90, respectively. The trained machine learning models from this work can be applied in future human brain CT image prediction

关键词： Medical imaging Computed Tomography Magnetic Resonance Imaging human brain machine learning cross-modality synthesis

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：