检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zheng, Haotian Wang, Qizhou Fang, Zhen Xia, Xiaobo Liu, Feng Liu, Tongliang Han, Bo Department of Computer Science Hong Kong Baptist University Hong Kong School of Electronic Engineering Xidian University China Australian Artificial Intelligence Institute University of Technology Sydney Australia Sydney AI Centre The University of Sydney Australia School of Computing and Information Systems The University of Melbourne Australia

Out-of-distribution (OOD) detection discerns OOD data where the predictor cannot make valid predictions as in-distribution (ID) data, thereby increasing the reliability of open-world classification. However, it is typically hard to collect real out-of-distribution (OOD) data for training a predictor capable of discerning ID and OOD patterns. This obstacle gives rise to data generation-based learning methods, synthesizing OOD data via data generators for predictor training without requiring any real OOD data. Related methods typically pre-train a generator on ID data and adopt various selection procedures to find those data likely to be the OOD cases. However, generated data may still coincide with ID semantics, i.e., mistaken OOD generation remains, confusing the predictor between ID and OOD data. To this end, we suggest that generated data (with mistaken OOD generation) can be used to devise an auxiliary OOD detection task to facilitate real OOD detection. Specifically, we can ensure that learning from such an auxiliary task is beneficial if the ID and the OOD parts have disjoint supports, with the help of a well-designed training procedure for the predictor. Accordingly, we propose a powerful data generation-based learning method named Auxiliary Task-based OOD Learning (ATOL) that can relieve the mistaken OOD generation. We conduct extensive experiments under various OOD detection setups, demonstrating the effectiveness of our method against its advanced counterparts. The code is publicly available at: https://***/tmlr-group/ATOL. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Pheromone Matrix Eigenvalue-based Convergence Assessment Indicator for Ant Colony Optimization

Pheromone Matrix Eigenvalue-based Convergence Assessment Ind...

引用

Machine intelligence Theory and Applications (MiTA), International Conference on

作者： Xu Li Lin Shi Jian-Yu Li Jing Xu Zhi-Hui Zhan School of Computer Science and Engineering South China University of Technology Guangzhou P. R. China Research Center of Intelligent Computing & Big Data Technology Guangdong University of Finance and Economics Guangzhou Guangdong P. R. China College of Artificial Intelligence Nankai University Tianjin P. R. China

ISBN: (数字)9798350385670

ISBN: (纸本)9798350385687

As a crucial member of the evolutionary computation (EC), ant colony optimization (ACO) converges to the optimal result through a continuous process of iterative optimization. However, determining the convergence status of an ant colony remains a challenging task without well-established methods. To this end, this paper proposes a global evaluation indicator—average absolute eigenvalue of pheromone matrix (AAEPM) by constructing a pheromone matrix and analyzing its eigenvalue variations. This indicator aims to assess the convergence status of the ant colony during the evolutionary process. Experimental results show that the AAEPM is correlated with the convergence status of ACO and is not significantly influenced by algorithm parameters and problem scale.

关键词： Measurement Ant colony optimization Heuristic algorithms Evolutionary computation Eigenvalues and eigenfunctions Robustness Iterative methods Optimization Machine intelligence Convergence

来源：评论

学校读者我要写书评

暂无评论

A Multiscale Orchestrated Computational Framework to Reveal Emergent Phenomena in Neuroblastoma

SSRN

引用

SSRN 2023年

作者： Carlos, Borau Wertheim, K.Y. Hervas-Raluy, S. Sainz-DeMena, D. Walker, D. Chisholm, R. Richmond, P. Varella, V. Viceconti, M. Montero, A. Gregori-Puigjané, E. Mestres, J. Kasztelnik, M. García-Aznar, J.M. Mechanical Engineering Dept University of Zaragoza Zaragoza Spain Department of Computer Science Insigneo Institute for In Silico Medicine University of Sheffield Sheffield United Kingdom Department of Industrial Engineering Alma Mater Studiorum University of Bologna Italy Medical Technology Lab IRCCS Istituto Ortopedico Rizzoli Bologna Italy Baldiri Reixac 4 Barcelona Spain ACC Cyfronet AGH University of Science and Technology Kraków Poland Centre of Excellence for Data Science Artificial Intelligence and Modelling and School of Computer Science University of Hull Kingston upon Hull United Kingdom

Neuroblastoma is a complex and aggressive type of cancer that affects children. Current treatments involve a combination of surgery, chemotherapy, radiotherapy, and stem cell transplantation. However, treatment outcomes vary due to the heterogeneous nature of the disease. Computational models have been used to analyse data, simulate biological processes, and predict disease progression and treatment outcomes. While continuum cancer models capture the overall behaviour of tumors, and agent-based models represent the complex behaviour of individual cells, multiscale models represent interactions at different organisational levels, providing a more comprehensive understanding of the system. In 2018, the PRIMAGE consortium was formed to build a cloud-based decision support system for neuroblastoma, including a multi-scale model for patient-specific simulations of disease progression. This model, integrated into an online platform, will allow clinicians to optimise treatment regimens and reduce the number of costly and time-consuming clinical trials. This work outlines the challenging framework's model architecture, data workflow, hypothesis, and resources employed in its development. © 2023, The Authors. All rights reserved.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Research on Hand-Oriented Tactile Evoked Brain-computer Interface Rehabilitation Method

Research on Hand-Oriented Tactile Evoked Brain-Computer Inte...

引用

Chinese Control Conference (CCC)

作者： Wanmeng Cai Lingling Chen Xin Guo Mengge Wang School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin China Intelligent Rehabilitation Device and Detection Technology Engineering Research Centre of the Ministry of Education Tianjin China Control Engineering Technology Innovation Center of Hebei Province Hebei University of Technology Tianjin P.R. China School of Electrical Engineering Hebei University of Technology Tianjin China

In recent years, the incidence of stroke has increased due to the growing issue of aging, significantly affecting the quality of life of patients. Functional hand rehabilitation is one of the common symptoms. However, in most cases, mechanical repetitive rehabilitation methods are used clinically, lacking patient's autonomous intention and effort. Brain-computer interface (BCI) can be used as a solution to overcome such problems by proposing a hand rehabilitation protocol utilizing vibration stimulation induced P300-BCI. Firstly, the vibration stimulation module was designed to be placed at the fingertip, with the amplitude adjusted to solve the problems of patient fatigue and low tactile sensation during the experiment. Secondly, the optimal channel was selected using the P300 characteristics evoked by different stimuli, and the classification accuracy was improved to more than 80% by cross-subject differences. Finally, the soft actuator chamber air pressure and bending angle are analyzed to establish the soft braking P300-BCI online system. Experimental results indicate that the actuator to a soft robotic hand based on BCI is valid in rehabilitation. This work can further promote neuroplasticity of patients and achieve closed-loop neuromotor rehabilitation for the in-loop population.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based EEG Signal Classification of Epileptic Patients

Deep Learning-Based EEG Signal Classification of Epileptic P...

引用

Expert Clouds and Applications (ICOECA), International Conference on

作者： V. Senthil Kumar C. Karpagavalli S. Pradeep S. Divya Syed Noeman Taqui Nadanakumar Vinayagam Department of Computer Science and Engineering SRM Institute of Science and Technology Tiruchirapalli Tamil Nadu India Department of Artificial Intelligence and Data Science Ramco Institute of Technology Rajapalayam Tamil Nadu India Department of Electronics and Communication Engineering S.A. Engineering College Chennai Tamil Nadu India Department of Biomedical Engineering Dr. N. G.P. Institute of Technology Coimbatore Tamil Nadu India Department of VLSI Microelectronics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Automobile Engineering Hindustan Institute of Technology and Science Padur Chennai Tamil Nadu India

ISBN: (数字)9798350385793

ISBN: (纸本)9798350385809

Epilepsy is a neurological disorder characterized by repeated seizures throughout the day. Epilepsy affects around 65 million people worldwide. For people with focal epilepsy, surgery is a possibility but medicine is the standard treatment for generalized epilepsy. Unfortunately, these medications fail to control epileptic seizures in more than 30% of patients. Yet, this ends up in accidents and significantly shortens the patient's life expectancy. An electroencephalogram (EEG) is a critical diagnostic tool for epilepsy. The conventional method for detecting epileptic activity is expert human interpretation of multi-channel EEG readings. This is a complex and time-consuming procedure, thus many researchers have tried to automate it using Machine Learning (ML) and Deep Learning (DL) methods. Unfortunately, the investigation did not produce satisfactory results. This study aims to fill this research gap by proposing a new CNN-BLSTM (Convolutional Neural Network-Bidirectional Long Short-Term Memory) based hybrid DL model for epileptic detection. The EEG data from Kaggle was collected and processed. This study uses the same amount of data and epochs for training, validation, and testing all four DL models such as AlexNet, VGG-16, InceptionV3, and the proposed model. According to the experiment findings, the proposed model has a better level of accuracy (98.37 % ) than the other three models.

关键词： Training Accuracy Epilepsy Surgery Brain modeling Electroencephalography data models

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diagnostic Precision in Gastric Bleeding through Automated Lesion Segmentation: A Deep DuS-KFCM Approach

arXiv

引用

arXiv 2024年

作者： Liu, Xian-Xian Xu, Mingkun Wei, Yuanyuan Qin, Huafeng Song, Qun Fong, Simon Tien, Feng Luo, Wei Gao, Juntao Zhang, Zhihua Siu, Shirley The Department of Computer and Information Science University of Macau 999078 China Guangdong Institute of Intelligence Science and Technology Zhuhai519031 China Department of Biomedical Engineering The Chinese University of Hong Kong Shatin999077 China Department of Neurology David Geffen School of Medicine University of California Los AngelesCA90095 United States The School of Computer Science and Information Engineering Chongqing Technology and Business University Chongqing400067 China Institute of Artificial Intelligence Chongqing Technology and Business University Chongqing400067 China Hebei Key Laboratory of Medical Data Science Institute of Biomedical Informatics School of Medicine Hebei University of Engineering Hebei Province Handan056038 China The director of the Institute of Clinical Medicine The First People’s Hospital of Foshan Guangzhou510060 China Tsinghua University California Beijing100084 China Beijing Institute of Genomics Chinese Academy of Sciences Beijing100101 China Centre for Artificial Intelligence Driven Drug Discovery Macao Polytechnic University Rua de Luís Gonzaga Gomes 999078 China

Timely and precise classification and segmentation of gastric bleeding in endoscopic imagery are pivotal for the rapid diagnosis and intervention of gastric complications, which is critical in life-saving medical procedures. Traditional methods grapple with the challenge posed by the indistinguishable intensity values of bleeding tissues adjacent to other gastric structures. Our study seeks to revolutionize this domain by introducing a novel deep learning model, the Dual Spatial Kernelized Constrained Fuzzy C-Means (Deep DuS-KFCM) clustering algorithm. This Hybrid Neuro-Fuzzy system synergizes Neural Networks with Fuzzy Logic to offer a highly precise and efficient identification of bleeding regions. Implementing a two-fold coarse-to-fine strategy for segmentation, this model initially employs the Spatial Kernelized Fuzzy C-Means (SKFCM) algorithm enhanced with spatial intensity profiles and subsequently harnesses the state-of-the-art DeepLabv3+ with ResNet50 architecture to refine the segmentation output. Through extensive experiments across mainstream gastric bleeding and red spots datasets, our Deep DuS-KFCM model demonstrated unprecedented accuracy rates of 87.95%, coupled with a specificity of 96.33%, outperforming contemporary segmentation methods. The findings underscore the model’s robustness against noise and its outstanding segmentation capabilities, particularly for identifying subtle bleeding symptoms, thereby presenting a significant leap forward in medical image processing. © 2024, CC BY.

关键词： Medical image processing

来源：评论

学校读者我要写书评

暂无评论

Detection of Abnormalities in Chest X-Rays Using Convolutional Neural Networks

Detection of Abnormalities in Chest X-Rays Using Convolution...

引用

Paradigm Shift in Information Technologies with Innovative Applications in Global Scenario (ICPSITIAGS), IEEE International Conference on

作者： Harshith Babu Rahul Mishra P. Karthigaikumar Parikshit N. Mahalle Prasanta Kumar Parid Sachin Pund Computer Science and Engineering Hindusthan College of Engineering & Tech Coimbatore India Centre for Interdisciplinary Research in Business and Technology Institute of Engineering and Technology Chitkara University Punjab India Department of Electronics And Communication Engineering Karpagam College of Engineering Coimbatore Department of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune India Department of Rural Managementn KIIT University Bhubaneswar Department of Industrial Engineering Shri Ramdeobaba College of Engineering and Management Nagpur Maharashtra India

ISBN: (数字)9798350329773

ISBN: (纸本)9798350329780

The purpose of this look is to increase an automated gadget for detecting chest X-ray imaging abnormalities through a Convolutional Neural community (CNN). The usage of a CNN permits real-time detection of abnormalities that could otherwise be missed via radiologists, as well as increases the efficiency of clinical experts by using being able to hit upon ability abnormalities without the need for extra tests. In this observation, 285 chest scans had been accrued from a local health facility and analyzed using a custom-built CNN. Through the use of various convolutional layers, various functions have been extracted and applied to stumble on abnormalities. Adjustments to the model have been made by including additional convolutional layers and adjusting the filters. The ensuing model carried out a ninety-seven—2 % accuracy fee in identifying abnormalities in chest X-rays. The outcomes of this look display the hit implementation of a CNN in detecting abnormalities in chest X-rays. In addition, further studies are had to refine the model and boom accuracy. Moreover, similar research is recommended to examine its use in scientific decision-making for sufferers. The results of this have a look at can be seen as a step forward in the improvement of automated clinical analysis structures and their usage in clinical decision-making.

关键词： Filters Decision making Lung cancer Real-time systems Convolutional neural networks Clinical diagnosis Information technology

来源：评论

学校读者我要写书评

暂无评论

3D Skull Completion via Two-stage Conditional Diffusion-Based Signed Distance Fields

3D Skull Completion via Two-stage Conditional Diffusion-Base...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zhenhong Liu Xudong Ru Xingce Wang Zhongke Wu Yi-Cheng Zhu Chong Zhang Alejandro F. Frangi School of Artificial Intelligence Beijing Normal University Beijing China Department of Neurology Peking Union Medical College Hospital Beijing China Bioimage Analysis Barcelona Spain Department of Computer Science Christabel Pankhurst Institute Division of Informatics Imaging and Data Sciences School of Health Sciences School of Engineering The University of Manchester UK Department of Cardiovascular Sciences and the Department of Electrical Engineering Medical Imaging Research Centre (MIRC) KU Leuven Leuven Belgium Alan Turing Institute London UK

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

A fast and fully automatic design of 3D cranial implants is highly desired in cranioplasty, and is key to the treatment of skull trauma. We have defined the repair of skull defects as a 3D shape completion task by proposing a two-stage diffusion model based on the representation of 3D shapes using signed distance function (SDF). Specifically, we design a diffusion model conditioned on partial shapes, we compress the 3D shape into a compact latent representation using the encoder in the vector quantized variational autoencoder (VQ-VAE) and learn the diffusion model based on this compressed discrete representation. Encoding the latent space with the autoencoder can achieve high-quality 3D cranial shape completion. In order to accurately capture local and fine-grained shape details, the training data is geometrically encoded from a compactly learned code-book. The two-stage diffusion generator with a coarse-to-fine approach possesses precise and expressive structural modeling capabilities to ensure the supplementation of detailed geometric information. Experimental results verified sufficient expressiveness of our model with generating high-fidelity results with fine-grained local details, outperforming the state-of-the-art methods.

关键词： Solid modeling Three-dimensional displays Shape Autoencoders Training data Implants Diffusion models Skull Vectors Cranial

来源：评论

学校读者我要写书评

暂无评论

Enhancing Dynamic Images For End-To-End Training-Based Object Detection

Enhancing Dynamic Images For End-To-End Training-Based Objec...

引用

International Conference on ICT in Business Industry & Government (ICTBIG)

作者： Dharmesh Dhabliya K.S. Bhuvaneshwari Ashmeet Kaur G. Ramya Sourav Rampal Manu S. E. Department of Information Technology Vishwakarma Institute of Technology Pune India Department of Artificial Intelligence and Data Science Karpagam College of Engineering Coimbatore India Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of ECE Prince Shri Venkateshwara Padmavathy Engineering College Chennai India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh India School of Engineering and Technology Civil Engineering JAIN (Deemed to be University) Bangalore Karnataka India

ISBN: (数字)9798331518981

ISBN: (纸本)9798331518998

In computer vision, object identification using convolutional neural networks is currently trending. There will be a dramatic drop in detection ability in low-light situations due to the image's lighting component, which severely affects object identification. For improved detection results, it is recommended to use a low light picture enhancement approach as a pre processing mechanism to increase image quality. However, current enhancing strategies could be ineffective on some samples because of the intricacy of low-light conditions. As a result, doing better overall detection in low-light circumstances is challenging. We focus on improving object recognition accuracy using picture augmentation in this work, not human perceptual quality. The proposed image enhancement model is compared with the other enhancement techniques such as Histogram equalization (HE), Contrast limited adaptive histogram equalization (CLAHE), gamma correction (GC), and balance contrast enhancement technique (BCET). For the object detection we have used three different methods of CNN to evaluate our image enhancementmodel. With a high detection rate of 98%, the suggested technique outperforms competing CNN algorithms on bigger datasets. When compared to GC, HE, CLAHE, and BCET, our suggested strategy yields more efficient object identification with values of 0.8219), 0.8052 (recall), and 0.8133 (F1-score).

关键词： Measurement Histograms computer vision Computational modeling Lighting Object detection Adaptive equalizers Object recognition Convolutional neural networks Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Lightweight Neural Network Based Garbage Image Classification Using a Deep Mutual Learning 1

引用

11th International Symposium on Parallel Architectures, Algorithms and Programming, PAAP 2020

作者： Liu, Xiao Wu, Zhi-Ze Wu, Zi-Jun Zou, Le Xu, Li-Xiang Wang, Xiao-Feng Department of Environmental Engineering Hefei University Hefei Anhui230601 China Anhui Provincial Engineering Laboratory of Big Data Technology Application for Urban Infrastructure Department of Computer Science and Technology Hefei University Hefei230601 China Institute of Applied Optimization School of Artificial Intelligence and Big Data Hefei University Hefei Anhui230601 China

ISBN: (数字)9789811600104

ISBN: (纸本)9789811600098

With the construction and development of civilized cities, image based garbage classification has gradually become an important concern in computer vision community. During the algorithms for image classification, the strong ability of Convolution Neural Networks (CNNs) in feature learning makes it the most successful approach at the moment. However, the parameters of CNNs model are very huge, and its training usually depends on a large amount of samples. In this article, we tackle the problem of lightweight neural network based garbage image classification, which aims to learn classifier with a small number of model parameters. Specifically, we utilize the MobileNetV2 for the backbone of feature extraction network and jointly train such two nets in a way of deep mutual learning. It realizes the information distillation between the teacher and the student. With this, we can significantly improve the learning ability of the MobileNetV2 based lightweight neural network. The experimental results on a self-assembled dataset show that our proposal effectively classifies the garbage and achieves a classification effect batter than the state of the arts in terms of testing accuracy, time and model size. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Image classification

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：