检索结果-内蒙古大学图书馆

Automatic skin lesion classification using a novel densely connected convolutional network integrated with an attention module

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第7期14卷 8943-8956页

作者： Shan, Pufang Chen, Jialei Fu, Chong Cao, Lin Tie, Ming Sham, Chiu-Wing School of Computer Science and Engineering Northeastern University Shenyang110819 China Engineering Research Center of Security Technology of Complex Network System Ministry of Education Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China School of Information and Communication Engineering Beijing Information Science and Technology University Beijing100101 China Science and Technology on Space Physics Laboratory Beijing100076 China School of Computer Science The University of Auckland Auckland New Zealand

Automated skin lesion classification in dermoscopy images remains challenging due to the existence of artefacts and intrinsic cutaneous features, diversity of lesion morphology, insufficiency of training data, and class imbalance problem. To address these challenges, we propose a new densely connected convolutional network termed AttDenseNet-121, which is obtained by integrating the convolutional block attention module (CBAM) into DenseNet-121. CBAM is a simple yet efficient attention module, which is further improved by adding a novel pooling layer (multiscale-pooling) to effectively enhance its attention capability. The optimized CBAM strengthens the representation power of DenseNet-121 by emphasizing meaningful features and suppressing unnecessary ones, thus significantly enhancing the classification performance. Besides, to handle the imbalanced dataset, we employ an improved focal loss function rather than the traditional cross-entropy loss function to train AttDenseNet-121. The improved focal loss is calculated from a different perspective compared with the original focal loss. It makes the distribution of positive samples and negative samples in each batch the same as that in the original data, successfully mitigating the negative influence of class imbalance on this multi-class classification task. We conduct extensive experiments on the public benchmark dataset (HAM10000) and the results indicate that our proposed method achieves superior performance compared with that of the baselines and state-of-the-art algorithms. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

An Improved Deadlock Recovery Policy of Flexible Manufacturing Systems Based on Resource Flow Graphs

引用

IEEE Access 2024年 12卷 65202-65212页

作者： Tseng, Ching-Yun Chen, Ju-Chin Pan, Yen-Liang National Kaohsiung University of Science and Technology Department of Electronic Engineering Kaohsiung807618 Taiwan R.O.C. Air Force Academy Mathematics and Physics Division General Education Center Gangshan Kaohsiung820009 Taiwan National Kaohsiung University of Science and Technology Department of Computer Science and Information Engineering Kaohsiung807618 Taiwan Chaoyang University of Technology Department of Aeronautical Engineering Taichung413310 Taiwan

The system deadlock problem of the flexible manufacturing system (FMS) needs to be solved urgently. Deadlocks may occur when resources are repeatedly requested by multiple working processes, where such competition causes a lack of resources, and the system cannot get into subsequent processes smoothly. In this paper, we build FMS by using a particular class of Petri Net (PN) model called a system of simple sequential processes with resources (S3PR) net, which features a high utilization rate of resources. When parts of resources are held by related processes and these processes wait for others to release resources to move on, a circular waiting situation occurs. Circular waiting is one of the conditions for system deadlocks occurring, where the system under this situation has a high probability of causing system deadlocks. The resources being held have to be released to break the waiting states. This paper develops a novel control transition-based deadlock recovery policy by combining graph theory and reachability graph analysis technique. The proposed approach firstly builds a subnet of the PN model called resource flow graph (RFG) and finds out all its hold and request circuits (HRCs), which may lead to a circular waiting situation. In addition, we design a new algorithm to obtain the minimal set of control transitions further. We introduce three PN models of FMS to demonstrate the proposed method. Through experimental results and comparison between related works, it is known that the proposed deadlock recovery uses fewer controllers and has the same performance. © 2013 IEEE.

关键词： Frequency modulation

来源：评论

学校读者我要写书评

暂无评论

Cancer Cytoplasm Segmentation from Cell image Based on Transfer Learning 24

Cancer Cytoplasm Segmentation from Cell Image Based on Trans...

引用

6th International Conference on image, Video and Signal Processing, IVSP 2024

作者： Sultana, Rebeka Horibe, Hibiki Murakami, Tomoaki Shimizu, Ikuko Institute Of Global Innovation Research Tokyo University Of Agriculture And Technology Tokyo Japan Institute Of Agriculture Division Of Animal Life Science Tokyo University Of Agriculture And Technology Tokyo Japan Institute Of Engineering Division Of Advanced Information Technology & Computer Science Tokyo University Of Agriculture And Technology Tokyo Japan

ISBN: (纸本)9798400716829

image segmentation is one of the most popular approaches used in digital pathology. Most existing deep learning-based image segmentation models extract nuclear from the background in cell images. The nuclear of cancer cell images are irregular in shape and size, with unclear borders. Detecting cancer regions from cell images for detailed analysis depending on the diagnosis's purpose, including other regions, is also necessary. Because of the characteristics of cancer cell images, conventional segmentation models trained on existing datasets targeted to extract cell regions only fail to detect cancer cytoplasm in cell images. Therefore, in this research, H&E stained cancer cell images are labeled manually, and segmentation is performed by transfer learning using a conventional method to segment cancer cytoplasm in cell images. Experimental results confirm that the IoU and dice coefficient are improved by 14% and 2%, respectively, compared to the method without transfer learning. © 2024 Owner/Author.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Evaluation of State-of-the-Art Deep Learning Models for Road Surface Type Classification

引用

Intelligent Automation & Soft Computing 2023年第8期37卷 1275-1291页

作者： Narit Hnoohom Sakorn Mekruksavanich Anuchit Jitpattanakul Image Information and Intelligence Laboratory Department of Computer EngineeringFaculty of EngineeringMahidol UniversityNakhon Pathom73170Thailand Department of Computer Engineering School of Information and Communication TechnologyUniversity of PhayaoPhayao56000Thailand Department of Mathematics Faculty of Applied ScienceKing Mongkut’s University of Technology North BangkokBangkok10800Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Science and Technology Research InstituteKing Mongkut’s University of Technology North BangkokBangkok10800Thailand

In recent years,as intelligent transportation systems(ITS)such as autonomous driving and advanced driver-assistance systems have become more popular,there has been a rise in the need for different sources of traffic situation *** classification of the road surface type,also known as the RST,is among the most essential of these situational data and can be utilized across the entirety of the ITS ***,the benefits of deep learning(DL)approaches for sensor-based RST classification have been demonstrated by automatic feature extraction without manual *** ability to extract important features is vital in making RST classification more *** work investigates the most recent advances in DL algorithms for sensor-based RST classification and explores appropriate feature extraction *** used different convolutional neural networks to understand the functional architecture better;we constructed an enhanced DL model called SE-ResNet,which uses residual connections and squeeze-and-excitation mod-ules to improve the classification *** experiments with a publicly available benchmark dataset,the passive vehicular sensors dataset,have shown that SE-ResNet outperforms other state-of-the-art *** proposed model achieved the highest accuracy of 98.41%and the highest F1-score of 98.19%when classifying surfaces into segments of dirt,cobblestone,or asphalt ***,the proposed model significantly outperforms DL networks(CNN,LSTM,and CNN-LSTM).The proposed RE-ResNet achieved the classification accuracies of asphalt roads at 98.98,cobblestone roads at 97.02,and dirt roads at 99.56%,respectively.

关键词： Road surface type classification deep learning inertial sensor deep pyramidal residual network squeeze-and-excitation module

来源：评论

学校读者我要写书评

暂无评论

Pre-Impact and Impact Fall Detection Based on a Multimodal Sensor Using a Deep Residual Network

引用

Intelligent Automation & Soft Computing 2023年第6期36卷 3371-3385页

作者： Narit Hnoohom Sakorn Mekruksavanich Anuchit Jitpattanakul Image Information and Intelligence Laboratory Department of Computer EngineeringFaculty of EngineeringMahidol UniversityNakhon Pathom73170Thailand Department of Computer Engineering School of Information and Communication TechnologyUniversity of PhayaoPhayaoThailand Department of Mathematics Faculty of Applied ScienceKing Mongkut’s University of Technology North BangkokBangkok 10800Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Science and Technology Research Institute King Mongkut’s University of Technology North BangkokBangkok 10800Thailand

Falls are the contributing factor to both fatal and nonfatal injuries in the ***,pre-impact fall detection,which identifies a fall before the body collides with the floor,would be ***,researchers have turned their attention from post-impact fall detection to pre-impact fall ***-impact fall detection solutions typically use either a threshold-based or machine learning-based approach,although the threshold value would be difficult to accu-rately determine in threshold-based ***,while additional features could sometimes assist in categorizing falls and non-falls more precisely,the esti-mated determination of the significant features would be too time-intensive,thus using a significant portion of the algorithm’s operating *** this work,we developed a deep residual network with aggregation transformation called FDSNeXt for a pre-impact fall detection approach employing wearable inertial *** proposed network was introduced to address the limitations of fea-ture extraction,threshold definition,and algorithm *** training on a large-scale motion dataset,the KFall dataset,and straightforward evaluation with standard metrics,the proposed approach identified pre-impact and impact falls with high accuracy of 91.87 and 92.52%,*** addition,we have inves-tigated fall detection’s performances of three state-of-the-art deep learning models such as a convolutional neural network(CNN),a long short-term memory neural network(LSTM),and a hybrid model(CNN-LSTM).The experimental results showed that the proposed FDSNeXt model outperformed these deep learning models(CNN,LSTM,and CNN-LSTM)with significant improvements.

关键词： Pre-impact fall detection deep learning wearable sensor deep residual network

来源：评论

学校读者我要写书评

暂无评论

An Efficient ResNetSE Architecture for Smoking Activity Recognition from Smartwatch

引用

Intelligent Automation & Soft Computing 2023年第1期35卷 1245-1259页

作者： Narit Hnoohom Sakorn Mekruksavanich Anuchit Jitpattanakul Department of Computer Engineering Image Information and Intelligence LaboratoryFaculty of EngineeringMahidol UniversityNakhon Pathom73170Thailand Department of Computer Engineering School of Information and Communication Technology University of PhayaoPhayao56000Thailand Department of Mathematics Faculty of Applied ScienceKing Mongkut’s University of Technology North BangkokBangkok10800Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Science and Technology Research InstituteKing Mongkut’s University of Technology North BangkokBangkok 10800Thailand

Smoking is a major cause of cancer,heart disease and other afflictions that lead to early *** effective smoking classification mechanism that provides insights into individual smoking habits would assist in implementing addiction treatment *** activities often accompany other activities such as drinking or ***,smoking activity recognition can be a challenging topic in human activity recognition(HAR).A deep learning framework for smoking activity recognition(SAR)employing smartwatch sensors was proposed together with a deep residual network combined with squeeze-and-excitation modules(ResNetSE)to increase the effectiveness of the SAR *** proposed model was tested against basic convolutional neural networks(CNNs)and recurrent neural networks(LSTM,BiLSTM,GRU and BiGRU)to recognize smoking and other similar activities such as drinking,eating and walking using the UT-Smoke *** different scenarios were investigated for their recognition performances using standard HAR metrics(accuracy,F1-score and the area under the ROC curve).Our proposed ResNetSE outperformed the other basic deep learning networks,with maximum accuracy of 98.63%.

关键词： Smoking activity recognition deep residual network smartwatch sensors deep learning

来源：评论

学校读者我要写书评

暂无评论

Competition on robust deep learning

引用

National science Review 2023年第6期10卷 13-15页

作者： Yinpeng Dong Chang Liu Wenzhao Xiang Hang Su Jun Zhu Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML Center THBI Lab BNRist Center Tsinghua University Institute of Image Communication and Networks Engineering in the Department of Electronic Engineering (EE) Shanghai Jiao Tong University Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Peng Cheng Laboratory Pazhou Laboratory (Huangpu)

PROBLEM In recent years,the rapid development of artificial intelligence (AI) technology,especially machine learning and deep learning, is profoundly changing human production and *** various fields,such as robotics,face recognition,autonomous driving and healthcare,AI is playing an important ***,although AI is promoting the technological revolution and industrial progress,its security risks are often *** studies have found that the wellperforming deep learning models are extremely vulnerable to adversarial examples [1-3].The adversarial examples are crafted by applying small,humanimperceptible perturbations to natural examples,but can mislead deep learning models to make wrong *** vulnerability of deep learning models to adversarial examples can raise security and safety threats to various realworld applications.

关键词： robustness adversarial example adversarial training deep learning

来源：评论

学校读者我要写书评

暂无评论

Report-Guided Cross-Modal Representation Learning for Predicting EGFR Mutations by Whole Slide image

Report-Guided Cross-Modal Representation Learning for Predic...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Qiao, Qi Shi, Jun Jiang, Zhiguo Wang, Wei Wu, Haibo Zheng, Yushan Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Hefei University of Technology School of Software Hefei230601 China Beihang University Image Processing Center School of Astronautics Beijing102206 China University of Science and Technology of China Division of Life Sciences and Medicine Department of Pathology First Affiliated Hospital of Ustc Hefei230036 China University of Science and Technology of China Intelligent Pathology Institute Division of Life Sciences and Medicine Hefei230036 China Beihang University School of Engineering Medicine Beijing Advanced Innovation Center for Biomedical Engineering Beijing100191 China

ISBN: (纸本)9798350386226

Traditional PCR/NGS-based multigene panel testing is time-consuming and costly. Predicting EGFR mutations directly from H&E stained whole slide images (WSIs) can alleviate these limitations. Furthermore, histopathological reports contain valuable textual information that correlates with tissue areas in WSIs. However, recent research mainly analyses EGFR mutation status only from a single modality, ignoring rich information contained in reports. In this paper, we propose a report-guided cross-modal representation learning method for predicting EGFR mutations by WSIs. Specifically, we reconstruct report-level embeddings through exploring intrinsic relationships between diagnostic words in histopathological reports and tissue areas in WSIs. Finally, reconstructed histopathological report embedding and aggregated WSI embedding are fused for final prediction. More importantly, molecular testing report is also introduced as prior supervision information at the training stage to guarantee semantic consistency of fused feature and molecular report embedding. We evaluate our method on the TCGA-EGFR public benchmark dataset and an in-house clinical dataset (USTC-EGFR). Experimental results demonstrate that our method outperforms existing approaches in EGFR mutation prediction, highlighting the benefits of cross-modal learning in enhancing feature representational ability. The code is available at https://***/HFUT-miaLab/RCRL. © 2024 IEEE.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Lightweight Deep Residual Network for Motorcyclist Behavior Recognition Using Inertial Sensors 8

Lightweight Deep Residual Network for Motorcyclist Behavior ...

引用

8th International Conference on information technology, InCIT 2024

作者： Hnoohom, Narit Mekruksavanich, Sakorn Jitpattanakul, Anuchit Mahidol University Faculty of Engineering Image Information and Intelligence Laboratory Department of Computer Engineering Nakhon Pathom Thailand University of Phayao Department of Computer Engineering School of Information and Communication Technology Phayao Thailand King Mongkut's University of Technology Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics North Bangkok Thailand

ISBN: (纸本)9798350366303

Motorcyclist behavior recognition (MBR) is a significant factor in improving road safety and preventing accidents. Inertial sensors, such as accelerometers, gyroscopes, and magnetometers, have shown promising potential for capturing the dynamic behavior of motorcyclists. However, existing approaches often require complex models and significant computational resources, limiting their deployment in real-world scenarios. This study presents a MotoNeXt architecture, which is a light deep residual network for correctly identifying the behavior of motorcyclists using data from inertial sensors. Our approach leverages the power of deep learning while maintaining a compact model size, making it suitable for resource-constrained environments. The proposed network incorporates multi-kernel residual blocks to facilitate the learning of hierarchical features and improve gradient flow during training. We evaluate our method on a publicly available benchmark dataset, MB-IMU, collected from multiple riders under various riding conditions. Experimentation has shown that our lightweight model achieves cutting-edge performance, outperforming a variety of existing techniques. In Scenario I, using accelerometer, gyroscope, and magnetometer data, MotoNeXt achieved an accuracy result of 78.90088% along with an F1-score of 81.56738%. According to Scenario II, which included additional sensor data such as VelInc, OriInc, and Euler angles, MotoNeXt further improved its performance, achieving an accuracy result of 83.29735% along with an F1-score of 84.95352%. The proposed approach offers a practical solution for real-time MBR, enabling the development of intelligent transportation systems and rider assistance technologies. Our experiments highlight the effectiveness of lightweight deep learning models in extracting meaningful patterns from inertial sensor data. This opens up opportunities for further investigation in this field. © 2024 IEEE.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

Wasserstein Distance Constraint and Parameter Sparsification for Batched and Iterative Knowledge Editing 39

Wasserstein Distance Constraint and Parameter Sparsification...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Qiao, Shanbao Liu, Xuebing Na, Seung-Hoon Center for Advanced Image and Information Technology Department of Computer Science and Artificial Intelligence Jeonbuk National University Korea Republic of

ISBN: (纸本)157735897X

Model knowledge editing has become a widely researched topic because it enables the efficient and rapid injection of new knowledge into language models, as well as the correction of erroneous or outdated knowledge. Existing model knowledge editing methods are typically classified into two categories: single-instance sequential editing and massive one-time editing. However, the batched and iterative editing method is better aligned with model updating patterns in practical applications. In this work, we examine the performance of parameter-update-based models on a novel batched iterative editing benchmark. Our findings indicate that as the number of editing iterations increases, the accumulation of updated parameters leads to a greater shift in the model's parameter distribution, making it harder to maintain both the editing performance and the stability of the model. To address this degradation issue, we propose two methods: the Wasserstein distance constraint and the parameter update sparsification, where the Wasserstein distance constraint optimizes the transition of parameter distribution before and after editing, and the parameter update sparsification significantly reduces the number of updated parameters, thereby alleviating instability in the parameter distribution caused by their accumulation over iterations. Our methods are generally applicable to various parameter-update-based knowledge editing models. Experiments on the zsRE and CounterFact datasets demonstrate that our methods improve editing performance and enhance the stability of batched iterative editing in the later stages across different models. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Knowledge engineering

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：