检索结果-内蒙古大学图书馆

International Conference on image, Vision and intelligent Systems, ICIVIS 2023

作者： Zhou, Shangqi Li, Xintong Fu, Yanyu Ouyang, Xinyu Yang, Jinzhu Grzegorzek, Marcin Li, Chen Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China Institute of Medical Informatics University of Luebeck Luebeck Germany Department of Knowledge Engineering University of Economics in Katowice Katowice Poland

ISBN: (纸本)9789819708543

Cervical cancer ranks as the fourth most frequently diagnosed cancer. This disease has an extended precancerous stage and can be completely cured and prevented through early detection. Currently, the analysis of histopathological images of cervical cancer relies on manual assessment by pathologists, a subjective and time-consuming process. Moreover, there is limited research on differentiating the severity of cervical cancer in histopathological images. To address these challenges, this study proposes a classification algorithm based on high-order conditional random field for cervical cancer histopathologic images. The algorithm effectively categorizes images into high differentiation, medium differentiation, and low differentiation stages. Three deep learning models, namely VGG-16, Inception-V3, and ResNet-50, are utilized for pre-classification at the image block level. For image-level classification, the Visual Transformer model is employed. Finally, the block-level and image-level classification components are integrated using the conditional random field model, resulting in the high-order conditional random field model. Following training and testing using the dataset, the model achieves an overall accuracy of 75.4%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Microgrid energy management strategy considering microgrid economy and rSOC stability: A model-based study 43

Microgrid energy management strategy considering microgrid e...

引用

43rd Chinese Control Conference, CCC 2024

作者： Huang, Haizhou Xia, Zhiping Shan, Xinkai Wang, Jie Li, Xi Huazhong University of Science and Technology School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518055 China

ISBN: (纸本)9789887581581

Microgrids possess the ability to use renewable energy efficiently and play an increasingly significant role in environmental protection and sustainable development. Meanwhile, reversible solid oxide fuel cell (rSOC) is currently a new type of energy conversion and storage. Combining with microgrid systems is a great way to benefit from its high capacity, high efficiency, and cleanliness. However, rSOC's complex system of coupled heat, electricity, and gas presents a significant challenge in finding energy management strategies for microgrid applications containing rSOC. In this study, for a microgrid system combining rSOC, battery energy storage system (BESS), solar photovoltaic (PV), and wind turbine generator (WTG), we propose a model-based energy management strategy that simultaneously takes into account the economy of the microgrid system and the stability of the rSOC system. First of all, the microgrid is modeled with great detail, including the wind turbine, solar panels, battery storage system, and rSOC. In addition, the microgrid energy management problem is framed as a mathematical programming problem, with the attention focusing on the costs of BESS aging and operational energy loss of rSOC. In particular, this study also proposes a penalty strategy to reduce the power fluctuation amplitude of the rSOC system and reduce the mode switching frequency of the rSOC system. Using the solver, solving for each device's target power in a microgrid. The actual power operating curve is output by tracking the target power under slope constraints using the Simulink model. We then conduct a case study using data from Wuhan, China. Our research shows that compared with the control strategy based on rule control, the control strategy proposed in this study can reduce the power variation amplitude of the rSOC system by 79%, reduce the mode switching frequency by 85%, reduce the system operating cost by 4.5% and increase the energy self-sufficiency rate by 9%. © 2024 Techn

关键词： Wind turbines

来源：评论

学校读者我要写书评

暂无评论

Discussion on application of FLIC-Fluent coupled simulation technology on medium-scale and large-scale municipal solid waste incinerators 6

Discussion on application of FLIC-Fluent coupled simulation ...

引用

6th International Conference on intelligent Computing, Communication, and Devices, ICCD 2023

作者： Zhang, Hongze Guangxi Key Laboratory of Machine Vision and Intelligent Control Guangxi Wuzhou China Guangxi Colleges and Universities Key Lab. of Image Processing and Intelligent Information System Guangxi Wuzhou China School of Electronics and Information Engineering Wuzhou University Guangxi Wuzhou China

ISBN: (数字)9781510666269

ISBN: (纸本)9781510666252

Today, the world economy is in the stage of rapid development, followed by the rising quantity, the decreasing moisture content, and the increasing heat value of Municipal Solid Waste (MSW). Since waste incineration has the advantages of excellent volume reduction effect, high resource utilization efficiency, and less secondary pollution to the environment, waste incineration disposal technology has received extensive attention worldwide. With the continuous increase of the urban population, the amount of sewage sludge is growing year by year. The process of the sludge incineration system is highly complicated, and the cost of construction and operation is high. The waste incinerator can process not only MSW but also sewage sludge. Therefore, the co-incineration of sewage sludge with MSW in the existing waste incinerator is a safe and effective way to dispose of sewage sludge. In this paper, the simulation results of Computational Fluid Dynamics (CFD) are analyzed for medium-scale and large-scale waste incinerators, characterized by high moisture content, high ash content, low heat value of sewage sludge, and incomplete combustion and high pollutant emissions in waste incinerators. With FLIC-Fluent coupled simulation method, the critical information such as temperature field, velocity field, concentration field of principal components, and the pollutant emissions can be predicted. Based on the CFD simulation results, the performance and structure of waste incinerators can be optimized, and the new products can be designed and developed. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Waste incineration

来源：评论

学校读者我要写书评

暂无评论

Multiple Machine Learning Fusion Based analysis of Fat Composition in CT images

Multiple Machine Learning Fusion Based Analysis of Fat Compo...

引用

International Conference on image, Vision and intelligent Systems, ICIVIS 2023

作者： Fu, Yanyu Quanyu, E. Zhou, Shangqi Ouyang, Xinyu Yang, Jinzhu Grzegorzek, Marcin Li, Chen Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China Institute of Medical Informatics University of Luebeck Luebeck Germany Department of Knowledge Engineering University of Economics in Katowice Katowice Poland

ISBN: (纸本)9789819708543

Intra-abdominal fat is a crucial factor in determining metabolic syndrome and insulin resistance. Therefore, high levels of intra-abdominal fat are always accompanied by a series of diseases such as diabetes, ischemia, hypertension, and dyslipidemia. Although methods such as the ultrasonic method and electrical impedance method have been widely used to calculate body fat tissue in recent years, these methods only provide qualitative analysis of the overall degree of obesity. However, for quantitative analysis of abdominal fat and adipose tissue distribution in the human body, the computed tomography (CT) fat segmentation method is necessary. This paper focuses on machine learning, image segmentation, and multi-feature fusion of mean clustering as its main technical directions. In terms of application, it aims to perform a quantitative analysis of the distribution and proportion of intra-abdominal fat in the abdominal cavity of the human body. The study concluded that the quantitative analysis of fat after the fusion method is more accurate, with a subcutaneous fat accuracy rate of 84.26% and a visceral fat accuracy rate of 70.20%. It can effectively, conveniently, and objectively analyze the degree of obesity in the human body. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Air Pollution Monitoring By Integrating Local and Global Information in Self-Adaptive Multiscale Transform Domain

引用

IEEE Transactions on Multimedia 2025年 27卷 3716-3728页

作者： Gu, Ke Liu, Yuchen Liu, Hongyan Liu, Bo Qiao, Junfei Lin, Weisi Zhang, Wenjun Beijing University of Technology School of Information Science and Technology Engineering Research Center of Intelligent Perception and Autonomous Control of Ministry of Education Beijing Laboratory of Smart Environmental Protection Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing Artificial Intelligence Institute Beijing100124 China Massey University School of Mathematical and Computational Sciences New Zealand Nanyang Technological University College of Computing and Data Science Singapore Shanghai Jiao Tong University Institute of Image Communication and Information Processing Shanghai China

As the deadliest form of pollution, air pollution had a prolonged severe damage to the human health and life safety of nearly 99% of the world's population. Facing to the problem that billions of tons of pollutants discharged into the air per year by industrial activities, this paper proposed a novel image-based air pollution monitor (IAPM) by incorporating local and global information in the self-adaptive multiscale transform domain, so as to achieve the timely and effective leakage detection of typical air pollutants from a single image. To be specific, this paper first developed a screen-shaped module according to two significant findings in visual neuroscience, which include the high sensitivity of human eyes to horizontal and vertical stimuli and the center-surround inhibition, by designing and fusing the square module, horizontal strip module and vertical strip module parallelly for simulating the behaviour of human eyes to extract local features. Second, the learnable weights and proportional mapping were applied to incorporate the screen-shaped module and lightweight vision transformer as backbone, towards more richly exploiting and fusing local and global information just as the way a brain perceives external stimuli. Third, a new self-adaptive multiscale transform domain method was devised based on two motivations from the visual characteristics of multiscale perception and the brain characteristics of self-adaptive domain transform to modify the backbone by using the operations of pooling and pointwise convolution. Extensive experiments implemented on the datasets of carbon particulate matters and ethylene leakage confirmed the superior monitoring performance of the proposed IAPM model beyond the state-of-the-art (SOTA) peers by an accuracy gain of about 4%. Furthermore, the proposed IAPM model only required 0.089 GFLOPs and 0.15 million model parameters, remarkably outperforming SOTA competitors in computational efficiency and storage resources. © 1999-2

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Fabric Defect Defection based on Lightweight Convolutional Denoising Auto-Encoder 22

Fabric Defect Defection based on Lightweight Convolutional D...

引用

8th International Conference on Computing and Artificial Intelligence, ICCAI 2022

作者： Jin, Dong Li, Wenzheng Sun, Zhigang Li, Xiao School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781450396110

In the industrial production environment, the scarcity of defect samples and the high labor cost of labeling defect samples make supervised machine learning models difficult to implement. In addition, defect detection using deep learning models usually requires high computation cost and advanced hardware platform, which is not suitable for running on embedded platforms. To solve this problem, this paper proposes an unsupervised fabric defect detection method based on lightweight convolutional denoising auto-encoder(LCDAE). The LCDAE model is constructed by the bottleneck layer in MobileNetV3. Experimental results show that the method can effectively detect and localize defects with less computation and has the potential to perform defect detection on edge-embedded platforms. © 2022 ACM.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

A Time-Independent Control Method for Variable-Speed Load-Bearing Walking with Suspended Backpack

A Time-Independent Control Method for Variable-Speed Load-Be...

引用

第43届中国控制会议

作者： Zhiyuan He Yu Cao Yifei Guo Jian Huang Hubei Key Laboratory of Brain-inspired Intelligent Systems Key Laboratory for Image Processing and Intelligent ControlSchool of Artificial Intelligence and AutomationHuazhong University of Science and Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Walking with a load brings a significant burden to human shoulders,resulting in increasing metabolic energy consumption and the risk of skeleton and muscle *** backpack has been widely conducted for load-bearing walking,but exiting time-dependent control methods and event-based control methods are unable to exploit the characteristics of human gait *** this case,a time-independent control(TIC) method capable of eliminating the time dependence and adapting to variable speed is *** on the dynamical model of human-backpack system,an assistance profile along with the parameter optimization method are introduced which allows the backpack to reduce the burden on human shoulders during load-bearing *** the simulation evaluation,the proposed TIC method is compared with an impedance controller based time-dependent method and a locked backpack,under both constant speed and variable speed *** results demonstrates that the TIC case achieves an 89.1% reduction in dynamic load on shoulder under the condition of constant speed and a 78.2% reduction under the condition of variable speed,compared with the LOCKED case.

关键词： suspended backpack load carriage time-independent control

来源：评论

学校读者我要写书评

暂无评论

Moving Forward Together: A Multi-User Pattern Extraction Neural Model for Sequential Recommendations 23

Moving Forward Together: A Multi-User Pattern Extraction Neu...

引用

Proceedings of the 2023 6th International Conference on Artificial Intelligence and Pattern Recognition

作者： Xiangpeng Du Xiaoge Li Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xian University of Posts and Telecommunications China

ISBN: (纸本)9798400707674

The sequential recommendation is a very important task in recommendation systems. The aim of it is to dynamic predict user's interests based on their historical behaviors. Despite recent progress, most of deep learning approaches focus on extracting the behavioral patterns of a single user. Pulling multiple users can increase the diversity of historical information. In this paper, we propose multi-user behavioral pattern extraction model (TMGN) via a combination of traditional behavioral pattern extraction and graph convolutional aggregation. Concretely, TMGN first learns the graph structure of users and items. Then it performs graph convolution aggregation to derive a representation of users to extract user interest features. We recall the users with the highest similarity by calculating the cosine similarity of each candidate user. Finally, we inject multiple users' sequence patterns and time information into the muti-head attention mechanism. Experiments on actual data (Movielens1m, Movielen20m and Amazon beauty) show that the proposed method outperforms current state-of-the-art sequential recommendation methods. TMGN achieves an average improvement of 5.67%, 5.75%, 7.32%, and 7.19% over the most robust baseline in Hit@5, Hit@10, NDCG@5, and NDCG@10, respectively. We provide extensive ablation studies to analyze the impact of each model component on TMGN.

关键词： Graph Convolutional Network Self-attention Sequential Recommendation Sequential prediction Temporal Embedding

来源：评论

学校读者我要写书评

暂无评论

Dilation-Supervised Learning: A Novel Strategy for Scale Difference in Retinal Vessel Segmentation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1693-1707页

作者： Wang, Huadeng Zuo, Wenbin Li, Bingbing Pan, Xipeng Liu, Zhenbing Lan, Rushi Luo, Xiaonan Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China Guilin University of Electronic Technology School of Computer Science and Information Security Guilin541004 China Ganzhou Municipal Hospital Department of Pathology Ganzhou341000 China

Retinal fundus image segmentation based on deep learning is an important method for auxiliary diagnosis of ophthalmic diseases. Due to the scale difference of the blood vessels and the imbalance between foreground and background pixels in the fundus image, the deep learning network will inevitably ignore thin vessels when downsampling and feature learning. For the scale difference problem, this article aims to tackle its limitation from two perspectives: changing the supervised approach and adapting the feature learning. Correspondingly, a dilation-supervised learning method and an adaptive scale dimensional attention mechanism which are used to construct a two-stage segmentation model is proposed. Moreover, we introduce a quantitative approach to evaluate the scale difference of the blood vessels. With the help of the proposed weighted loss function, the segmentation results are refined, and the class imbalance problem between foreground and background pixels is resolved. Finally, the proposed adaptive threshold selection method is used in the postprocessing of segmentation results. The experiments on DRIVE, STARE, CHASE_DB1, and HRF datasets show that the proposed method achieves better segmentation performance compared with other state-of-the-art methods, and has good generalization ability and robustness. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Assist-as-Needed Variable Admittance Controller for Adaptive Support of Mobile Walking Assistive Robots 30

An Assist-as-Needed Variable Admittance Controller for Adapt...

引用

30th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2024

作者： Chen, Xinxing Zheng, Yue Su, Zongming Leng, Yuquan Huang, Jian Fu, Chenglong Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen China Huawei Technologies Technology Planning Department Shenzhen China Key Laboratory for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9798350391916

Mobile walking assistive robots have been widely used for monitoring patients' gait patterns and providing support to prevent falls. Traditional approaches often separate the operational modes of these robots into human-following and supporting modes, which can lead to discontinuities in assistance and potentially compromise safety. This paper proposes a novel assist-as-needed control strategy that incorporates a Balance Index (BI) to dynamically adjust the robot's support based on the user's balance capability. The BI is calculated using the interaction force between the user and the robot along the z-axis and the gait symmetry index (GSI). The proposed variable admittance controller modifies its parameters based on the BI, ensuring seamless transitions between compliance and support modes. Experimental validation was conducted with a healthy subject walking both with and without a knee fixation brace. The results demonstrate that the robot provides minimal interference during natural gait and increased support during impaired gait, validating the effectiveness of the proposed control strategy in enhancing user safety and promoting natural walking patterns. © 2024 IEEE.

关键词： Assistive technology

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：