检索结果-内蒙古大学图书馆

SSRN 2025年

作者： Hernández, Nerea Ortuño, Francisco Rojas, Ignacio Department of Computer Engineering Automation and Robotics ETSIIT CITIC-UGR University of Granada 18071 Spain

Colorectal cancer remains one of the leading causes of mortality worldwide, often developing from precancerous polyps. The risk of malignant transformation is closely linked to the degree of dysplasia, characterized by abnormalities in cell morphology and tissue organization. Accurate dysplasia grading is vital for early diagnosis and improved patient outcomes. Whole slide imaging (WSI) facilitates high-resolution digital analysis of tissue samples, but the complexity of histological patterns and subjective human interpretation highlight the need for more automated analysis *** this study, we propose a deep learning model for dysplasia classification in colorectal histology using a weakly supervised learning approach. Unlike traditional methods, our model does not require pixel-level annotations and can automatically identify the most relevant regions for classification. We achieve state-of-the-art accuracy, reaching 96.7\% on the CRS10K dataset and 95.5\% in external validation using TCGA images. To enhance model transparency, we integrate interpretability mechanisms through heatmap visualizations, allowing a better understanding of the model’s decision-making process. Additionally, we emphasize the importance of uncertainty-aware classification in medical Artificial Intelligence (AI), ensuring that highly confident predictions can be automated while directing expert attention to ambiguous cases. Our goal is to develop reliable and explainable AI tools that support pathologists in making accurate and timely diagnoses, ultimately improving colorectal cancer detection and patient care. © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Design and Development of an In-Pipe Mobile Robot for Pipeline Inspection with AI Defect Detection System

Design and Development of an In-Pipe Mobile Robot for Pipeli...

引用

International Conference on Control, automation and Systems ( ICCAS)

作者： Azamat Kenzhekhan Akbayan Bakytzhanova Sultan Omirbayev Yelnur Tuieubayev Madiyar Daniyalov Azamat Yeshmukhametov Department of Robotics Engineering Nazarbayev University Astana Kazakhstan Department of Robotics and Automation Satbayev University Almaty Kazakhstan

In today's modern world, pipelines serve as a vital component of the economic infrastructure of countries, serving as a lifeblood vascular system. To prevent disasters, timely inspection and maintenance operations are critical. In-pipe inspection robots are emerging as a promising solution to prevent any negative consequences in the pipeline industry. In this research, we propose a new design concept of motor placement and extension system that employs compression springs as the passive extension mechanism. The primary objective of the new design is to provide video feedback, enabling the robot to detect and recognize various types of obstructions and leak sources, including cracks, corrosion, weld defects, and deformations of the pipe structure. To further enhance the capabilities of the robot, a deep learning system will be applied with a carefully created dataset. This will enable the robot to learn and classify anomalies with increased accuracy and efficiency. This research paper is organized in the following order; introduction, robot design, control board, defect detection system, and results part with evaluation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Healthcare Monitoring Companion: The Social Robot

Healthcare Monitoring Companion: The Social Robot

引用

Artificial Intelligence For Internet of Things (AIIoT), International Conference on

作者： Rahul Goraksha Arunkumar Bongale Sameer Sayyad Satish Kumar Department of Robotics and Automation Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune India Department of Robotics and Automation Symbiosis Centre for Applied Artificial Intelligence Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

There is a rising scarcity of healthcare professionals to meet the demand of taking care of aged people. Social robots are becoming more and more popular because of the benefits they provide; during the pandemic, in particular, several of their primary applications are advantageous. The purpose of this work is to build the prototype of social robots and carry out the integration of those robots into healthcare monitoring using Thing Speak and Raspberry Pi. This prototype of social robots with Thing Speak and Raspberry Pi hosts an array of sensors (for measuring a multitude of data from the body of humans) like heartbeat sensor, Dallas temperature sensor, Radio-Frequency Identification (RFID), ultrasonic sensor, and Infrared (IR) sensor along with other components like motor controlling module and DC motor. The data from these sensors are transmitted to the cloud platform Thing Speak, offering remote monitoring and data analysis capabilities and the Raspberry Pi acts as the central processing element in our design, which additionally helps in triggering corresponding alerts regarding the patient status. Finally, we experimentally validate our design using 2 cases and then we present the assessment of the patient alerting feature.

关键词： Temperature sensors Temperature measurement Ultrasonic variables measurement Social robots Prototypes Medical services Sensors

来源：评论

学校读者我要写书评

暂无评论

Thermally Drawn Monolithic Polymer Continuum Robot with Laser Cutting Profile

Thermally Drawn Monolithic Polymer Continuum Robot with Lase...

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Liu, Huanghua Zou, Yun Xu, Zheng Gao, Anzhu Shanghai Jiao Tong University Institute of Medical Robotics Department of Automation China Ministry of Education Key Laboratory of System Control and Information Processing Shanghai200240 China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9798350325706

Continuum robots have the great potential in endoluminal diagnosis and intervention toward narrow and confined workspace. However, fabrication of continuum robots still poses a grant challenge in its miniaturization. To solve this, this paper designs a thermally drawn monolithic polymer continuum robot with laser cutting profile. First, the continuum robot is designed with two degrees of freedom (DOF) for shape deflection, and it consists of four optical fibers with the fiber Bragg grating (FBG) sensor on each for tension sensing as driving cables. Second, its main body is a multi-channel polycarbonate (PC) tube produced by thermal drawing process, and a series of rectangular cutouts are made on it via laser cutting process. By combining these two fabrication processes, the developed continuum robot realizes the integration of the multi-channel structure and the notch feature. Third, a control framework of puller-follower controller using the integrated tension sensing is proposed for teleoperation control. Finally, experimental setup is built for the robot validation, and results show that the repeated positioning accuracy of the robot is 1.08 mm. Moreover, a micro endoscope and a needle are added to the end of the continuum robot, and a phantom study of auripuncture and drug delivery is completed to verify the preliminary feasibility. And the proposed fabrication approach enables the miniaturization and complex structure for the cable-driven continuum robots. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spiking Neural Network Feature Discrimination Boosts Modality Fusion

arXiv

引用

arXiv 2025年

作者： Oikonomou, Katerina Maria Kansizoglou, Ioannis Gasteratos, Antonios Department of Production and Management Engineering Laboratory of Robotics and Automation Democritus University of Thrace Xanthi Greece

Feature discrimination is a crucial aspect in neural network design, as it directly impacts the network’s ability to distinguish between classes and generalize across diverse datasets. The accomplishment of achieving high-quality feature representations ensures high intra-class separability and poses one of the most challenging research directions. While convetional deep neural networks (DNNs) rely on complex transformations and very deep networks to come up with meaningful feature representations, they usually require days of training and consume significant energy amounts. To this end, spiking neural networks (SNNs) offer a promising alternative. SNN’s ability to capture temporal and spatial dependencies renders them particularly suitable for complex tasks, where multi-modal data are required. In this paper, we propose a feature discrimination approach for multi-modal learning with SNNs, focusing on audio-visual data. We employ deep spiking residual learning for visual modality processing and a simpler yet efficient spiking network for auditory modality processing. Lastly, we deploy a spiking multilayer perceptron for modality fusion. We present our findings and evaluate our approach against similar works in the field in classification challenges. To the best of our knowledge, this is the first work investigating feature discrimination in SNNs. © 2025, CC BY-NC-SA.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Augmenting Attention and Focus Using Brainwave Monitoring and Haptic Feedback

Augmenting Attention and Focus Using Brainwave Monitoring an...

引用

International Carpathian Control Conference (ICCC)

作者： Andrei-Costin Trasculescu Ionut-Cristian Resceanu Horatiu Roibu Florina-Luminita Petcu Stefan-Irinel Cismaru Constantin Patrascu Nicu George Bizdoaca Mechatronics and Robotics Department Faculty of Automation Computers and Electronics University of Craiova Craiova Romania

ISBN: (数字)9798350350708

ISBN: (纸本)9798350350715

The emerging technologies are focusing on monitoring and augmenting people in doing various tasks. One of the newest haptic technologies uses ultrasonic soundwaves to create the feeling of touching an object or sensations linked to a specific action. This paper aims to analyze and demonstrate that brainwave monitoring and haptic feedback via ultrasonic technology can increase an individual's focus and attention levels using the system. The applications in which this technology can prove its value are various, from learning and training to the operation of very sensitive and high-precision equipment that requires a lot of attention and focus. From the point of view of the fields in which this technology can be applied, they can also be varied, from the didactic field, machine operation and even medicine. A non-invasive technology, it can be easily implemented and applied to various environments. The equipment can also be calibrated and used according to the specific needs of each activity so that the feedback provided by the system is not too aggressive in applications where the level of attention does not need to be very high. Still, it can be calibrated to be very sensitive in cases where even a small loss of attention or focus can affect that specific activity. In the following paper, the authors combined ultrasonic feedback technology with brainwave monitoring technology to create an application to demonstrate all the benefits of this kind of augmentation of attention and focus, which is very effective in various domains, including education and training.

关键词： Training Power demand Ultrasonic transducer arrays Mixed reality Focusing Virtual reality Haptic interfaces

来源：评论

学校读者我要写书评

暂无评论

Domain-Invariant Similarity Activation Map Contrastive Learning for Retrieval-Based Long-Term Visual Localization

引用

IEEE/CAA Journal of Automatica Sinica 2022年第2期9卷 313-328页

作者： Hanjiang Hu Hesheng Wang Zhe Liu Weidong Chen Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China IEEE Department of Automation Institute of Medical RoboticsKey Laboratory of System Control and Information Processing of Ministry of EducationKey Laboratory of Marine Intelligent Equipment and System of Ministry of EducationShanghai Jiao Tong UniversityShanghai 200240China Department of Computer Science and Technology University of CambridgeCambridge CB30FDUnited Kingdom

Visual localization is a crucial component in the application of mobile robot and autonomous *** retrieval is an efficient and effective technique in image-based localization *** to the drastic variability of environmental conditions,e.g.,illumination changes,retrievalbased visual localization is severely affected and becomes a challenging *** this work,a general architecture is first formulated probabilistically to extract domain-invariant features through multi-domain image ***,a novel gradientweighted similarity activation mapping loss(Grad-SAM)is incorporated for finer localization with high *** also propose a new adaptive triplet loss to boost the contrastive learning of the embedding in a self-supervised *** final coarse-to-fine image retrieval pipeline is implemented as the sequential combination of models with and without Grad-SAM *** experiments have been conducted to validate the effectiveness of the proposed approach on the CMU-Seasons *** strong generalization ability of our approach is verified with the RobotCar dataset using models pre-trained on urban parts of the CMU-Seasons *** performance is on par with or even outperforms the state-of-the-art image-based localization baselines in medium or high precision,especially under challenging environments with illumination variance,vegetation,and night-time ***,real-site experiments have been conducted to validate the efficiency and effectiveness of the coarse-to-fine strategy for localization.

关键词： Deep representation learning place recognition visual localization

来源：评论

学校读者我要写书评

暂无评论

Synthesys of Adaptive Control System for Thrusters of Underwater Robots Using Technical Diagnostics

Synthesys of Adaptive Control System for Thrusters of Underw...

引用

2023 International Conference on Ocean Studies, ICOS 2023

作者： Zuev, Alexander Filaretov, Vladimir Zhirabok, Alexey Protsenko, Alexander Institute of Marine Technology Problems Vladivostok Russia Institute of Automation and Control Processes Vladivostok Russia Far Eastern Federal University Department of Automatics and Robotics Vladivostok Russia

ISBN: (纸本)9798350382457

The paper describes the development of adaptive control system for thrusters of underwater robots that allows you to compensate for the consequences of single and paired faults. This system., due to the additional control signals formed., make it possible to maintain operability and ensure stabilization of the most important characteristics of thrusters in the event of unexpected faults. Control signals are formed taking into account estimates of the values of deviations of the parameters of the thrusters from their nominal values and errors in the readings of sensors of angular velocity of thrusters. The operability and high efficiency of the developed system was confirmed by simulation. © 2023 IEEE.

关键词： Adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

Step-by-step Linearized Kalman Filter-Based Fault Detection of Workpiece Machining

Step-by-step Linearized Kalman Filter-Based Fault Detection ...

引用

2023 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS 2023

作者： Sun, Xiaohui Wu, Xinyu Wen, Chenglin Ma, Xue Tsinghua University Department of Automation Beijing China Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Shenzhen China Guangdong University of Petrochemical Technology School of Automation Maoming China

ISBN: (纸本)9798350337754

This paper is concerned with step-by-step linearized Kalman filter to deal with multiplicative faults diagnosis problem for class of nonlinear systems. Multiplicative fault variables are defined as parameter variables to be estimated, and linear dynamic models between fault variables and all variables are established. The indirect linear state and measurement models of fault variables and the corresponding step-by-step linearized Kalman filters are established based on current estimated values of all variable and some obtained estimated values of future variables;further, combined with fault variables, a filter is designed for state variables in the linearized system. On basis of EKF, the redisual generation is obtained. The effectiveness of the novel filter is verified in workpiece machining process. © 2023 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

A Manta Ray-Inspired Biosyncretic Robot with Stable Controllability by Dynamic Electric Stimulation

引用

Cyborg and Bionic Systems 2022年第1期2022卷 314-326页

作者： Chuang Zhang Yiwei Zhang Wenxue Wang Ning Xi Lianqing Liu State Key Laboratory of Robotics Shenyang Inst itute of AutomationChinese Academy of SciencesShenyang 110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China School of Automation and Electrical Engineering Shenyang Ligong University Shenyang 110159China Emerging Technologies Institute Department of Industrial Manufacturing Systems Engineering University of Hong KongPokfulamChina

Biosyncretic robots,which are new nature-based robots in addition to bionic robots,that utilize biological materials to realize their core function,have been supposed to further promote the progress in *** as the main operation mechanism relates to the robotic overall ***,biosyncretic robots actuated by living biological actuators have attracted increasing ***,innovative propelling modes and control methods are still necessary for the further development of controllable motion performance of biosyncretic *** this work,a muscle tissue-based biosyncretic swimmer with a manta *** propelling mode has been *** is more,to improve the stable controllability of the biosyncretic swimmer,a dynamic control method based on circularly distributed multiple electrodes(CDME)has been *** this method,the direction of the electric field generated by the CDME could be real-time controlled to be parallel with the adtuation tissue of the dynamic ***,the instability of the tissue actuation induced by the dynamic included angle between the tissue axis and electric field direction could be ***,the biosyncretic robot has demonstrated stable,controllable,and efective swimming,by adjusting the electric stimulation pulse direction,amplitude,and *** work may be beneficial for not only the development of biosyncretic robots but also other related studies including bionic design of soft robots and muscle tissue engineering.

关键词： Robot robot Dynamic

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：