检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and Biomimetics

作者： Zhen Li Wen-Qian Yue Gui-Bin Bian Shuai Zhang Wei-Peng Liu Shuo Li School of Electronic and Information Engineering Tongji University Shanghai China Institute of Automation Chinese Academy of Sciences Beijing China School of Health Sciences and Biomedical Engineering Hebei University of Technology Tianjin China School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin China Departments Biomedical Engineering and Computer and Data Science Case Western Reserve University

In microscopic cataract surgery, capsulorhexis is the first, most critical step. However, recognizing the boundary of the rhexis during capsulorhexis is challenging and has rarely been studied due to its intraoperative invisibility, variable shape, and lack of a proprietary labeled dataset, especially in the robot-sssisted surgery. To solve the problems, this paper proposes a creative dynamic boundary recognition solution, which includes a novel segmentation network, DCTNet, and a compensation block. First, the dilated HRNet is designed to constrain the over-compression while maintaining high-resolution representation for better detail preservation. Second, the cascaded transformer block is proposed: The decoupling transformer (DET) is developed to assign dynamic-static weights thus learning the variation pattern for segmented targets decoupling. The coupling transformer(COT) with redistributed embeddings is then developed to fuse diverse-resolution tokens for multi-scale prediction coupling. Moreover, the compensation block compensates for inter-frame movement by key-point registration and recovers a more realistic boundary by a smoothing process. Creatively, we mathematically estimate the uncertainty of framework to eliminate the misidentifications due to aleatoric uncertainty in data. Finally, to evaluate the proposed framework, we establish the first known capsulorhexis dataset, CapSeg. Our proposed DCTNet achieves superior performance to state-of-the-art networks with a lower computational cost, and the feasibility experiment shows its great potential in medical surgical robot.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Big Data for Enhancing Cybersecurity in Enterprise Environments Proactive Threat Detection and Prevention

Big Data for Enhancing Cybersecurity in Enterprise Environme...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Upender Reddy Chityala Ammar H. Shnain Manoj Govindaraj Prashant Johri T. Kuppuraj N.Lavanya Devi Equinox IT Solutions LLC (Senior ServiceNow Developer - IHG) Department Of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Management Studies Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India School of Computing Science and Engineering Galgotias University Greater Noida India Department of Computer Applications Karpagam Academy of Higher Education Coimbatore India Department of ECE PSNA College of Engineering and Technology India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

This research explores the integration of big data technologies and machine learning to enhance cybersecurity in enterprise environments focusing on proactive threat detection and prevention. Traditional security systems often struggle to keep up with the growing complexity and volume of cyber threats, necessitating a more advanced, data-driven approach. The proposed methodology leverages real-time data processing, predictive modeling, and anomaly detection to improve threat detection accuracy, reduce response times, and enhance system scalability. By collecting and analyzing data from various network sources, including logs from security devices and endpoint protection software, the system detects potential threats more efficiently than conventional methods. Machine learning algorithms such as supervised and unsupervised learning, along with big data platforms like Apache Spark, enable real-time analysis of large volumes of data, ensuring timely identification of both known and unknown cyber threats. The results demonstrate significant improvements in detection accuracy, system scalability, and incident resolution time, with the proposed methodology outperforming traditional security systems in key performance metrics. This research highlights the potential of big data-driven cybersecurity solutions in addressing modern challenges and offers a framework for organizations to implement more effective, scalable, and proactive security measures to safeguard their digital assets.

关键词： Scalability Prevention and mitigation Machine learning Organizations Big Data Predictive models Data processing Threat assessment Real-time systems computer security

来源：评论

学校读者我要写书评

暂无评论

An Automated Calibration Scheme for PLL in Time-to-Digital Converters

An Automated Calibration Scheme for PLL in Time-to-Digital C...

引用

IEEE International Conference on Circuits and Systems (ICCS)

作者： Jiayuan Xu Hang Yu Yan Li Daoming Xi Binjie Ge Hongzhao Liu Shenzhen Laboratory of IC Design for IOT College of Computer Science and Software Engineering Shenzhen University Shenzhen China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Dept. of Electronics and Computer Engineering SHENZHEN MSU-BIT University Shenzhen China Quality and Standards Academy Shenzhen Technology University Shenzhen China

In high performance Time-to-Digital Converters (TDCs), PLL can be adopted to generate the required reference clock, which is in $\sim 100 \ \text{MHz}$ range. In order to improve the phase noise performance, the full VCO frequency range in such a PLL is generally divided into multiple sectors, which can be selected by digital code. This paper proposes an automated calibration scheme to set the digital code for optimized VCO performance. Primarily based on successive approximation algorithm, the proposed scheme completes the automated calibration with only minimal steps. By co-simulating with a typical PLL, the efficacy of the proposed scheme is fully validated. Tentatively synthesized using CMOS 180nm technology, the automated calibration scheme only occupies $100\times 100\text{um}^{2}$ of silicon area, and consists of 144 logical gates. The power consumption is only $\sim 100\ \text{uW}$ .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Innovations in CPR: A Comprehensive Survey on Enhanced Resuscitation Techniques

arXiv

引用

arXiv 2024年

作者： Islam, Saidul Rjoub, Gaith Elmekki, Hanae Bentahar, Jamal Pedrycz, Witold Cohen, Robin Concordia Institute for Information Systems Engineering Concordia University Montreal Canada Faculty of Information Technology Aqaba University of Technology Aqaba Jordan Department of Computer Science Khalifa University Abu Dhabi United Arab Emirates Department of Electrical and Computer Engineering University of Alberta Edmonton Canada Systems Research Institute Polish Academy of Sciences Warsaw Poland Research Center of Performance and Productivity Analysis Istinye University Sariyer Istanbul Turkey David R. Cheriton School of Computer Science University of Waterloo Waterloo Canada

This survey paper explores the transformative role of Machine Learning (ML) and Artificial Intelligence (AI) in Cardiopulmonary Resuscitation (CPR). It examines the evolution from traditional CPR methods to innovative ML-driven approaches, highlighting the impact of predictive modeling, AI-enhanced devices, and real-time data analysis in improving resuscitation outcomes. The paper provides a comprehensive overview, classification and critical analysis of current applications, challenges, and future directions in this emerging field. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Detection of Physical Anomalies in IoT Networks Using Machine Learning Techniques

Detection of Physical Anomalies in IoT Networks Using Machin...

引用

Advancement in Renewable Energy and Intelligent Systems (AREIS), International Conference on

作者： M. A. Mukunthan Jose Anand A. Stalin Kesavan Malini Mutyala R. Kesavan R. Geetha Department of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of ECE KCG College of Technology Chennai Tamil Nadu India Department of Marine Engineering Academy of Maritime Education and Training Chennai Tamil Nadu Department of CSBS Vignana Bharathi Institute of Technology Hyderabad Telangana India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai Tamilnadu Department of Computing Technologies SRM Institute of Science and Technology Chennai Tamilnadu

ISBN: (数字)9798350387230

ISBN: (纸本)9798350387247

This work focuses on the implementation of a Machine Learning (ML) algorithm for detecting physical anomalies in Internet of Things (IoT) networks. A Wireless Sensor Network (WSN) was deployed, collecting data under two scenarios: normal operation and an altered state exhibiting physical anomalies. The WSN, composed of humidity, Hall effect, barometer, and temperature sensors, communicated using the MQTT protocol with an Edge node for data capture. Data profiling and preprocessing were conducted to clean and optimize the dataset for ML. The K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest (RF) algorithm were employed to classify network traffic, with hyperparameters tuned using Randomized Search CV. The dataset was split into training (75%) and testing (25%) sets, with performance metrics such as accuracy, precision, recall, F1 score, and ROC curve analyzed. The final model achieved high accuracy (99.53 %) and showed excellent precision (1) with a classification time of 0.0012 seconds per packet. These results demonstrate the RF model's effectiveness in detecting physical anomalies in IoT networks, although further optimization may be needed for real-world scalability.

关键词： Support vector machines Radio frequency Performance evaluation Wireless sensor networks Accuracy Computational modeling Scalability Nearest neighbor methods Reliability Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Unknown Word Detection for English as a Second Language (ESL) Learners Using Gaze and Pre-trained Language Models

arXiv

引用

arXiv 2025年

作者： Ding, Jiexin Zhao, Bowen Wang, Yuntao Liu, Xinyun Hao, Rui Chatterjee, Ishan Shi, Yuanchun Institute Tsinghua University Beijing China Electrical & Computer Engineering University of Washington SeattleWA United States Groundlight AI SeattleWA United States Department of Computer Science and Technology Tsinghua University Beijing China Rice University HoustonTX United States School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Paul G. Allen School of Computer Science and Engineering University of Washington SeattleWA United States Qinghai University Xining China

English as a Second Language (ESL) learners often encounter unknown words that hinder their text comprehension. Automatically detecting these words as users read can enable computing systems to provide just-in-time definitions, synonyms, or contextual explanations, thereby helping users learn vocabulary in a natural and seamless manner. This paper presents EyeLingo, a transformer-based machine learning method that predicts the probability of unknown words based on text content and eye gaze trajectory in real time with high accuracy. A 20-participant user study revealed that our method can achieve an accuracy of 97.6%, and an F1-score of 71.1%. We implemented a real-time reading assistance prototype to show the effectiveness of EyeLingo. The user study shows improvement in willingness to use and usefulness compared to baseline methods. © 2025, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

RETRACTED ARTICLE: A multi-scale and rotation-invariant phase pattern (MRIPP) and a stack of restricted Boltzmann machine (RBM) with preprocessing for facial expression classification (Journal of Ambient Intelligence and Humanized Computing, (2021), 12, 3, (3447-3463), 10.1007/s12652-020-02517-7)

引用

Journal of Ambient Intelligence and Humanized Computing 2024年

作者： Sherly Alphonse, A. Shankar, K. Jeyasheela Rakkini, M.J. Ananthakrishnan, S. Athisayamani, Suganya Singh, A. Robert Gobi, R. Department of Information Technology Ponjesly College of Engineering Nagercoil India Department of Computer Applications Alagappa University Karaikudi India School of Computing Sastra Deemed To Be University Thanjavur India School of Computing Kalasalingam Academy of Research and Education Anand Nagar India Department of Computer Science Christ University Bengalore India

The Publisher has retracted this article in agreement with the Editor-in-Chief. The article was submitted to be part of a guest-edited issue. An investigation by the publisher found a number of articles, including this one, with a number of concerns, including but not limited to compromised editorial handling and peer review process, inappropriate or irrelevant references or not being in scope of the journal or guest-edited issue. Based on the investigation’s findings the publisher, in consultation with the Editor-in-Chief therefore no longer has confidence in the results and conclusions of this article. S. Ananthakrishnan, A. Robert Singh, and R. Gobi disagree with this retraction. M. J. Jeyasheela Rakkini did not explicitly state whether they agree or disagree with this retraction. The remaining authors did not respond to correspondence from the Publisher regarding this retraction. © Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ANAS: Sentence Similarity Calculation Based on Automatic Neural Architecture Search 4th

ANAS: Sentence Similarity Calculation Based on Automatic Neu...

引用

4th IFIP TC 12 International Conference on Intelligence science, ICIS 2020

作者： Wang, Dong-Sheng Zhao, Cui-Ping Wang, Qi Ofori, Kwame Dwomoh Han, Bin Liu, Ga-Qiong Wang, Shi Wang, Hua-Yu Zhang, Jing School of Computer Science Jiangsu University of Science of Technology Zhenjiang Jiangsu212001 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China School of Army Engineering University Nanjing Jiangsu210007 China

ISBN: (纸本)9783030748258

Sentence similarity calculation is one of several research topics in natural language processing. It has been widely used in information retrieval, intelligent question answering and other fields. Traditional machine learning methods generally extract sentence features through manually defined feature templates and then perform similarity calculations. This type of method usually requires more human intervention and constantly has to deal with domain migration problems. Automatically extracting sentence features using certain deep learning algorithms helps to solve domain migration problems. The training data is of the domain is required to complete the extraction process. However, the neural network structure design in the deep learning model usually requires experienced experts to carry out multiple rounds of the tuning design phase. Using an automatic neural architecture search (ANAS) technology deals with all the network structure design problems. This paper proposes a sentence similarity calculation method based on neural architecture search. This method uses a combination of grid search and random search. The method in this paper is tested on the Quora "Question-Pairs" data set and has an accuracy of 81.8%. The experimental results show that the method proposed in this paper can efficiently and automatically learn the network structure of the deep learning model to achieve high accuracy. © 2021, IFIP International Federation for Information Processing.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A Light-Weight ANN Model for Landslide Detection: A Case Study of Idukki, India

A Light-Weight ANN Model for Landslide Detection: A Case Stu...

引用

IEEE International Conference on Aerospace Electronics and Remote Sensing technology (ICARES)

作者： Shweta Vincent Babitha Ganesh Sameena Pathan Vishwajeet Kulkarni Parth Sirohi Tushar Agarwal Silvia Raquel Garcia Benitez Department of Mechatronics Manipal Academy of Higher Education Manipal Institute of Technology Manipal Karnataka INDIA Department of Mechatronics Department of Computer Science and Engineering Canara Engineering College Manipal Institute of Technology Mangalore Karnataka INDIA Department of Information and Communication Technology Manipal Academy of Higher Education Manipal Institute of Technology Manipal Karnataka INDIA Department of Electronics and Communication Engineering Manipal Academy of Higher Education Manipal Institute of Technology Manipal Karnataka INDIA Electrical and Computing Coordination Instituto De Ingenieria UNAM Mexico City MEXICO

This article presents a light-weight ANN model for the creation of a landslide susceptibility map (LSM) for the district of Idukki in the South Indian state of Kerala. The landslide conditioning factors (LCF) considered for the creation, training, validation and testing of the LSM are elevation, slope, aspect, curvature, topographic wetness index (TWI), stream power index (SPI), rainfall, topographic ruggedness index (TRI), geology, soil type and land use and land cover. The Frequency Ratio (FR) analysis has been carried out on the LCFs and those having the highest Predictive Rate (PR) have been determined as aspect, slope, rainfall and soil type. Once the LSM is created, it is tested using landslide and non-landslide points using the proposed ANN model which yields an accuracy of 83.5%. Future scope in this work is to improve the accuracy of the model by using metaheuristic algorithms for optimization of weights of the ANN model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Where Precision Meets Efficiency: Transformation Diffusion Model for Point Cloud Registration 39

Where Precision Meets Efficiency: Transformation Diffusion M...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yuan, Yongzhe Wu, Yue Fan, Xiaolong Gong, Maoguo Miao, Qiguang Ma, Wenping MoE Key Lab of Collaborative Intelligence Systems Xidian University China School of Computer Science and Technology Xidian University China School of Electronic Engineering Xidian University China Academy of Artificial Intelligence College of Mathematics Science Inner Mongolia Normal University China School of Artificial Intelligence Xidian University China

ISBN: (纸本)157735897X

We propose a transformation diffusion model for point cloud registration to balance precision and efficiency. Our method formulates point cloud registration as a denoising diffusion process from noisy transformation to object transformation, which is represented by quaternion and translation. Specifically, in training stage, object transformation diffuses from ground-truth transformation to random distribution, and the model learns to reverse this noising process. In sampling stage, the model refines randomly generated transformation to the optimal transformation in a progressive way. We derive the variational bound in closed form for training and provide instantiation of the model. Our diffusion model maps transformation into latent space, and splits the transformation into two components (rotation and translation) based on the fact that they belong to different solution spaces. In addition, our work provides the following crucial findings: (i) Point cloud registration, one of the representative discriminative tasks, can be solved by a generative way and mapped into latent space to obtain new unified probabilistic formulation. (ii) Our model, Transformation Diffusion Model (TDM) can be a plug-and-play agent for point cloud registration, making our method applicable to different deep registration networks. Experimental results on synthetic and real-world datasets demonstrate that, in correspondence-free and correspondence-based scenarios, TDM can both achieve exceeding 60% performance improvements and higher efficiency simultaneously. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

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：