检索结果-内蒙古大学图书馆

Defocus Blur Segmentation Using Genetic Programming and Adaptive Threshold

computers, Materials & Continua 2022年第3期70卷 4867-4882页

作者： Muhammad Tariq Mahmood Future Convergence Engineering School of Computer Science and EngineeringKorea University of Technology and EducationCheonan31253Byeongcheon-myeonKorea

Detection and classification of the blurred and the non-blurred regions in images is a challenging task due to the limited available information about blur type,scenarios and level of *** this paper,we propose an effective method for blur detection and segmentation based on transfer learning *** proposed method consists of two separate *** the first step,genetic programming(GP)model is developed that quantify the amount of blur for each pixel in the *** GP model method uses the multiresolution features of the image and it provides an improved blur *** the second phase,the blur map is segmented into blurred and non-blurred regions by using an adaptive threshold.A model based on support vector machine(SVM)is developed to compute adaptive threshold for the input blur *** performance of the proposed method is evaluated using two different datasets and compared with various state-of-the-art *** comparative analysis reveals that the proposed method performs better against the state-of-the-art techniques.

关键词： Blur measure blur segmentation sharpness measure genetic programming support vector machine

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Based Collaborative Perception for Vehicular Networks

Reinforcement Learning Based Collaborative Perception for Ve...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Chen, Hongyi Lin, Zhiping Zhu, Yunjun Li, Jieling Xiao, Liang Tang, Yuliang Zhang, Yanyong Institute of Artificial Intelligence Xiamen University China Xiamen University Dept. Information and Communication Engineering China University of Science and Technology of China School of Computer Science and Technology China

ISBN: (纸本)9798350351255

Reinforcement learning (RL)-based collaborative perception in vehicular networks chooses the sub-frame of radio channel resources for connected autonomous vehicles (CAVs) to exchange sensing data to enhance the perception performance, but leads to inaccurate detection in the light detection and ranging (LiDAR)-based object detection due to the asynchronous scan period of the LiDAR point clouds. This paper proposes a RL-based collaborative perception scheme to choose the transmit power and sub-frame to share the feature maps extracted from point clouds. Based on the estimated packet timestamp, the network topology and the channel gains among CAVs, this scheme enhances the perception accuracy and latency against path-loss and interference. The collaborative risk in the policy distribution is formulated as a weighted sum of the perception latency and packet loss rate to avoid the time asynchronization and information loss of the feature map exchange. The performance bound of the perception accuracy and latency is provided based on a Nash equilibrium of the cooperative game among CAVs. Simulation results based on five CAVs show the performance gain of the perception accuracy and latency over the benchmarks. © 2024 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Experimentation Using GEI and AFDEI for Person Recognition with PCA, LDA, and Ensemble Machine Learning Techniques 4

Experimentation Using GEI and AFDEI for Person Recognition w...

引用

4th IEEE Asian Conference on Innovation in technology, ASIANCON 2024

作者： Sonare, Babita Saxena, Deepika Katkar, Vijay Poornima University Department of Computer Science and Engineering Rajasthan Jaipur India School of Engineering and Technology Pimpri Chinchwad University Pune India

ISBN: (纸本)9798350354218

This paper investigates person recognition using GAIT patterns, focusing on Gait Energy Image (GEI) and Accumulative Frame Difference Energy Image (AFDEI). Feature extraction was performed using Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and a fusion of PCA-LDA. Various classifiers, including Logistic Regression, NB, SVM, MLP, Random Forest, and KNN, were assessed. Results showed that KNN with Principal Component Analysis -fusion features achieved 73.5% accuracy, while Random Forest with LDA-GAIT Energy Image features achieved 77.4%. SVM and Naive Bayesian with Principal Component Analysis-Linear Discriminant Analysis fusion features achieved 76.0%. Ensemble techniques, including Adaboost, Gradient Boosting, and Extreme Gradient Boosting, were also tested. The highest accuracies were 67.9% for SVM-Adaboost with Principal Component Analysis-GAIT Energy Image features, 70.4% for Random Forest-Adaboost with Linear Discriminant Analysis-GAIT Energy Image features, and 75.9% for Logistic Regression-Adaboost with PCA-LDA Analysis fusion features. This study underscores the significance of feature extraction techniques and the selection of appropriate machine learning classifiers in enhancing the accuracy of person recognition systems based on GAIT patterns, providing valuable insights for future research and practical implementations. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Research on Facial Landmark Detection Algorithm Based on Improved Attention Mechanism

Research on Facial Landmark Detection Algorithm Based on Imp...

引用

2022 International Conference on Artificial Intelligence, Virtual Reality, and Visualization, AIVRV 2022

作者： Cui, Xi-Shuo Shi, Tian-Wei Cui, Wen-Hua Tao, Ye School of Electronic and Information Engineering University of Science and Technology Liaoning Liaoning Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Liaoning Anshan114051 China

ISBN: (纸本)9781510662988

In recent years, facial landmark detection has assumed an important role in various fields. However, the current facial landmark detection algorithms are still lacking in recognition accuracy. In order to solve the above problem, this paper uses Ghost bottleneck to replace the original bottleneck on the basis of the original model of PFLD model, and adds and improves the CBAM attention mechanism. The improved PFLD model increases the ability of the model to extract facial landmark and improves the accuracy of the algorithm. The improved model has high accuracy and low parametric number and improves the accuracy of facial landmark detection. It also provides a new idea for facial landmark detection task. © 2023 SPIE. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Reshaping the imprinting strategy through the thermo-responsive moiety-derived“deep eutectic solvents”effect

引用

Chinese Chemical Letters 2024年第1期35卷 441-445页

作者： Huihuang Xiong Yiqun Wan Yong Fan Mengjia Xu Aiping Yan Yushan Zhang Qifei Jiang Hao Wan State Key Laboratory of Food Science and Technology Nanchang UniversityNanchang 330047China School of Chemistry and Chemical Engineering Nanchang UniversityNanchang 330031China Jiangxi Province Key Laboratory of Modern Analytical Science Nanchang UniversityNanchang 330031China Department of Computer Science University of California IrvineIrvine 92697United States

As a new concept having emerged in last few years,the“deep eutectic solvents”(DESs)effect integrated into the imprinting technology inevitably exposes design limitations of stimuli-responsive molecularly imprinted polymers(MIPs),as well as inadequate analysis of the adsorption performance of ***,a simple yet defined N-isopropylacrylamide/(3-acrylamidopropyl)trimethylammonium chloride(NIPAM/APTMAC)binary DESs system was proposed to prepare intelligent MIPs with ***,magnetic and thermo-responsive MIPs based on functional monomers-derived DESs(TMDESs-MIPs1)were synthesized,revealing DESs effect-regulated affinity/kinetics for the enhanced adsorption capability,eco-friendly thermo-regulated elution for high release efficiency,and simple magnetic separation,along with superior selectivity to rhein(RH)and good regeneration ***-DESs-MIPs1 were utilized to extract RH from Cassiae semen samples coupled with high performance liquid chromatography(HPLC),yielding satisfactory recoveries(79.47%−110.82%)and low limits of detection(LOD)(16.67μg/L).Another two kinds of MIPs adopting the thermo-responsive moiety-derived DESs effect strategy further demonstrated great applicability of such intelligent MIPs for analyses of complicated samples.

关键词： Deep eutectic solvents Molecularly imprinted polymers Magnetic Thermo-responsive Thermo-regulated elution

来源：评论

学校读者我要写书评

暂无评论

Exploring Academic Integrity in the Age of Generative AI 21

Exploring Academic Integrity in the Age of Generative AI

引用

21st International Conference on Information technology Based Higher Education and Training, ITHET 2024

作者： Ward, Anthony Manoharan, Sathiamoorthy Ye, Xinfeng School of Physics and Engineering Technology University of York York United Kingdom School of Computer Science University of Auckland Auckland New Zealand

ISBN: (纸本)9798331516635

Traditionally, statistics suggest that around 30% of students resort to cheating when presented with the opportunity. This alarming trend often goes unnoticed by instructors, as many do not actively monitor for such misconduct. However, the onset of the pandemic saw a surge in cheating incidents, mainly due to the shift to online learning environments where supervision was more challenging. Despite this, instances of cheating remained detectable, albeit with some effort. As we transition out of the pandemic era, a new challenge has emerged in the form of generative AI technology, which has dramatically altered the landscape of academic dishonesty. With the advent of sophisticated generative AI models, it has become virtually impossible to discern between authentic student work and AI-generated content in unsupervised settings. Consequently, there has been a noticeable decline in detected cheating cases compared to pre-pandemic levels, largely attributed to the widespread use of generative AI tools. Traditional plagiarism detection software such as Turnitin and MOSS, once considered reliable safeguards against academic dishonesty, have become obsolete in the face of these advanced AI systems. The unique solutions produced by generative AI render such detection methods ineffective, posing a significant challenge to maintaining academic integrity in the modern educational landscape. This paper explores the nature of academic misconduct incidents in the context of two universities across the globe: one in the United Kingdom and the other in New Zealand. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Rethinking attribute localization for zero-shot learning

引用

science China(Information sciences) 2024年第7期67卷 184-196页

作者： Shuhuang CHEN Shiming CHEN Guo-Sen XIE Xiangbo SHU Xinge YOU Xuelong LI School of Electronic Information and Communication Huazhong University of Science and Technology School of Computer Science and Engineering Nanjing University of Science and Technology School of Artificial Intelligence Optics and Electronics Northwestern Polytechnical University

Recent advancements in attribute localization have showcased its potential in discovering the intrinsic semantic knowledge for visual feature representations, thereby facilitating significant visual-semantic interactions essential for zero-shot learning(ZSL). However, the majority of existing attribute localization methods heavily rely on classification constraints, resulting in accurate localization of only a few attributes while neglecting the rest important attributes associated with other classes. This limitation hinders the discovery of the intrinsic semantic relationships between attributes and visual features across all *** address this problem, we propose a novel attribute localization refinement(ALR) module designed to enhance the model's ability to accurately localize all attributes. Essentially, we enhance weak discriminant attributes by grouping them and introduce weighted attribute regression to standardize the mapping values of semantic attributes. This module can be flexibly combined with existing attribute localization *** experiments show that when combined with the ALR module, the localization errors in existing methods are corrected, and state-of-the-art classification performance is achieved.

关键词： zero-shot learning attention mechanism attribute localization image classification

来源：评论

学校读者我要写书评

暂无评论

Robot Manipulation Strategy for Explosives Disposal in Cluttered Scenes 8th

Robot Manipulation Strategy for Explosives Disposal in Clutt...

引用

8th International Conference on Cognitive Systems and Information Processing, ICCSIP 2023

作者： Guo, Run Yuan, Yi Sun, Funchun Wen, Shuhuan Chen, Yang Li, Linxiang School of Electrical Engineering Yanshan University Qinhuangdao China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9789819980208

Compared to human operator, robotic arm possesses the advantages of high accuracy and controllability in handling and manipulating hazardous materials. Due to the complexity and variability of application scenarios, such as the objects are stacked, it is a great challenge to accurately select target objects and manipulation mode in the fields of security and demolition. To address these problems, robotic arm systems require capabilities in target object detection, object relationship reasoning, and manipulation strategy selection. In this paper, we propose a framework with the abilities of reasoning about the unknown relationships between target objects and interfering objects, predicting manipulation sequences, and adopting appropriate manipulation strategies for hazardous object detection and manipulation processing. We conduct a series of experiments in indoor single-target, multi-target, and outdoor scenarios to complete the assigned tasks with improved manipulation sequences. These results serve as evidence of the effectiveness of the proposed framework. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Enhancing Capabilities of Recommendation System for Electric Vehicles Using Reinforcement Learning 1

Enhancing Capabilities of Recommendation System for Electric...

引用

1st International Conference on Computing, sciences and Communications, ICCSC 2024

作者： Rawat, Daksh Singh, Akshay Kumar Singh, Simar Preet Bennett University Greater Noida India School of Computer Science Engineering and Technology Bennett University Greater Noida India

ISBN: (纸本)9798350353648

In the future, electric vehicles, including automobiles, motorcycles, and public transport, are expected to play a significant role in daily commutes. However, India's current infrastructure lacks a wellestablished and integrated network of charging stations to support this growth. This application aims to bridge that gap by providing electric vehicle users with detailed information about charging stations, including availability, status, number of chargers, and compatibility with their vehicles. Users can also book chargers in advance for a hassle-free experience. A key feature of the application is the ability to plan longdistance trips by mapping out routes with real-time information on charger locations and availability, ensuring access to functional chargers throughout their journey. This application includes a review section where users can share feedback, helping others make informed decisions about where to charge. For businesses, the application offers specialized subscription services to companies like Uber that operate electric vehicle-based taxis, allowing them to book entire charging stations and access administrative features. Additionally, small businesses and private charger owners can register their chargers for public use, contributing to the charging network while ensuring transparency and reliability for users through real-time data sharing. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Accurate scoliosis vertebral landmark localization on X-ray images via shape-constrained multi-stage cascaded CNNs

引用

Fundamental Research 2024年第6期4卷 1657-1665页

作者： Zhiwei Wang Jinxin Lv Yunqiao Yang Yi Lin Qiang Li Xin Li Xin Yang Britton Chance Center for Biomedical Photonics Wuhan National Laboratory for OptoelectronicsHuazhong University of Science and TechnologyWuhan 430074China MoE Key Laboratory for Biomedical Photonics Collaborative Innovation Center for Biomedical EngineeringHuazhong University of Science and TechnologyWuhan 430074China Department of Computer Science City University of Hong KongHong Kong 999077China Department of Computer Science and Engineering The Hong Kong University of Science and TechnologyHong Kong 999077China Department of Radiology Union HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430022China School of Electronic Information and Communications Huazhong University of Science and TechnologyWuhan 430074China

Vertebral landmark localization is a crucial step in various spine-related clinical applications,which requires detecting the corner points of 17 ***,the neighboring landmarks often disturb each other because of the homogeneous appearance of vertebrae,making vertebral landmark localization extremely *** this paper,we propose a multi-stage cascaded convolutional neural network(CNN)to split a single task into two sequential steps:center point localization to roughly locate 17 center points of vertebrae,and corner point localization to determine four corner points for each vertebra without any *** landmarks in each step were located gradually from a set of initialized points by regressing offsets using cascaded *** resist the mutual attraction of the vertebrae,principal component analysis was employed to preserve the shape constraint in offset *** evaluated our method on the AASCE dataset,comprising 609 tight spinal anteroposterior X-ray images,and each image contained 17 vertebrae composed of the thoracic and lumbar spine for spinal shape *** experimental results demonstrated the superior performance of vertebral landmark localization over other state-of-the-art methods,with the relative error decreasing from 3.2e−3 to 7.2e−4.

关键词： Vertebra X-ray Landmark localization Multi-stage Cascade Shape constraint

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：