检索结果-内蒙古大学图书馆

ESE-GAN: Zero-Shot Food Image Classification Based on Low Dimensional Embedding of Visual Features

IEEE Transactions on Multimedia 2024年 27卷 1-11页

作者： Li, Gaojie Li, Yaochen Liu, Jingle Guo, Wei Tang, Wenneng Liu, Yuehu School of Software Engineering Xi'an Jiaotong University Xi'an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China

Existing zero-shot learning based image classification methods transform the zero-shot learning problem into supervised learning by applying generative adversarial network (GAN) to synthesize visual features of unseen classes. However, the visual features generated by the generator tend to be biased towards seen classes, and the discriminator is too weak to generate high-quality image features. To solve these problems, we propose a novel zero-shot food image classification method based on low dimensional embedding of visual features. Our method applies reinforced semantic guidance to increase the discriminative ability of the model by enhancing the strong distribution of input features. Moreover, the visual space is utilized as the embedding space to reduce the bias towards seen classes by reducing the distance between semantic information and visual features in the embedding space. Finally, the feature distribution of unseen classes is further specified by improving the prototype similarity function. Extensive experiments on three food datasets and four general benchmark datasets demonstrate the effectiveness of the proposed method. IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Detection of Alzheimer's Disease using Deep Learning: An Optimized Approach 6

Detection of Alzheimer's Disease using Deep Learning: An Opt...

引用

6th International Conference on Intelligent Autonomous Systems, ICoIAS 2023

作者： Ahmed, Gulnaz Joo Er, Meng Zikria, Shahid Sadiq Fareed, Muhammad Institute of Artificial Intelligence and Marine Robotics Dalian Maritime University Dalian China Software Engineering Institute of Guangzhou Department of Software Engineering Guangzhou China

ISBN: (纸本)9798350371253

This paper suggests a new CNN that requires just a few parameters to diagnose AD and is perfect for training on smaller datasets. Compared to existing state-of-the-art models, the proposed model uses a more optimized technique to identify the early stages of Alzheimer's disease. The image is sharpened and normalized as part of the preparation phase to help the model learn more quickly and succinctly. We used a bespoke CNN model that makes precise predictions with minimum parameters. Five Convolutional layers and three fully connected layers, which have equally learned samples from each class, make up the proposed model. The approach was compared using a variety of accuracy metrics, such as accuracy, AUC, precision, recall, and Fl-Score, as well as categorical cross-entropy loss, self, and other comparisons. To accurately forecast the method, several trials were carried out. The values for the evaluation measures are as follows: accuracy, AUC, precision, recall, fl-score, and loss are 99.95%, 99.99%, 99.97%, 99.95%, and 0.0016 respectively. According to simulation results, the proposed model performs better than existing cutting-edge models in all evaluation metrics. © 2023 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Support vector machine with discriminative low-rank embedding

引用

CAAI Transactions on Intelligence Technology 2024年第5期9卷 1249-1262页

作者： Guangfei Liang Zhihui Lai Heng Kong Computer Vision Institute College of Computer Science and Software EngineeringShenzhen UniversityShenzhenChina Shenzhen Institute of Artificial Intelligence and Robotics for Society ShenzhenChina Department of Breast and Thyroid Surgery BaoAn Central Hospital of ShenzhenShenzhenChina

Support vector machine(SVM)is a binary classifier widely used in machine ***,neglecting the latent data structure in previous SVM can limit the performance of SVM and its *** address this issue,the authors propose a novel SVM with discriminative low-rank embedding(LRSVM)that finds a discriminative latent low-rank subspace more suitable for SVM *** extension models of LRSVM are introduced by imposing different orthogonality constraints to prevent computational inaccuracies.A detailed derivation of the authors’iterative algorithms are given that is essentially for solving the SVM on the low-rank ***,some theorems and properties of the proposed models are presented by the *** is worth mentioning that the subproblems of the proposed algorithms are equivalent to the standard or the weighted linear discriminant analysis(LDA)*** indicates that the projection subspaces obtained by the authors’algorithms are more suitable for SVM classification compared to those from the LDA *** convergence analysis for the authors proposed algorithms are also ***,the authors conduct experiments on various machine learning data sets to evaluate the *** experiment results show that the authors’algorithms perform significantly better than other algorithms,which indicates their superior abilities on classification tasks.

关键词： iterative methods machine leaning support vector machunes

来源：评论

学校读者我要写书评

暂无评论

Reward-Based Energy-Aware Routing Protocols in Wireless Sensor Networks

Reward-Based Energy-Aware Routing Protocols in Wireless Sens...

引用

International Conference on Smart Applications and Sustainability in the Artificial Intelligence of Things, SAS-AIoT 2024

作者： Salama, Ramiz Alturjman, Sinem Altrjman, Chadi Al-Turjman, Fadi Department of Computer Engineering AI and Robotics Institute Research Center for AI and IoT Near East University Nicosia Cyprus Artificial Intelligence Software and Information Systems Engineering Departments AI and Robotics Institute Near East University Nicosia Cyprus

ISBN: (纸本)9783031782756

Smart cities, industrial automation, healthcare, and environmental monitoring are just a few of the industries that have seen revolutionary changes as a result of Wireless Sensor Networks’ (WSNs) explosive growth. WSNs are significantly hampered by the limited energy resources of their sensor nodes, which are usually battery-powered and placed in inaccessible locations, despite their wide-ranging applications. As a result, energy efficiency is now a crucial component of these networks’ operation and design. Though these protocols frequently fail to adjust to the dynamic and unpredictable nature of WSNs, traditional energy-aware routing methods have been created to decrease energy consumption by choosing the best paths for data transfer. By allowing sensor nodes to learn from their surroundings and make wise routing decisions, the machine learning field of reinforcement learning (RL) provides a viable answer to these problems. In contrast to conventional techniques, RL-based protocols provide continuous energy optimization by dynamically modifying their routing strategies in response to real-time feedback. This paper investigates how to include RL methods—specifically, Q-learning and SARSA—into WSN energy-aware routing protocols. The suggested method creates a more distributed and scalable solution by enabling each node to independently learn and modify its routing choices. The effectiveness of RL-based routing protocols is compared to traditional methods through comprehensive simulations. The findings show that by slowing down the rate at which energy is being used up by each node, RL not only increases energy efficiency but also lengthens the network's operational life. In particular, Q-learning demonstrates a notable improvement in sustaining data delivery rates and network connectivity under various circumstances. Although a little more computationally demanding, the SARSA algorithm offers greater flexibility in situations where network topology changes often. Th

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Using Gamification to Increase Healthcare Professionals’ Cybersecurity Awareness

Using Gamification to Increase Healthcare Professionals’ Cy...

引用

International Conference on Smart Applications and Sustainability in the Artificial Intelligence of Things, SAS-AIoT 2024

作者： Salama, Ramiz Alturjman, Sinem Altrjman, Chadi Al-Turjman, Fadi Department of Computer Engineering AI and Robotics Institute Research Center for AI and IoT Near East University Nicosia Cyprus Artificial Intelligence Software Information Systems Engineering Departments AI and Robotics Institute Near East University Nicosia Cyprus

ISBN: (纸本)9783031782756

Cybersecurity knowledge is essential in today’s increasingly digital healthcare environment to protect sensitive patient data and guarantee the integrity of healthcare systems. But conventional cybersecurity training approaches frequently fail to hold healthcare professionals’ attention, which results in inadequate application and retention of the material. In order to increase cybersecurity awareness among healthcare professionals, this study investigates the use of gamification—a technological technique that incorporates game design aspects into non-gaming contexts—as an innovative method. A mixed-methods research methodology is used in the study to assess the effectiveness of a cybersecurity training program that is gamified. To encourage user involvement and motivation, the program incorporates aspects like leaderboards, interactive scenarios, badges, and points. The study included a total of 100 healthcare professionals from various departments, offering a thorough understanding of the program’s effects across a range of positions and experience levels. Pre- and post-training surveys were used to gather quantitative data on participant changes in knowledge, attitudes, and behaviors pertaining to cybersecurity procedures. Furthermore, semi-structured interviews yielded qualitative insights that further elucidated the participants’ perspectives and experiences with the gamified training method. Comparing gamification to conventional training approaches, the results show that gamification dramatically improves engagement and knowledge retention. The willingness of the participants to acquire and use cybersecurity techniques in their daily lives has reportedly increased. Additionally, the gamified components strengthened the training objectives by fostering a competitive yet cooperative learning environment. The potential of gamification as a game-changing instrument for cybersecurity education in healthcare settings is highlighted by this study. Healthcare busines

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Temporally Consistent 3D Human Motion Estimation from a Video 7

Temporally Consistent 3D Human Motion Estimation from a Vide...

引用

7th International Conference on Computer Graphics and Virtuality, ICCGV 2024

作者： Zhang, Zhaobing Liu, Yuehu Wang, Shaorong Yan, Yuanfeng School of Software Engineering Xi’an Jiaotong University Xi’an China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (数字)9781510679788

ISBN: (纸本)9781510679771

It is still difficult to accurately extract smooth and consistent 3D human motion from video footage over time. While some existing techniques have achieved favorable outcomes by utilizing the combined features of consecutive frames, many of them compromise accuracy in order to reduce jitter or do not have a complete understanding of the temporal nature of human movement. To this end, we model the natural smoothing properties in body motion by learning the long-range temporal relationship between the kinematic features of the human body in the video and the enhanced current frame features. First, we use the velocity and acceleration of key points to effectively capture temporal features as our temporal motion prior, and then we have created a module that uses a hierarchical attention mechanism to improve the representation of the current frame by selectively focusing on important temporal information from both past and future frames. This enhances the correlation between frames and improves the overall quality of the feature representation. Ultimately these two parts of features are aggregated together through a global motion aware network and linear fusion is performed to obtain the final accurate 3D human motion. © 2024 SPIE.

关键词： Acceleration

来源：评论

学校读者我要写书评

暂无评论

Velocity Field-Based Surveillance Video Frame Deletion Detection Using Siamese Network 27th

Velocity Field-Based Surveillance Video Frame Deletion Detec...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Su, Yang Tan, ShunQuan Huang, Jiwu College of Information Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9783031783111

Surveillance videos play a crucial role in providing evidences. However, the deletion of even a few frames can significantly impact the interpretation of events, while the deletion can be performed easily using video editing softwares without leaving visual traces. This paper introduces a novel method to detect video frame deletion based on velocity field characteristics. The main idea is to convert long videos into a feature sequence, which appears as a sequence containing outlier values for videos with frame deletions, and as a sequence without outlier values for original videos. The proposed approach employs a siamese network to distinguish frame deletions between adjacent frames. A video can be transformed into a feature sequence through the siamese network, and the resulting sequence is fed into a binary classifier for final classification. Experimental results demonstrate the effectiveness of our proposed approach, even for longer videos (e.g., 2000 frames) with minimal frame deletions (e.g., 1 frame). © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Digital forensics

来源：评论

学校读者我要写书评

暂无评论

Event-enhanced synthetic aperture imaging

引用

Science China(Information Sciences) 2025年第3期68卷 388-390页

作者： Siqi LI Shaoyi DU Jun-Hai YONG Yue GAO Beijing National Research Center for Information Science and Technology School of SoftwareTsinghua University Institute for Brain and Cognitive Sciences Beijing Laboratory of Brain and Cognitive IntelligenceTsinghua University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and ApplicationsInstitute of Artificial Intelligence and Robotics Xi'an Jiaotong University

Synthetic aperture imaging(SAI) methods aim to see through dense occlusions and reconstruct the target scene behind occlusions. Traditional frame-based SAI methods,e.g., DeOccNet [1], take the occluded light field ima...

关键词：

来源：评论

学校读者我要写书评

暂无评论

General Optimal Trajectory Planning:Enabling Autonomous Vehicles with the Principle of Least Action

引用

engineering 2024年第2期33卷 63-76页

作者： Heye Huang Yicong Liu Jinxin Liu Qisong Yang Jianqiang Wang David Abbink Arkady Zgonnikov School of Vehicle and Mobility Tsinghua UniversityBeijing 100084China Department of Cognitive Robotics Faculty of MechanicalMaritime and Materials Engineering(3mE)Delft University of TechnologyDelft 2628Netherlands Department of Software Technology Faculty of Electrical EngineeringMathematics and Computer ScienceDelft University of TechnologyDelft 2628Netherlands Xi’an Institute of High-Technology Xi’an 710051China

This study presents a general optimal trajectory planning(GOTP)framework for autonomous vehicles(AVs)that can effectively avoid obstacles and guide AVs to complete driving tasks safely and ***,we employ the fifth-order Bezier curve to generate and smooth the reference path along the road *** coordinates are then transformed to achieve the curvature continuity of the generated *** the road constraints and vehicle dynamics,limited polynomial candidate trajectories are generated and smoothed in a curvilinear coordinate ***,in selecting the optimal trajectory,we develop a unified and auto-tune objective function based on the principle of least action by employing AVs to simulate drivers’behavior and summarizing their manipulation characteristics of“seeking benefits and avoiding losses.”Finally,by integrating the idea of receding-horizon optimization,the proposed framework is achieved by considering dynamic multi-performance objectives and selecting trajectories that satisfy feasibility,optimality,and *** simulations and experiments are performed,and the results demonstrate the framework’s feasibility and effectiveness,which avoids both dynamic and static obstacles and applies to various scenarios with multi-source interactive traffic ***,we prove that the proposed method can guarantee real-time planning and safety requirements compared to drivers’manipulation.

关键词： Autonomous vehicle Trajectory planning Multi-performance objectives Principle of least action

来源：评论

学校读者我要写书评

暂无评论

Parallel Bounded Search for the Maximum Clique Problem

引用

Journal of Computer Science & Technology 2023年第5期38卷 1187-1202页

作者：江华白珂刘海姣李初民 Felip Manya 付樟华 Engineering Research Center of Cyberspace Yunnan UniversityKunming 650500China School of Software Yunnan UniversityKunming 650500China Laboratory of Modeling Information and SystemsUniversity of Picardie Jules VerneAmiens 80039France Artificial Intelligence Research Institute Spanish National Research CouncilCatalonia 08193Spain Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen 518000China Institute of Robotics and Intelligent Manufacturing Chinese University of Hong KongShenzhen 518000China

Given an undirected graph,the Maximum Clique Problem(MCP)is to find a largest complete subgraph of the *** is NP-hard and has found many practical *** this paper,we propose a parallel Branch-and-Bound(BnB)algorithm to tackle this NP-hard problem,which carries out multiple bounded searches in *** search has its upper bound and shares a lower bound with the rest of the *** potential benefit of the proposed approach is that an active search terminates as soon as the best lower bound found so far reaches or exceeds its upper *** describe the implementation of our highly scalable and efficient parallel MCP algorithm,called PBS,which is based on a state-of-the-art sequential MCP *** proposed algorithm PBS is evaluated on hard DIMACS and BHOSLIB *** results show that PBS achieves a near-linear speedup on most DIMACS instances and a superlinear speedup on most BHOSLIB ***,we give a detailed analysis that explains the good speedups achieved for the tested instances.

关键词： Branch-and-Bound(BnB) maximum clique problem(MCP) parallel search

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：