检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Shi, Jianxin Chen, Jinhao Chen, Xiaolong Ma, Jun Wo, Tianyu School of Computer Science and Engineering Beihang University Beijing China Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology Guangzhou China

ISBN: (纸本)9798350368741

Accurately predicting the future motions of traffic agents is essential for autonomous systems. Despite the significant success of existing motion forecasting methods based on supervised learning, they still exhibit two main limitations. First, when annotated data for a scene is limited, these methods often fail to achieve the expected accuracy. Second, they typically rely on complex architectures and extensive prior knowledge to improve performance. To overcome these challenges, we propose MF-BERT, a novel framework that adapts the concept of BERT to motion forecasting, inspired by advancements in the self-supervised pre-training paradigm. During pre-training, we design a siamese sequence modeling task with an asymmetric mask strategy to capture complex behavior patterns of agents. During fine-tuning, the pre-trained representation module initializes the feature encoder of the motion forecasting model, and a multimodal trajectory decoder generates all possible predictions. Experimental results demonstrate the superiority of MF-BERT over state-of-the-art methods. © 2025 IEEE.

关键词： Autonomous Motion Forecasting Self-supervised Learning Time Series Analysis

来源：评论

学校读者我要写书评

暂无评论

Multiobjective adaptive car-following control of an intelligent vehicle based on receding horizon optimization

引用

science China(Information sciences) 2023年第4期66卷 301-302页

作者： Hongbo GAO Juping ZHU Fei ZHANG Ruidong YAN Junjie ZHOU Lei JIANG Jianqiang WANG Keqiang LI Department of Automation University of Science and Technology of China Institute of Advanced Technology University of Science and Technology of China Department of Computational Mathematics School of Mathematical Sciences Anhui University School of Traffic and Transportation Beijing Jiaotong University Autonomous Driving Business Unit Chery Automobile School of College of Computer Science and Technology Zhejiang University China North Vehicle Research Institute School of Automotive Engineering Tsinghua University

Dear editor, Vehicle control is one of the key steps of intelligent driving [1]. Algorithms based on receding horizon optimization(RHO) can predict future trajectories and handle multiobjective constraint conditions; therefore, RHO-based methods have attracted considerable attention in the field of vehicle control. Although existing methods use RHO to design controllers, they do not simultaneously meet the multiobjective optimal control performance requirements on tracking, fuel economy, and ride comfort.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An adaptive Q-learning based particle swarm optimization for multi-UAV path planning

引用

Soft Computing 2024年第13-14期28卷 7931-7946页

作者： Tan, Li Zhang, Hongtao Liu, Yuzhao Yuan, Tianli Jiang, Xujie Shang, Ziliang School of Computer Science and Engineering Beijing Technology and Business University No. 33 Fucheng Road Haidian District Beijing100048 China Chongqing Institute of Microelectronics Industry Technology University of Electronic Science and Technology of China Xiyong Micro-electricity Park Pingba District Chongqing400000 China

In recent times, the path planning of unmanned aerial vehicles (UAVs) in 3D complex flight environments has become a hot topic in the field of UAV technology. Path planning is a crucial process that involves determining the trajectory of the UAV from the point of origin to its destination. However, a number of algorithms proposed for this task have been proven inefficient in this 3D space. In response, this paper proposes the use of an adaptive Q-Learning based particle swarm optimization to tackle the problem. This algorithm introduces the Q-Learning algorithm and designs four states and actions for each particle. Based on the accumulated experience from reinforcement learning, the particles can choose the appropriate action in different states. To evaluate the performance of the AQLPSO algorithm, extensive simulation experiments were conducted. These experiments involved comparing the AQLPSO algorithm with existing algorithms such as PSO, PSO-SA, and RMPSO. The results of the simulations demonstrated that the AQLPSO algorithm outperformed these algorithms in terms of multiple performance metrics. It effectively solved the UAV path planning problem in 3D complex flight environments by reducing the likelihood of falling into local optima, improving efficiency, and achieving faster convergence towards the global optimal solution. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks (GANs) for Artistic Style Transfer in Images

Generative Adversarial Networks (GANs) for Artistic Style Tr...

引用

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Jamalpur, Bhavana Kiruthiga, S. Ranjitha, B. Lefty Joyson, J. Jayaram, K. Soundar, K. Ruba S R University Department of Computer Science and Artificial Intelligence India School of Computing Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science & Engineering Chennai India Mohan Babu University Department of Mathematics India Jp College of Engineering Department of Computer Science and Engineering Ayikudi India College of Engineering Adoor Department of Computer Science and Engineering Pathanamthitta India Department of Computer Science and Engineering Sivakasi India

ISBN: (纸本)9798350375442

Many in computer vision and computational imaging consider Generative Adversarial Networks (GANs) a big advance. Style transfer converts semantic visual content into creative styles. Recently, GANs for style transfer have gained popularity. Adversarial training of GANs to create realistic counterfeits has yielded encouraging results. High-quality style transfer results have been achieved using this method. Mode collapse is a common problem in classical GANs. This causes unsteady training and poor style transmission. Additionally, the GAN generator only supports one style. Therefore, numerous GANs must be trained to allow users to shift styles. This study examines artistic style transfer in photographs using depth extraction generative adversarial network (DE-GAN). This research aims to improve photo aesthetics by adding famous artworks' distinctive qualities. This study investigates DE-GANs' mechanics and how they modify text while keeping a style's creative qualities. By studying adversarial training, this work hopes to understand how DE-GAN achieves this dual goal. This research analyzes DE-GAN-based style transfer models to evaluate their effectiveness, identify their limits, and recommend areas for improvement. The experiments show that DE-GAN creates realistic and attractive stylized visuals. This study also discusses DE-GAN's practical applications, problems, and future possibilities in artistic style transfer. © 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

On the Adversarial Robustness of Hierarchical Classification

On the Adversarial Robustness of Hierarchical Classification

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Wang, Ran Zeng, Simeng Wu, Wenhui Jia, Yuheng Ng, Wing W. Y. Wang, Xizhao School of Mathematical Sciences Shenzhen University Shenzhen518060 China College of Electronic and Information Engineering Shenzhen University Shenzhen518060 China School of Computer Science and Engineering Southeast University Nanjing211189 China School of Computer Science and Engineering South China University of Technology Guangzhou510006 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

ISBN: (纸本)9781665410205

Deep neural networks (DNNs) have demonstrated remarkable success on various learning problems, but they face a formidable challenge in the form of adversarial attacks. Especially, when dealing with complex classification tasks for numerous classes with a hierarchical structure, the adversarial robustness of a DNN model may drop seriously. In this paper, we investigate the adversarial robustness of DNN models on such complex classification tasks. In response, we propose a two-stage hierarchical classification framework, which is composed of a coarse-grained classifier and a series of fine-grained classifiers. A data correction sampling module is designed between the two stages, in order to mitigate the influence of misclassification caused by the coarse-grained classifier;and a discriminative filter learning module is employed in the fine-grained classification, in order to gain better distinguish abilities among fine-grained categories. Experiments on the well-known dataset CIFAR-100 and a newly-constructed hierarchical dataset mini-ImageNet76 demonstrate that employing a hierarchical framework can effectively improve the model robustness on such complex classification tasks. © 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

MKGL: Mastery of a Three-Word Language 38

MKGL: Mastery of a Three-Word Language

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Guo, Lingbing Bo, Zhongpu Chen, Zhuo Zhang, Yichi Chen, Jiaoyan Lan, Yarong Sun, Mengshu Zhang, Zhiqiang Luo, Yangyifei Li, Qian Zhang, Qiang Zhang, Wen Chen, Huajun College of Computer Science and Technology Zhejiang University China ZJU-Ant Group Joint Lab of Knowledge Graph China Ant Group China Department of Computer Science The University of Manchester United Kingdom School of Computer Science and Engineering Beihang University China School of Computer Science Beijing University of Posts and Telecommunications China School of Software Technology Zhejiang University China

Large language models (LLMs) have significantly advanced performance across a spectrum of natural language processing (NLP) tasks. Yet, their application to knowledge graphs (KGs), which describe facts in the form of triplets and allow minimal hallucinations, remains an underexplored frontier. In this paper, we investigate the integration of LLMs with KGs by introducing a specialized KG Language (KGL), where a sentence precisely consists of an entity noun, a relation verb, and ends with another entity noun. Despite KGL's unfamiliar vocabulary to the LLM, we facilitate its learning through a tailored dictionary and illustrative sentences, and enhance context understanding via real-time KG context retrieval and KGL token embedding augmentation. Our results reveal that LLMs can achieve fluency in KGL, drastically reducing errors compared to conventional KG embedding methods on KG completion. Furthermore, our enhanced LLM shows exceptional competence in generating accurate three-word sentences from an initial entity and interpreting new unseen terms out of KGs. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Algorithmic Innovations in Machine Learning for Drug Discovery and Pharmaceutical Innovations 2

Algorithmic Innovations in Machine Learning for Drug Discove...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Sangeetha, M. Harin Fernandez, F. Mary Ganesh Ramachandran, A. Saravanan, S.K. Bhanumathi, M. University of Technology and Applied Sciences Department of Computer Engineering Nizwa Oman Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science Chennai India Saveetha School of Engineering Simats BigData and Network Security Department of Computers Science and Engineering Tamil Nadu Chennai India Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350384277

Algorithmic advancements in machine learning have transformed drug discovery and pharmaceutical innovation. This study examines how machine learning might speed medication development and pharmaceutical innovation. Data from genomes, chemistry, and clinical trials is collected to start the research. Careful data cleansing, normalization, and feature engineering prepare the data for model building. Random Forest, SVM, NN, Decision Tree, and Logistic Regression are tested for prediction. ROC AUC results show that Random Forest is the most accurate model at 86%. Ensemble approaches have drug discovery potential. Beyond accuracy, models are assessed for precision, false positive, and false negative rates. Drug discovery relies on precision to measure positive predictions. The Random Forest model makes the most accurate positive predictions at 0.87. However, false positives and negatives also matter in drug discovery. The Decision Tree model contains the falsest positives (35), underlining the need to reduce them to save resources. The Neural Network approach reduces false negatives to 12, ensuring good medication candidates are not overlooked. The results show that different machine learning models have trade-offs, underscoring the necessity for a personalized strategy depending on objectives and restrictions. Algorithmic breakthroughs in pharmaceutical innovation reduce medication development time by 40% and cost by 25%, according to the study. © 2024 IEEE.

关键词： Drug discovery

来源：评论

学校读者我要写书评

暂无评论

A Survey of Punjabi Language Translation using OCR and ML 10

A Survey of Punjabi Language Translation using OCR and ML

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Khepra, Shaveta Kumari, Priya Gupta, Raj Abhishek Bramhe, Vijendra Singh School of Engineering and Technology Sharda University Department of Computer Science and Engineering Greater Noida India Shri Ramdeobaba College of Engineering and Management Department of Computer Science and Engineering Nagpur India

ISBN: (纸本)9789380544472

The use of Natural Language Processing (NLP) in machine translation has grown in significance as technologies as well as computers have become more prevalent in our daily lives. This essay's goal is to evaluate the work done in the field of natural language processing (NLP) to translate the Gurmukhi script, which is primarily used to represent the Punjabi language. Together with Hindi and Punjabi, the languages written throughout the Gurumukhi script has more than 1.5 billion native users, making it among the most used language worldwide. However, there is limited research available on the Gurmukhi script. The study presented in this paper focuses on using machine learning and AI techniques to translate written Gurmukhi text into Hindi and English languages. The input for the translation process will be in the form of machine-printed Gurmukhi text, while the output will be provided in both Hindi and English languages. The goal of this study is to enhance how well global languages absorb information and technology, making it easier and more accurate to translate from regional languages. In conclusion, the paper provides a comprehensive review of the work related to the translation of Gurmukhi script using NLP techniques, with a focus on the use of machine learning and AI. The findings of this study can contribute to the development of more advanced and accurate translation systems, making the exchange of information and knowledge more accessible for people who speak different languages. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Derivative Matrix-Based Covert Communication Method in Blockchain

引用

computer Systems science & engineering 2023年第7期46卷 225-239页

作者： Xiang Zhang Xiaona Zhang Xiaorui Zhang Wei Sun Ruohan Meng Xingming Sun School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China School of Hydrology and Water Resources Nanjing University of Information Science&TechnologyNanjing210044China Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Key Laboratory of Hydrometeorological Disaster Mechanism andWarning ofMinistry ofWater Resources Nanjing210044China Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) NanjingUniversity of Information Science&TechnologyNanjing210044China School of Automation Nanjing University of Information Science&TechnologyNanjing210044China School of Computer Science Engineering Nanyang Technological UniversitySingapore

The data in the blockchain cannot be tampered with and the users are anonymous,which enables the blockchain to be a natural carrier for covert ***,the existing methods of covert communication in blockchain suffer from the predefined channel structure,the capacity of a single transaction is not high,and the fixed transaction behaviors will lower the concealment of the communication ***,this paper proposes a derivation matrix-based covert communication method in *** uses dual-key to derive two types of blockchain addresses and then constructs an address matrix by dividing addresses into multiple layers to make full use of the redundancy of ***,to solve the problem of the lack of concealment caused by the fixed transaction behaviors,divide the rectangular matrix into square blocks with overlapping regions and then encrypt different blocks sequentially to make the transaction behaviors of the channel addresses match better with those of the real ***,the linear congruence algorithm is used to generate random sequence,which provides a random order for blocks encryption,and thus enhances the security of the encryption *** results show that this method can effectively reduce the abnormal transaction behaviors of addresses while ensuring the channel transmission efficiency.

关键词： Covert communication blockchain concealment security capacity derivation

来源：评论

学校读者我要写书评

暂无评论

Multi-cost fusion stereo matching algorithm based on guided filter aggregation 3

Multi-cost fusion stereo matching algorithm based on guided ...

引用

3rd International Conference on Artificial Intelligence and computer engineering, ICAICE 2022

作者： Liu, Jingwen Zhang, Xuedong School of Computer and Software Engineering University of Science and Technology Liaoning Anshan114051 China School of Electronic and Information Engineering University of Science and Technology Liaoning Anshan114051 China

ISBN: (纸本)9781510663473

Aiming at the low matching accuracy of existing local stereo matching algorithms in weak texture areas, a local stereo matching algorithm based on multi-matching cost fusion and guided filtering cost aggregation with adaptive parameters is proposed. First, use the gradient direction to improve the gradient cost, and calculate the matching cost by combining the gradient cost with the Census transform and color cost. Secondly, the cost is aggregated by the guided filtering of adaptive parameters;Finally, the final disparity map is obtained through disparity calculation and multi-step disparity refinement. The improved algorithm is tested on 15 training sets on the Middlebury3 platform, and the average false matching rates of bad4.0 in all areas and non-occluded areas are 19.9% and 13.2%, respectively, which is improved compared with AD-Census and other algorithms. © 2023 SPIE.

关键词： Textures

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：