检索结果-内蒙古大学图书馆

Evolutional Codes: Novel Efficient Graph Data Representation for Mobile Edge Computing

IEEE Transactions on Network Science and engineering 2024年第1期11卷 1387-1397页

作者： Sun, Elaine Y.-N. Wu, Hsiao-Chun Huang, Scott C.-H. Kuan, Yen-Cheng Yung, Chi National Tsing Hua University Department of Electrical Engineering Hsinchu30013 Taiwan Louisiana State University School of Electrical Engineering and Computer Science Baton RougeLA70803 United States Yuan Ze University Innovation Center for Ai Applications Chungli32003 Taiwan International College of Semiconductor Technology Hsinchu30010 Taiwan

To transmit big graph data emerging from prevalent social networks and biological networks over mobile devices has become challenging nowadays. Since graphs are usually represented by the associated adjacency matrices or graph data structures, dynamic node (vertex) re-ordering to reflect the nodes' real relations (for example, spatial or structural relations) is desirable in practice but impossible for these two existing graph-representation methods. Lately, we proposed a novel evolutional coding technique, which can restructure graph data dynamically, flexibly, and efficiently for transmission among mobile devices. Memory efficiency, in terms of number of memory storage units, is a crucial performance measure for mobile edge computing. To select the optimal graph-representation strategy for arbitrary graph data, we define a new graph-taxonomy metric dependent on the edge density (edges per node) in this work. According to our newly defined graph-taxonomy metric, one can choose the optimal graph-representation solution among the three aforementioned methods in terms of required memory-storage space for any application. Pertinent theorems and proofs for the underlying comparative studies on graph representation are presented in this article. © 2013 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Domain Aware Multi-task Pretraining of 3D Swin Transformer for T1-Weighted Brain MRI 17th

Domain Aware Multi-task Pretraining of 3D Swin Transformer ...

引用

17th Asian Conference on computer Vision, ACCV 2024

作者： Kim, Jonghun Kim, Mansu Park, Hyunjin Department of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea Republic of Center for Neuroscience Imaging Research Institute for Basic Science Suwon Korea Republic of AI Graduate School Gwangju Institute of Science and Technology Gwangju Korea Republic of

ISBN: (纸本)9789819609000

The scarcity of annotated medical images is a major bottleneck in developing learning models for medical image analysis. Hence, recent studies have focused on pretrained models with fewer annotation requirements that can be fine-tuned for various downstream tasks. However, existing approaches are mainly 3D adaptions of 2D approaches ill-suited for 3D medical imaging data. Motivated by this gap, we propose novel domain-aware multi-task learning tasks to pretrain a 3D Swin Transformer for brain magnetic resonance imaging (MRI). Our method considers the domain knowledge in brain MRI by incorporating brain anatomy and morphology as well as standard pretext tasks adapted for 3D imaging in a contrastive learning setting. We pretrain our model using large-scale brain MRI data of 13,687 samples spanning several large-scale databases. Our method outperforms existing supervised and self-supervised methods in three downstream tasks of Alzheimer’s disease classification, Parkinson’s disease classification, and age prediction tasks. The ablation study of the proposed pretext tasks shows the effectiveness of our pretext tasks. Our code is available at ***/jongdory/DAMT. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

A Joint Tracking System: Robot is Online to Access Surveillance Views

A Joint Tracking System: Robot is Online to Access Surveilla...

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Lin, Zheyuan Ji, Shanshan Wang, Wen Qin, Mengjie Yang, Rong Wan, Minhong Gu, Jason Li, Te Zhang, Chunlong Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Research Center for Intelligent Robotics Hangzhou311100 China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou311100 China Dalhousie University Department of Electrical and Computer Engineering HalifaxNSB3H 4R2 Canada

ISBN: (纸本)9798350325706

The application of robots in social life, equipped with sensors and actuators and embedded with ai, assists people in all aspects. However, the first perspective of the robot horizon is heavily constrained, which weakens its performance. A joint tracking system is designed and built to deal with this, by integrating a surveillance system with the robot visual, providing a third perspective. This system takes one horizontal view and two top views from various directions as inputs and matches a person among the frames and in time sequence. In order to deal with the identity match with a huge visual feature gap, a special dataset is collected, simultaneously labeling identities from a mobile robot perspective and multiple indoor static surveillance monitors. The experiment shows that such match is a task worth exploring that can be better handled by training on our dataset than existing open source Re-identification (Re-id) datasets. Moreover, in the real scenario, this system improves the performance on issues like in and out of the robot's field of vision and heavy occlusion by people or objects. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Revisiting kernel attention with correlated Gaussian process representation 24

Revisiting kernel attention with correlated Gaussian process...

引用

Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence

作者： Long Minh Bui Tho Tran Huu Duy Dinh Tan Minh Nguyen Trong Nghia Hoang FPT Software AI Center and School of Electrical Engineering and Computer Science Washington State University FPT Software AI Center and Department of Mathematics National University of Singapore FPT Software AI Center Department of Mathematics National University of Singapore School of Electrical Engineering and Computer Science Washington State University

Transformers have increasingly become the de facto method to model sequential data with state-of-the-art performance. Due to its widespread use, being able to estimate and calibrate its modeling uncertainty is important to understand and design robust transformer models. To achieve this, previous works have used Gaussian processes (GPs) to perform uncertainty calibration for the attention units of transformers and attained notable successes. However, such approaches have to confine the transformers to the space of symmetric attention to ensure the necessary symmetric requirement of their GP's kernel specification, which reduces the representation capacity of the model. To mitigate this restriction, we propose the Correlated Gaussian Process Transformer (CGPT), a new class of transformers whose self-attention units are modeled as cross-covariance between two correlated GPs (CGPs). This allows asymmetries in attention and can enhance the representation capacity of GP-based transformers. We also derive a sparse approximation for CGP to make it scale better. Our empirical studies show that both CGP-based and sparse CGP-based transformers achieve better performance than state-of-the-art GP-based transformers on a variety of benchmark tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive SLAM Dataset for Indoor Exhibition Environments: Data Collection, Processing, and Comparative Evaluation

A Comprehensive SLAM Dataset for Indoor Exhibition Environme...

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Yuan, Songyu Zhang, Jing Pan, Chen Zhang, Chunlong Wan, Minhong Zheng, Tao Gu, Jason Zhejiang Lab Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Hangzhou311100 China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou311100 China Dalhousie University Department of Electrical and Computer Engineering HalifaxNSB3H 4R2 Canada

ISBN: (纸本)9798350325706

The field of Simultaneous Localization and Mapping(SLAM) has witnessed significant advancements in recent years. However, due to the difficulty of data obtains and ground-truth makes, there is a lack of real indoor scenarios datasets, especially the scenarios with less-texture, repeat-texture, extreme light condition, causing the slowly progress in indoor SLAM. In this paper, we present a dataset captured in a real indoor exhibition hall with diverse type of sensor data. Which contributes to diverse school of SLAM that using different sensors. We provide ground-truth 6DoF pose captured by motion capture devices, RGB-D data captured by a RealSense D455 camera. Laser-data captured by Ouster. And a high-resolution color point cloud captured by a laser scanner. This dataset offers three distinct sources of ground truth from real-world scenarios. It combines motion capture, ICP based laser localization, and visual localization methods to provide comprehensive and accurate reference data. This dataset is designed for evaluating positioning methods that employ various types of sensors, moving beyond a singular matrix-based evaluation approach. Besides, We show results of several state-of-the-art SLAM method in our datasets, illustrates the utility of our dataset and served as a reference for other researcher. We converge LiDAR-based SLAM with ground truth, made a good closure. An ensemble approach-based Visual SLAM, achieves results of odometry errors of 4% and loop closure position errors of 40 cm. Additionally, visual localization demonstrated an absolute position error of 21 cm using high-resolution point clouds. We highlight the potentials of our indoor datasets in LiDAR SLAM, RGB-D SLAM, and visual localization and combines method. The datasets are available at https://***/IMBAfarmer09/ExhibitionDataset © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DyFormer: A CNN-Transformer Network Combining Local and Global Attention for Optical Remote Sensing Object Detection 4

DyFormer: A CNN-Transformer Network Combining Local and Glob...

引用

4th International Conference on Artificial Intelligence, Virtual Reality and Visualization, aiVRV 2024

作者： Huang, Youxiang Wang, Qin Jiao, Donglai Wang, Shufei Wang, Yu Lu, Zhiyi Ohtsuki, Tomoaki Gui, Guan College of Telecommunications and Information Engineering Njupt Nanjing China Ai Research Center Nanjing Great Information Technology Co. Ltd Nanjing China Keio University Department of Information and Computer Science Yokohama Japan

ISBN: (纸本)9798331528744

Remote sensing image (RSI) object detection is crucial for natural disaster management, urban planning, and resource exploration. However, due to significant differences between RSIs and natural images (NIs), existing object detectors designed for NIs are not directly applicable to RSIs. CNN-based models typically require specialized attention modules to relate small targets to global contexts, while Transformer-based models often add modules to enhance detail extraction, increasing computational costs for edge deployment. To address these challenges, we propose DyFormer, a hybrid CNN-Transformer model that combines local and global attention mechanisms for effective feature fusion. Additionally, a feature residual pyramid network (FRPN) is introduced to enhance multi-scale feature integration. We conduct experiments on the open source NWPU VHR-10 dataset to evaluate the proposed DyFormer, achieving a mAP@0.5 of 61.7%, outperforms existing sort-of-the-art methods, demonstrating its effectiveness for RSI object detection tasks. © 2024 IEEE.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

An Actor-Critic Reinforcement Learning Scheme for Reactive 3D Optimal Motion Planning Based on Fluid Dynamics

An Actor-Critic Reinforcement Learning Scheme for Reactive 3...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Marios Malliaropoulos Panagiotis Rousseas Charalampos P. Bechlioulis Kostas J. Kyriakopoulos School of Mechanical Engineering Control Systems Laboratory National Technical University of Athens Department of Electrical and Computer Engineering University of Patras Center of AI & Robotics (CAIR) New York University Abu Dhabi

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

This work proposes a novel and provably correct method for three-dimensional optimal motion planning in complex environments. Our approach models the 3D motion planning problem by solving streamlines of the potential fluid flow, filling a gap in traditional motion planning techniques by guaranteeing a closed-loop, smooth and natural-looking navigation solution. Special emphasis is given to an inherent challenge of artificial potential field (APF) methods, namely establishing proofs of safety and stability over the entire optimization process. A model-based actor-critic reinforcement learning algorithm is introduced to approximate the optimal solution to the Hamilton-Jacobi-Bellman equation and update the controller parameters in a deterministic manner. Through a series of ROS-Gazebo software-in-the-loop simulations the proposed methodology demonstrates robustness and outperforms widely used methods such as the RRT ∗ , highlighting its contribution to the field of 3D optimal motion planning.

关键词： Solid modeling Three-dimensional displays Navigation Reinforcement learning Mathematical models Stability analysis Robustness Planning Safety Optimization

来源：评论

学校读者我要写书评

暂无评论

Machine Learning In Sustainable Development–An Overview

Machine Learning In Sustainable Development–An Overview

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Ramiz Salama Fadi Al-Turjman Chadi Altrjman Richa Gupta Department of Computer Engineering AI and Robotics Institute Research Center for AI and IoT Near East University Nicosia Turkey Artificial Intelligence Engineering Dept. AI and Robotics Institute Near East University Turkey Faculty of Engineering University of Kyrenia Kyrenia Turkey Waterloo University Canada Department of Computer Science and Engineering Graphic Era Hill University Dehradun India

I have studied how artificial intelligence (ai) or machine learning (ML) is applied in a sustainable system called "Eugenie" for my work, project, and thesis. In this project, I get to discuss Eugenie’s role in ensuring the sustainability of large environmental business organizations. I also get to discuss how it aids operation managers in making predictions about when their machines will break down days, weeks, and months in advance, allowing them to schedule maintenance cycles more effectively. In other words, Eugenie provides plant operators with data so they can prioritize repairs. Eugenie executes this process by utilizing real-time data from numerous sensors attached to large machinery and equipment in the process industry, metals and mining, oil and gas, and smart cities industries. Two products make up this program; the first is named RAY-FINN and the second is called PAPILLON. Eugenie assists businesses in a variety of ways, including:•aids in the attainment of operational excellence by process organizations•Always raise overall profitability.•Contributes to a greener and safer future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Robust Visually Secure Bit Plane Image Encryption Using Chaotic Map and SHA-512 3

A Robust Visually Secure Bit Plane Image Encryption Using Ch...

引用

3rd International Conference on Emerging Trends in Electrical, Control, and Telecommunication engineering, ETECTE 2024

作者： Khan, Jan Sher Ahmed, Saygin Siddiq Haq, Farman Ul Tariq, Noshina Ahmad, Jawad Ashraf, Muhammad Department of Avionics Engineering Air University Islamabad Pakistan Department of Renewable Energy Techniques College of Oil and Gas Techniques Engineering Northern Technical University Iraq Department of Computer Sciences SZABIST Islamabad Pakistan Department of AI and DS National University of Computer and Emerging Sciences Islamabad Pakistan Cybersecurity Center Prince Mohammad Bin Fahd University Alkhobar Saudi Arabia

ISBN: (纸本)9798331504861

With the introduction of the latest digital technologies, the protection of images from unauthorized use has become increasingly important, necessitating the development of robust image encryption techniques. This paper proposes a novel bit plane image encryption method that incorporates chaos theory and cryptographic hash functions. To ensure a high degree of security, the key for the three-dimensional Intertwining Logistic chaotic map is generated (initial conditions) using the SHA-512 hash algorithm. The chaotic map is then utilized to generate two random vectors and one random matrix, respectively. In order to shuffle the original bit plane structure, random vectors are used to scramble the pixel positions across the bit planes. A bitwise XOR operation is then performed on the shuffle bit planes with the third random matrix. To avoid the attention of potential hackers, a visually secured ciphertext image is generated by embedding the noise-like ciphertext within a host image. Several tests, such as histogram, correlation coefficient, key sensitivity, key space, entropy, Number of Pixel Change Rate (NPCR), and Unified Average Change Intensity (UACI), were performed on the proposed visually secured bit plane image encryption scheme. As a result of the extensive tests, one can conclude that the proposed scheme is robust and can withstand a wide range of possible cryptographic attacks. ©2024 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Reinforcement Learning Techniques in Simulated robotics Environments

Comparative Analysis of Reinforcement Learning Techniques in...

引用

IEEE International Conference of Intelligent Robotic and Control engineering (IRCE)

作者： Abey Yoseph M. Hassan Tanveer Razvan Cristian Voicu M. Farrukh Shahid Department of Robotics & Mechatronics Engineering Kennesaw State University Marietta Department of AI and Data Science National University of Computer and Emerging Sciences Karachi Pakistan

ISBN: (数字)9798350352399

ISBN: (纸本)9798350352405

Machine learning is a critical component of artificial intelligence and computer science that uses data and algorithms to emulate the way that humans learn and predict. Reinforcement learning, one of the many forms of machine learning, trains an agent through trial and error, with successful outcomes being rewarded and unsuccessful outcomes being penalized. The implementation of three reinforcement learning algorithms, Qlearning, Deep Q-Learning, and Double Deep Q-Learning, was tested using a series of ROS (Robot Operating System) packages in the Gazebo simulation environment. The Python openai_ros package and Gym libraries were used to input a robot into a configurable environment and test out the performance of a specific reinforcement learning algorithm. The agent’s action space was discretized into three specific actions, move forward, turn left, or turn right, that the robot could take. The reward or punishment was given after each step based on if the current action moved the robot towards the goal state or away from it. For each algorithm, the agent was first pre-trained on an obstacle free environment for 200 episodes and then was placed in an environment with two box-shaped obstacles to avoid. The algorithm/neural network parameters from the pre-training environment were loaded prior to the agent being tested in the new environment. The goal state at each episode was randomly generated and the robot’s performance was evaluated using the cumulative reward achieved per episode and the number of times it reached the goal.

关键词： Training Measurement Q-learning Machine learning algorithms Operating systems Robot vision systems Turning Prediction algorithms Libraries Robots

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：