检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Johnson, Jacob J. Qureshi, Ahmed H. Yip, Michael C. The Electrical and Computer Engineering Department University of California La Jolla San DiegoCA United States The Department of Computer Science Purdue University West LafayetteIN United States

Motion planning is integral to robotics applications such as autonomous driving, surgical robots, and industrial manipulators. Existing planning methods lack scalability to higher-dimensional spaces, while recent learning-based planners have shown promise in accelerating sampling-based motion planners (SMP) but lack generalizability to out-of-distribution environments. To address this, we present a novel approach, Vector Quantized-Motion Planning Transformers (VQ-MPT) that overcomes the key generalization and scaling drawbacks of previous learning-based methods. VQ-MPT consists of two stages. Stage 1 is a Vector Quantized-Variational AutoEncoder model that learns to represent the planning space using a finite number of sampling distributions, and stage 2 is an Auto-Regressive model that constructs a sampling region for SMPs by selecting from the learned sampling distribution sets. By splitting large planning spaces into discrete sets and selectively choosing the sampling regions, our planner pairs well with out-of-the-box SMPs, generating near-optimal paths faster than without VQ-MPT's aid. It is generalizable in that it can be applied to systems of varying complexities, from 2D planar to 14D bi-manual robots with diverse environment representations, including costmaps and point clouds. Trained VQ-MPT models generalize to environments unseen during training and achieve higher success rates than previous methods. Videos and code are available at https://***/***/vq-mpt/home. Copyright © 2023, The Authors. All rights reserved.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Advanced Persistent Threat Identification with Boosting and Explainable AI

引用

SN computer science 2023年第3期4卷 271页

作者： Hasan, Md. Mahadi Islam, Muhammad Usama Uddin, Jasim Department of Computer Science and Engineering Asian University of Bangladesh Ashulia Dhaka 1341 Bangladesh School of Computing and Informatics University of Louisiana at Lafayette 104 E University Ave Lafayette 70503 LA United States Department of Applied Computing and Engineering Cardiff School of Technologies Cardiff Metropolitan University Western Avenue Wales Cardiff CF5 2YB United Kingdom

Advanced persistent threat (APT) is a serious concern in cyber-security that has matured and grown over the years with the advent of technology. The main aim of this study is to establish an effective identification model for APT attacks to prevent and reduce their influence. Machine learning has the potential as well as substantial background to detect and predict cyber-security threats including APT. This study utilized several boosting-based machine learning methods to predict various types of APTs that are consistent in cyber-security domain. Furthermore, Explainable Artificial Intelligence (XAI) was coupled with the predictions to provide actionable insights to the domain stakeholders as well as practitioners in this domain. The results, particularly XGBoost with weighted F1 score of 0.97 and SHapley Additive exPlanations (SHAP)-based explanation, prove that boosting methods as well as machine learning models paired with XAI are indeed promising in handling cyber-security-related dataset problems which can be extrapolated towards new avenues of challenging research by effectively deploying boosting-based XAI models. © 2023, The Author(s).

关键词： APT Boosting Cyber-security Explainability Machine learning XAI

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Cost and Storage Optimization of Video Streaming in Cloud Environments

Deep Learning Approach for Cost and Storage Optimization of ...

引用

IEEE International Conference on Smart Cloud (SmartCloud)

作者： Mahmoud Darwich Taghreed Alghamdi Magdy Bayoumi Department of Mathematics and Computer Science University of Mount Union Alliance OH University of Ontario Institute of Technology Oshawa ON Canada Department of Electrical and Computer Engineering University of Louisiana Lafayette LA

As the demand for video streaming continues to rise, cloud computing has become a vital infrastructure for delivering reliable and scalable services. However, cost management and storage allocation pose significant challenges in this context. This paper presents a novel application of deep learning techniques to optimize cost and storage utilization in cloud environments for video streaming. The proposed framework leverages a hybrid deep learning model that combines Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. CNNs are employed for pattern recognition, allowing the model to identify recurring patterns in resource usage. LSTM networks, on the other hand, specialize in sequence prediction and enable accurate forecasting of future resource demands. By analyzing historical video views, the model can make precise predictions about future resource needs. This enables dynamic resource scaling, allowing cloud infrastructure to be efficiently allocated in response to streaming demands. Moreover, the framework addresses storage optimization challenges by incorporating deep learning insights into data placement, replication, and retrieval strategies. The results demonstrate significant improvements in cost efficiency and storage utilization, with cost reductions ranging from 15% to 20% compared to state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Enabled Efficient Storage and Retrieval of Video Streams in the Cloud

Deep Learning-Enabled Efficient Storage and Retrieval of Vid...

引用

IEEE International Conference on Smart Cloud (SmartCloud)

In recent years, the rapid growth of video data has presented challenges for efficient storage and retrieval in cloud-based systems. This research proposes a novel approach that utilizes machine learning techniques to address these challenges. The objective is to develop a robust framework that optimizes storage utilization, enhances retrieval efficiency, and maintains video quality with minimal latency. Machine learning algorithms are employed for tasks such as video compression, content analysis, and metadata extraction, enabling effective storage and retrieval mechanisms. The framework leverages advanced video analytics algorithms to extract relevant features, incorporating them into the storage and retrieval process for efficient indexing and organization of video content. The framework adapts to changing workloads and dynamically allocates resources for optimal performance in cloud environments. Extensive experiments and comparisons with existing methods validate the proposed framework, demonstrating significant improvements in storage utilization, retrieval performance, and scalability. Specifically, our framework achieves an average improvement of 25% in storage efficiency compared to another method. It also demonstrates faster retrieval speeds, with an improvement of approximately 10-20%, and achieves higher video quality ratings, with an improvement of approximately 10-20% compared to existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Constrained Motion Planning Transformers Using Learned Sampling Dictionaries

arXiv

引用

arXiv 2023年

作者： Johnson, Jacob J. Qureshi, Ahmed H. Yip, Michael C. Electrical and Computer Engineering Department University of California San Diego La Jolla CA United States Department of Computer Science Purdue University West LafayetteIN United States

Constrained robot motion planning is a ubiquitous need for robots interacting with everyday environments, but it is a notoriously difficult problem to solve. Many sampled points in a sample-based planner need to be rejected as they fall outside the constraint manifold, or require significant iterative effort to correct. Given this, few solutions exist that present a constraint-satisfying trajectory for robots, in reasonable time and of low path cost. In this work, we present a transformer-based model for motion planning with task space constraints for manipulation systems. Vector Quantized-Motion Planning Transformer (VQ-MPT) is a recent learning-based model that reduces the search space for unconstrained planning for sampling-based motion planners. We propose to adapt a pre-trained VQ-MPT model to reduce the search space for constraint planning without retraining or finetuning the model. We also propose to update the neural network output to move sampling regions closer to the constraint manifold. Our experiments show how VQ-MPT improves planning times and accuracy compared to traditional planners in simulated and real-world environments. Unlike previous learning methods, which require task-related data, our method uses pre-trained neural network models and requires no additional data for training and finetuning the model making this a one-shot process. We also tested our method on a physical Franka Panda robot with real-world sensor data, demonstrating the generalizability of our algorithm. We anticipate this approach to be an accessible and broadly useful for transfering learned neural planners to various robotic-environment interaction scenarios. Copyright © 2023, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Lifelong Robot Edutainment based on Self-Efficacy 5

Lifelong Robot Edutainment based on Self-Efficacy

引用

5th IEEE International Conference on Cybernetics, CYBCONF 2021

作者： Kaburagi, Rino Ishimaru, Yudai Chin, Wei Hong Yorita, Akihiro Kubota, Naoyuki Egerton, Simon Tokyo Metropolitan University Graduate School of Systems Design Tokyo Japan La Trobe University Department of Computer Science and Information Technology VIC Australia

ISBN: (纸本)9781665403207

As the importance of lifelong learning and recurrent education has been emphasized in recent years, it can be argued that people must study for the rest of their lives. Many people, however, find it difficult to engage in and maintain learning behavior, and adequate learning support is required for people to participate in and maintain learning. We developed a learning support system based on the learner's self-efficacy by the robot partner and explored its utility in this study to create an efficient learning support system by a robot partner. As a result, the proposed method's effectiveness was demonstrated by the fact that the proposed learning support system increased the learner's self-efficacy. © 2021 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

MSKI-Net: Towards modality-specific knowledge interaction for glioma survival prediction

MSKI-Net: Towards modality-specific knowledge interaction fo...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Ran Su Jin Xiao Hui Cui Ping Xuan Xikang Feng Leyi Wei Qiangguo Jin School of Computer Software College of Intelligence and Computing Tianjin University Tianjin China Department of Computer Science and Information Technology La Trobe University Melbourne Australia Department of Computer Science School of Engineering Shantou University China School of Software Northwestern Polytechnical University China AIDD Faculty of Applied Science Macao Polytechnic University Macao SAR China School of Information Xiamen University Xiamen China Yangtze River Delta Research Institute of Northwestern Polytechnical University Taicang China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Gliomas hold a prominent position in neurooncology due to their high malignancy and poor survival rates. Accurately predicting the prognosis and survival risk of glioma patients is crucial for clinical treatment. Recent advances in survival prediction methods emphasize the importance of integrating complementary information from diverse modalities while neglecting the significant modality gap between pathological images and genomic data. To address this issue, we propose a modality-specific knowledge interaction network (MSKI-Net), which integrates whole slide images (WSI), RNA-Seq gene expression data, and copy number variation (CNV) data for glioma survival analysis. The MSKI-Net consists of a modality-specific feature enhancement (MSFE) module, a modality-interactive cross-attention (MICA) module, and a modality-specific knowledge-guided representation learning (MSKR) module. The three modules collaborate by complementing modality-specific features with modality-agnostic knowledge to improve the learning capability of MSKI-Net. Furthermore, we construct a dataset named TCGA mm , which combines WSI, RNA-Seq, and CNV data from The Cancer Genome Atlas (TCGA) to address the issue of data scarcity. Extensive experiments demonstrate that MSKI-Net achieves superior performance in predicting the survival risk of glioma cancer.

关键词： Knowledge engineering Representation learning Pathology Genomics Prediction methods Data models Gene expression Bioinformatics Prognostics and health management Cancer

来源：评论

学校读者我要写书评

暂无评论

Extracting Stress-Related EEG Patterns from Pre-Sleep EEG for Forecasting Slow-Wave Sleep Deficiency

引用

IEEE Transactions on Neural Systems and Rehabilitation engineering 2024年 32卷 1817-1827页

作者： Su, Cheng-Hua Ko, Li-Wei Jung, Tzyy-Ping Onton, Julie Tzou, Shey-Cherng Juang, Jia-Chi Hsu, Chung-Yao Institute of Bioinformatics and Systems Biology National Yang Ming Chiao Tung University Hsinchu300 Taiwan Institute of Electrical and Control Engineering National Yang Ming Chiao Tung University Hsinchu300 Taiwan Kaohsiung Medical University Drug Development and Value Creation Research Center Department of Biomedical Science and Environmental Biology Kaohsiung807 Taiwan University of California San Diego Swartz Center for Computational Neuroscience La Jolla CA92093 United States National Yang Ming Chiao Tung University Department of Computer Science Hsinchu300 Taiwan University of California San Diego Institute for Neural Computation La Jolla CA92093 United States National Yang Ming Chiao Tung University Department of Biological Science and Technology Hsinchu300 Taiwan Kaohsiung Medical University Hospital Sleep Disorders Center Department of Neurology Kaohsiung807 Taiwan Kaohsiung Medical University College of Medicine Department of Neurology Kaohsiung807 Taiwan

Sleep is vital to our daily activity. lack of proper sleep can impair functionality and overall health. While stress is known for its detrimental impact on sleep quality, the precise effect of pre-sleep stress on subsequent sleep structure remains unknown. This study introduced a novel approach to study the pre-sleep stress effect on sleep structure, specifically slow-wave sleep (SWS) deficiency. To achieve this, we selected forehead resting EEG immediately before and upon sleep onset to extract stress-related neurological markers through power spectra and entropy analysis. These markers include beta/delta correlation, alpha asymmetry, fuzzy entropy (FuzzEn) and spectral entropy (SpEn). Fifteen subjects were included in this study. Our results showed that subjects lacking SWS often exhibited signs of stress in EEG, such as an increased beta/delta correlation, higher alpha asymmetry, and increased FuzzEn in frontal EEG. Conversely, individuals with ample SWS displayed a weak beta/delta correlation and reduced FuzzEn. Finally, we employed several supervised learning models and found that the selected neurological markers can predict subsequent SWS deficiency. Our investigation demonstrated that the classifiers could effectively predict varying levels of slow-wave sleep (SWS) from pre-sleep EEG segments, achieving a mean balanced accuracy surpassing 0.75. The SMOTE-Tomek resampling method could improve the performance to 0.77. This study suggests that stress-related neurological markers derived from pre-sleep EEG can effectively predict SWS deficiency. Such information can be integrated with existing sleep-improving techniques to provide a personalized sleep forecasting and improvement solution. © 2001-2011 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Embracing Reconfigurable Antennas in the Tri-hybrid MIMO Architecture for 6G and Beyond

arXiv

引用

arXiv 2025年

作者： Castellanos, Miguel Rodrigo Yang, Siyun Chae, Chan-Byoung Heath, Robert W. Department of Electrical Engineering and Computer Science University of Tennessee KnoxvilleTN37996 United States School of Integrated Technology Yonsei University Seoul03722 Korea Republic of Department of Electrical and Computer Engineering University of California La Jolla San DiegoCA92093 United States

Multiple-input multiple-output (MIMO) communication has led to immense enhancements in data rates and efficient spectrum management. The evolution of MIMO, though, has been accompanied by increased hardware complexity and array sizes, causing the system power consumption to increase. Despite past advances in power-efficient hybrid architectures, new solutions are needed to enable extremely large-scale MIMO deployments for 6G and beyond. In this paper, we introduce a novel architecture that integrates low-power reconfigurable antennas with both digital and analog precoding. This tri-hybrid approach addresses key limitations in traditional and hybrid MIMO systems by improving power consumption and adds a new layer for signal processing. We provide an analysis of the proposed architecture and compare its performance with existing solutions, including fully-digital and hybrid MIMO systems. The results demonstrate significant improvements in energy efficiency, highlighting the potential of the tri-hybrid system to meet the growing demands of future wireless networks. We conclude the paper with a summary of design and implementation challenges, including the need for technological advancements in reconfigurable array hardware and tunable antenna parameters. © 2025, CC BY.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

UAV-assisted Intelligent IoT Service Provisioning in Infrastructure-less Environments

UAV-assisted Intelligent IoT Service Provisioning in Infrast...

引用

Artificial Intelligence of Things (AIoT), IEEE Annual Congress on

作者： Qiushi Zheng Zhishu Shen Jiong Jin Zheng Lei Tommy Cheung Wei Xiang School of Science Computing and Engineering Technologies Swinburne University of Technology Melbourne Australia School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China School of Engineering Swinburne University of Technology Melbourne Australia School of Computing Engineering & Mathematical Sciences La Trobe University Melbourne Australia

ISBN: (数字)9798350392296

ISBN: (纸本)9798350392302

With the exponential advancement of beyond fifth/sixth generation (B5G/6G) mobile systems, coupled with the powerful capabilities of the Internet of Things (IoT) driven by artificial intelligence (AI), intelligent information services have become ubiquitous in various environments including the modern smart city. However, providing these intelligent services in infrastructure-less environments, such as remote or rural areas, still presents substantial challenges due to geographical and economic constraints. To address these challenges, we develop an AI-empowered IoT platform for infrastructure-less environments. The platform's reach is extended through non-terrestrial networks (NTNs), which incorporate unmanned aerial vehicles (UAVs) and satellites, thereby ensuring seamless and efficient communication coverage. In order to enhance the efficiency of task allocation, a dual-deep Q-learning (D- DQN) scheme is proposed for task sorting and task allocation, which simplifies decision-making complexity. We establish an experimental environment that simulates the IoT network services in infrastructure-less environments. Extensive experimental results demonstrate that our proposed system delivers superior performance against other baseline methods: it exhibits enhanced energy efficiency, with improvements seen in both task processing ratio and accuracy.

关键词： Satellites Accuracy Q-learning Smart cities Collaboration Energy efficiency Internet of Things

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：