检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Peng, Zengqi Wang, Yubin Han, Xu Zheng, Lei Ma, Jun Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology Guangzhou China Data Science and Analytics Thrust The Hong Kong University of Science and Technology Guangzhou China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology China

Recent advancements in reinforcement learning (RL) demonstrate the significant potential in autonomous driving. Despite this promise, challenges such as the manual design of reward functions and low sample efficiency in complex environments continue to impede the development of safe and effective driving policies. To tackle these issues, we introduce LearningFlow, an innovative automated policy learning workflow tailored to urban driving. This framework leverages the collaboration of multiple large language model (LLM) agents throughout the RL training process. LearningFlow includes a curriculum sequence generation process and a reward generation process, which work in tandem to guide the RL policy by generating tailored training curricula and reward functions. Particularly, each process is supported by an analysis agent that evaluates training progress and provides critical insights to the generation agent. Through the collaborative efforts of these LLM agents, LearningFlow automates policy learning across a series of complex driving tasks, and it significantly reduces the reliance on manual reward function design while enhancing sample efficiency. Comprehensive experiments are conducted in the high-fidelity CARLA simulator, along with comparisons with other existing methods, to demonstrate the efficacy of our proposed approach. The results demonstrate that LearningFlow excels in generating rewards and curricula. It also achieves superior performance and robust generalization across various driving tasks, as well as commendable adaptation to different RL algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

HTPS: Heterogeneous Transferring Prediction System for Healthcare Datasets

arXiv

引用

arXiv 2023年

作者： Syu, Jia-Hao Fojcik, Marcin Lin, Jerry Chun-Wei Cupek, Rafal Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Sciences Bergen Norway Department of Distributed Systems and Informatic Devices Silesian University of Technology Gliwice Poland

Medical internet of things leads to revolutionary improvements in medical services, also known as smart healthcare. With the big healthcare data, data mining and machine learning can assist wellness management and intelligent diagnosis, and achieve the P4-medicine. However, healthcare data has high sparsity and heterogeneity. In this paper, we propose a Heterogeneous Transferring Prediction System (HTPS). Feature engineering mechanism transforms the dataset into sparse and dense feature matrices, and autoencoders in the embedding networks not only embed features but also transfer knowledge from heterogeneous datasets. Experimental results show that the proposed HTPS outperforms the benchmark systems on various prediction tasks and datasets, and ablation studies present the effectiveness of each designed mechanism. Experimental results demonstrate the negative impact of heterogeneous data on benchmark systems and the high transferability of the proposed HTPS. Copyright © 2023, The Authors. All rights reserved.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

M3bunet:Mobile Mean Max Unet for Pancreas Segmentation on Ct-Scans

SSRN

引用

SSRN 2024年

作者： Juwita, Juwita Hassan, Ghulam Mubashar Akhtar, Naveed Datta, Amitava Department of Computer Science and Software Engineering The University of Western Australia Australia School of Computing and Information Systems The University of Melbourne Australia Department of Informatics Syiah Kuala University Banda Aceh Indonesia

Segmenting organs in CT scan images is a necessary process for multiple downstream medical image analysis tasks. Currently, manual CT scan segmentation by radiologists is prevalent, especially for organs like the pancreas, which requires a high level of domain expertise for reliable segmentation due to factors like small organ size, occlusion, and varying shapes. When resorting to automated pancreas segmentation, these factors translate to limited reliable labeled data to train effective segmentation models. Consequently, the performance of contemporary pancreas segmentation models is still not within acceptable ranges. To improve that, we propose M3BUNet, a fusion of MobileNet and U-Net neural networks, equipped with a novel Mean-Max (MM) attention that operates in two stages to gradually segment pancreas CT images from coarse to fine with mask guidance for object detection. This approach empowers the network to surpass segmentation performance achieved by similar network architectures and achieve results that are on par with complex state-of-the-art methods, all while maintaining a low parameter count. Additionally, we introduce external contour segmentation as a preprocessing step for the coarse stage to assist in the segmentation process through image standardization. For the fine segmentation stage, we found that applying a wavelet decomposition filter to create multi-input images enhances pancreas segmentation performance. We extensively evaluate our approach on NIH and MSD pancreas datasets. Our approach demonstrates performance improvement, achieving an average DSC value of up to 89.53±1.82 and IOU score of up to 81.16±0.03 for the NIH, and 88.60 ±1.48 DSC and 79.90±2.19 IOU for the MSD. © 2024, The Authors. All rights reserved.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Multi-channel Convolutional Neural Network for Hate Speech Detection in Social Media 9th

Multi-channel Convolutional Neural Network for Hate Speech D...

引用

9th EAI International Conference on Advancement of science and Technology, ICAST 2021

作者： Abebaw, Zeleke Rauber, Andreas Atnafu, Solomon IT Doctoral Program Addis Ababa University Addis Ababa Ethiopia Institute of Information Systems Engineering Technical University of Vienna Vienna Austria Department of Computer Science Addis Ababa University Addis Ababa Ethiopia

ISBN: (纸本)9783030937089

As online social media content continues to grow, so does the spread of hate speech. Hate speech has devastating consequences unless it is detected and monitored early. Recently, deep neural network-based hate speech detection models, particularly conventional single-channel Convolutional Neural Network (CNN), have achieved remarkable performance. However, the effectiveness of the models depends on the type of language they are trained on and the training data size. We argue that the effectiveness of the models could further be enhanced if we use multi-channel CNN models even for under-resourced languages that have limited training data size. This is because the single-channel CNN might fail to consider the potential effect of multiple channels to generate better features, which is not well investigated for hate speech detection. Therefore, in this work, we explore the use of multi-channel CNN to extract better features from different channels in an end-to-end manner on top of a word2vec embedding layer. Tested on a new small-scale Amharic hate speech dataset containing 2000 annotated social media comments, the experimental results show that the proposed multi-channel CNN model outperforms the single-channel CNN models but underperform from the baseline Support Vector Machine (SVM) with an average F-score of 81.3%, 78.2%, and 92.5% respectively. The finding of the study implies that the proposed MC-CNN model can be used as an alternative solution for hate speech detection using a deep learning approach when dataset scarcity is an issue. © 2022, ICST Institute for computer sciences, Social Informatics and Telecommunications engineering.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Beyond PCA: A Gram-Schmidt Approach to Feature Extraction

Beyond PCA: A Gram-Schmidt Approach to Feature Extraction

引用

Annual Allerton Conference on Communication, Control, and Computing

作者： Bahram Yaghooti Netanel Raviv Bruno Sinopoli Department of Electrical and Systems Engineering Washington University in St. Louis St. Louis MO USA Department of Computer Science and Engineering Washington University in St. Louis St. Louis MO USA

ISBN: (数字)9798331541033

ISBN: (纸本)9798331541040

Linear feature extraction at the presence of nonlinear dependencies among the data is a fundamental challenge in unsupervised learning. We propose using a Gram-Schmidt (GS) type orthogonalization process over function spaces in order to detect and remove redundant dimensions. Specifically, by applying the GS process over a family of functions which presumably captures the nonlinear dependencies in the data, we construct a series of covariance matrices that can either be used to identify new large-variance directions, or to remove those dependencies from the principal components. In the former case, we provide information-theoretic guarantees in terms of entropy reduction. In the latter, we prove that under certain assumptions the resulting algorithms detect and remove nonlinear dependencies whenever those dependencies lie in the linear span of the chosen function family. Both proposed methods extract linear features from the data while removing nonlinear redundancies. We provide simulation results on synthetic and real-world datasets which show improved performance over state-of-the-art feature extraction algorithms.

关键词： Numerical analysis Simulation Redundancy Linear algebra Feature extraction Entropy Data mining Unsupervised learning Principal component analysis Information theory

来源：评论

学校读者我要写书评

暂无评论

Sign Language to Text Conversion using RNN-LSTM

Sign Language to Text Conversion using RNN-LSTM

引用

Data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： Amutha Seviappan Kothai Ganesan Anna Anbumozhi A. Sameer Reddy B. Vamsi Krishna D.Sampath Reddy Computer Science and Engineering Kalasalingam Academy of Research and Education Virudhunagar India Department of CSE (AIML) KPR Institute of Engineering and Technology Coimbatore India Department of Data Science and Business systems SRM Institute of Science and Technology Chennai India

The speech-impaired community only uses sign language; the rest of society interacts verbally. Our research intends to fill this communication gap by proposing a state-of-the-art method for comprehending both static and moving signs in Indian Sign Language and translating them into text. Data is collected, pre-processed, and hand recognition is finished using media pipe holistic before being categorized into suitable speech output. Because LSTM networks can develop long-term dependencies, they were investigated and employed for the classification of gesture data. The constructed model exhibited a 100% accuracy rate while categorizing 26 motions, highlighting the usefulness of LSTM-based neural networks for sign language translation. For those who are deaf or dumb, translating sign language into text allows them to interact with each other or with people in the general public by using hand gestures. According to a survey we conducted on sign language comprehension, most people are unable to identify the hand gestures and mode of communication used by sign language users. After hearing about all the difficulties, they have communicating with regular people, we developed this initiative on sign language transcription. The community of deaf and mute people will benefit from this initiative because it explains the meaning of each hand gesture and uses hand gestures to communicate various signs. In this project, hand gestures were recognized using a pipeline method called media pipe, and training and testing were carried out using deep learning techniques. Sign language was then converted to text format.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Observer-Based Control of Second-Order Multi-vehicle systems in Bearing-Persistently Exciting Formations

arXiv

引用

arXiv 2024年

作者： Tang, Zhiqi Fidan, Baris Johansson, Karl H. Mårtensson, Jonas Hamel, Tarek Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology StockholmSE-10044 Sweden Mechanical and Mechatronics Engineering Department University of Waterloo ON Canada France

This paper proposes an observer-based formation tracking control approach for multi-vehicle systems with second-order motion dynamics, assuming that vehicles' relative or global position and velocity measurements are unavailable. It is assumed that all vehicles are equipped with sensors capable of sensing the bearings relative to neighboring vehicles and only one leader vehicle has access to its global position. Each vehicle estimates its absolute position and velocity using relative bearing measurements and the estimates of neighboring vehicles received over a communication network. A distributed observer-based controller is designed, relying only on bearing and acceleration measurements. This work further explores the concept of the Bearing Persistently Exciting (BPE) formation by proposing new algorithms for bearing-based localization and state estimation of second-order systems in centralized and decentralized manners. It also examines conditions on the desired formation to guarantee the exponential stability of distributed observer-based formation tracking controllers. In support of our theoretical results, some simulation results are presented to illustrate the performance of the proposed observers as well as the observer-based tracking controllers. © 2024, CC BY-NC-ND.

关键词： Acceleration measurement

来源：评论

学校读者我要写书评

暂无评论

Smart Water Flow Monitoring and Theft Detection System using IoT 1

Smart Water Flow Monitoring and Theft Detection System using...

引用

1st IEEE International Conference on Automation, Computing and Renewable systems, ICACRS 2022

作者： Samudrala, Varakumari Yeruva, Ajay Reddy Jayapal, N. Vijayakumar, T. Rajkumar, M. Razia, Shaik Andhra Pradesh Agiripalli521212 India Department of IP Engineering Ritchie Bros. Auctioneers 5667 Gibraltar Dr Ste 200 PleasantonCA94588 United States Department of Electronics and Communication Engineering Kongunadu College of Engineering and Technology Tamil Nadu Trichy621215 India Department of Computer Science and Business Systems Sri Eshwar College of Engineering Tamil Nadu Coimbatore641202 India School of Information Technology & Engineering VIT University Vellore Campus India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522302 India

ISBN: (纸本)9781665460842

Water is an essential and crucial resource in the world. Without water, there will not be any organisms, flora, and fauna on the planet. Water is most important for living organisms like humans, plants, and animals. Earth is covered by 71% of water bodies and 29% is covered by land. The human body is made up of nearly 70% of water. There is no life when there is no water. So, people should not waste water and use it accordingly. For domestic use, people store the water in their home tank which flows from the corporate tank or in a bore well. Either of the two there will be a water flow when the home tank is filled which leads to water wastage and there will also be a wastage of water when there is a leakage of water or theft of water during the flow of water to the home tank. To control and avoid the overflow of water, a smart water flow monitoring system and theft detection are implemented by using the Internet of Things (IoT). Sensors, NodeMCU, Solenoid valve, and Global System for Mobile communication (GSM) are used to implement this system. When there is a flow above the threshold value and leakage or theft, the cloud will send the alert message to the user. © 2022 IEEE

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Study on Exploring and Exploiting the High-dimensional Design Space for Analog Circuit Design Automation : (Invited Paper)

A Study on Exploring and Exploiting the High-dimensional Des...

引用

Asia and South Pacific Design Automation Conference

作者： Ruiyu Lyu Yuan Meng Aidong Zhao Zhaori Bi Keren Zhu Fan Yang Changhao Yan Dian Zhou Xuan Zeng Microelectronics Department State Key Lab of Integrated Chips and Systems Fudan University Shanghai China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong China Department of Electrical Engineering University of Texas at Dallas USA

The escalated intricacy of analog circuits, compounded by the high-dimensional nature of the design space, introduces complexities in optimizing circuit performance. Since the evaluation cost, often through circuit simulation, is resource-intensive and time-consuming, it is crucial to obtain a feasible design with a decent Figure of Merit (FOM) value within a limited simulation budget. In this study, we conduct an in-depth review and analysis of cutting-edge exploration and exploitation techniques developed to address the intricacies encountered in analog circuit design automation. Moreover, to enable algorithmic comparisons and advance the state of the field, we provide benchmarks encompassing analog circuit netlists with high-dimensional design variables, which empower researchers to rigorously assess and refine their optimization algorithms, leading to enhanced efficacy and novel developments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Open-Source Heterogeneous SoCs for AI The PULP Platform Experience

arXiv

引用

arXiv 2024年

作者： Conti, Francesco Garofalo, Angelo Rossi, Davide Tagliavini, Giuseppe Benini, Luca The Department of Electrical Electronic and Information Engineering University of Bologna Bologna40123 Italy The Department of Computer Science and Engineering University of Bologna Bologna40123 Italy The Integrated Systems Laboratory ETH Zürich Zurich8005 Switzerland

Since 2013, the PULP (Parallel Ultra-Low Power) Platform project has been oneof the most active and successful initiatives in designing research IPs andreleasing them as open-source. Its portfolio now ranges from processor cores tonetwork-on-chips, peripherals, SoC templates, and full hardware *** this article, we focus on the PULP experience designing heterogeneous AIacceleration SoCs - an endeavour encompassing SoC architecture definition;development, verification, and integration of acceleration IPs;front- andback-end VLSI design;testing;development of AI deployment software. Copyright © 2024, The Authors. All rights reserved.

关键词： System-on-chip

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：