检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Jipeng Kang Zhibin Zhang Yajie Liang Xu Chen Key Laboratory of Wireless Networks and Mobile Computing School of Computer Science Inner Mongolia University Hohhot China Engineering Research Center of Ecological Big Data School of Computer Science Inner Mongolia University Hohhot China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

When using deep reinforcement learning algorithms for reactive navigation, it is common to encounter situations where the agent gets stuck in a local optimum. In autonomous exploration without any prior knowledge, the exploration of environments is often suboptimal. Moreover, the agricultural robots performing tasks in farm fields face even more great challenges. To address this, we propose an Agricultural Robot Autonomous Exploration System (ARAES) that uses deep reinforcement learning algorithms to drive the robot to explore unknown farm environments. The whole system consists of a Global Path Planning (GPP) module and a Local Path Planning (LPP) module. The GPP module utilizes path points acquired along the heading direction in the environment and selects waypoints based on the collected path points to guide the robot towards the global goal, effectively alleviating local optima issues in reactive navigation. The LPP module learns local navigation motion policies in a simulated environment. It incorporates the learned policies into the motion planning stack, enabling the robot to move towards global goals based on the path points and way points. The advantages of the ARAES system are its autonomy and real-time performance, allowing the robot to operate without needing to know detailed prior information about the environment and enabling real-time adjustments of navigation policies according to current environments. Meanwhile, ARAES can construct maps in real-time as the robot moves in the environment. Experiments demonstrate that ARAES is advantageous because it does not rely on complex static and dynamic environment maps or prior information and delivers superior performance compared to other methods.

关键词： Agricultural robots Simultaneous localization and mapping Navigation Production Deep reinforcement learning Real-time systems Path planning

来源：评论

学校读者我要写书评

暂无评论

Scalable Optimal Margin Distribution Machine

arXiv

引用

arXiv 2023年

作者： Wang, Yilin Cao, Nan Zhang, Teng Shi, Xuanhua Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

Optimal margin Distribution Machine (ODM) is a newly proposed statistical learning framework rooting in the latest margin theory, which demonstrates better generalization performance than the traditional large margin based counterparts. However, it suffers from the ubiquitous scalability problem regarding both computation time and memory storage as other kernel methods. This paper proposes a scalable ODM, which can achieve nearly ten times speedup compared to the original ODM training method. For nonlinear kernels, we put forward a novel distribution-aware partition method to make the local ODM trained on each partition be close and converge fast to the global one. When linear kernel is applied, we extend a communication efficient SVRG method to accelerate the training further. Extensive empirical studies validate that our proposed method is highly computational efficient and almost never worsen the generalization. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

An Extensive Study on Pretrained Models for Natural Language Processing Based on Transformers

An Extensive Study on Pretrained Models for Natural Language...

引用

2022 International Conference on Electronics and Renewable Systems, ICEARS 2022

作者： Ramprasath, M. Dhanasekaran, K. Karthick, T. Velumani, R. Sudhakaran, P. Srm Institute of Science and Technology Department of Data Science and Business Systems School of Computing TamilNadu Chennai India Department of Computer Science and Engineering Andhra Pradesh Madhrawada India Srm Trp Enginerring College Department of Computer Science and Engineering Tamil Nadu Trichy India

ISBN: (纸本)9781665484251

In recent years, Pretraining Language Models based on Transformers -Natural Language Processing (PLMT-NLP) have been highly successful in nearly every NLP task. In the beginning, Generative Pre-trained model-based Transformer, BERT- Bidirectional Encoder model Representations using Transformers was used to develop these models. Models constructed on transformers, Self-supervise knowledge acquiring, and transfer learning establish the foundation of these designs. Transformed-based pre-trained models acquire common linguistic illustrations from vast amounts of textual information through self-supervised model and apply this information to downstream tasks. To eliminate the need to retrain downstream models, these models provide a solid foundation of knowledge. In this paper, the enhanced learning on PLMT-NLP has been discussed. Initially, a quick introduction to self-supervised learning is presented, then diverse core concepts used in PLMT-NLP are explained. Furthermore, a list of relevant libraries for working with PLMT-NLP has been provided. Lastly, the paper discusses about the upcoming research directions that will further improve these models. Because of its thoroughness and relevance to current PLMT-NLP developments, this survey study will positively serve as a valuable resource for those seeking to understand both basic ideas and new developments better. © 2022 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

FaceCaps for facial expression recognition

FaceCaps for facial expression recognition

引用

作者： Wu, Fangyu Pang, Chaoyi Zhang, Bailing College of Computer Science and Technology Zhejiang University HangzhouZhejiang China School of Computing and Data Engineering NingboTech University NingboZhejiang China

Facial expression recognition (FER) is a significant research task in the computer vision field. In this paper, we present a novel network FaceCaps for facial expression recognition with the following novel characteristics: an embedding structure based on a Capsule network which encodes relative spatial relationships between features;incorporates the feature polymerization property of FaceNet, thus offering a more efficient approach to discriminate complex facial expressions;a target reconstruction loss as a better regularization term for Capsule networks. Experimental results on both lab-controlled datasets (CK+) and real-world databases (RAF-DB and SFEW 2.0) demonstrate that the method significantly outperforms the state-of-the-art. © 2021 John Wiley & Sons, Ltd.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

When Artificial Intelligence meets Navarasas - Facial Expression Classification in Kathakali Using DSFD and CNN

When Artificial Intelligence meets Navarasas - Facial Expres...

引用

IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems (SPICES)

作者： Ganesh Neelakanta Iyer Nattapong Saengarunvong Minh Hien Le Department of Computer Science School of Computing National University of Singapore Singapore Department of Computer Engineering Faculty of Engineering King Mongkut’s University of Technology Thonburi Bangkok Thailand Department of Computer and Data Sciences Case School of Engineering Case Western Reserve University Cleveland Ohio USA

ISBN: (数字)9798350376135

ISBN: (纸本)9798350376142

Kathakali, an ancient art form that dates back to the 17th century, is renowned for its intricate hand gestures, dance movements, musical accompaniment, elaborate costumes, and makeup. Mastering such an art form is a challenge even for the most dedicated enthusiasts, given its unconventional methods of expression. However, with current advanced technology, we can use this to aid the learning of unfamiliar subjects by classifying factors to help the new learners. In this paper, we focus on classifying one aspect of the play, which is the expressions on the actor’s face given a picture using computer vision methods. To achieve the final model, we use a combination of Dual Shot Face Detector (DSFD) and Convolution Neural Network (CNN) and finally tuning up the epochs of the training process. With our dataset, the proposed model reached an accuracy of 93% among nine classes. This project hopes to introduce Kathakali to a wider audience and facilitate the learning process of this art form.

关键词： Training Accuracy Art Computational modeling Signal processing algorithms Detectors data models Faces Tuning Testing

来源：评论

学校读者我要写书评

暂无评论

Adaptive Cleaning in Manufacturing: A Decision Tree Model for Efficient Factory Sanitation 4

Adaptive Cleaning in Manufacturing: A Decision Tree Model fo...

引用

4th International Conference on Innovative Practices in Technology and Management, ICIPTM 2024

作者： Arulprakash, M. Raman, Ramakrishnan Gokhale, Atul A Saravanan, K. Ishwarya, M.V. Sujatha, S. Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur Chenagalpattu Tamil Nadu Chennai India Symbiosis Institute of Business Maharashtra Pune India Symbiosis School of Culinary Arts Maharashtra Pune India R.M.D. Engineering College Department of Information Technology Tamil Nadu Chennai India Agni College of Technology Artificial Intelligence and Data Science Department Tamil Nadu Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350307757

Industrial cleanliness is crucial in production settings, and this system offers a novel way to use Internet of Things (IoT) technology to strengthen this practice. The suggested solution uses a Decision Tree (DT) model and real-time data received from IoT sensors placed strategically around the facility to enable adaptive enhancements to cleaning processes. This system of sensors keeps tabs on a number of variables, including manufacturing schedules, environmental factors, and circulation. In real-time, the DT model may use this data to optimize cleaning locations, durations, and procedures, cutting down on wasteful downtime and resource usage without compromising cleanliness. When contrasted with conventional static cleaning methods, the adaptive cleaning system shows considerable gains in both sanitation efficiency and resource occupancy. Improving cleaning using IoT technology makes it more responsive and smart, which in turn makes production more efficient and less detrimental to the environment. It explains how the IoT and DT models worked together to make manufacturing processes more adaptable, under the lens of industrial hygiene. © 2024 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Online Doctor Recommendation Method for Doctor-Patient Interaction data and Doctor Attributes

Online Doctor Recommendation Method for Doctor-Patient Inter...

引用

International Conference on Application of Information and Communication Technologies (AICT)

作者： Chen Yi Li Chusong Tang Minglu Shanghai Institution of Computing Technology Ltd. Shanghai China School of Computer and Information Engineering Shanghai Polytechnic University Distributed Computing and Data Security Shanghai China Shanghai Maritime University Shanghai China

At present, LDA topic model, Word2Vec model and knowledge graph have been used to recommend doctors for online consultation, and have achieved certain results. However, the single word vector model will lead to some deficiencies in the recommendation results. In online consultation, patients have short questions and doctors have long answers, which is difficult to deal with uniformly. Therefore, this paper combines Sentence BERT sentence vector model, ELMO word vector model and doctor attribute model to build a set of combined recommendation model for intelligent doctor recommendation. In the empirical study, this paper chooses a large number of test patients as the research object. The results show that compared with the single word vector model, the combined recommendation model proposed in this paper is better in the accuracy rate, mean reciprocal rank and coverage rate of doctor recommendation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Beam Alignment for IEEE 802.11be Powered by Task Oriented Indoor UWB Localization

Beam Alignment for IEEE 802.11be Powered by Task Oriented In...

引用

IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

作者： Semih Serhat Karakaya Talip Tolga Sarı Elif Ak Berk Canberk Gökhan Seçinti Department of Computer Engineering Istanbul Technical University Istanbul Turkey BTS Group Istanbul Turkey School of Computing Engineering and The Built Environment Edinburgh Napier University UK Department of Artificial Intelligence and Data Engineering Istanbul Technical University Istanbul Turkey

ISBN: (数字)9798350362244

ISBN: (纸本)9798350362251

Coordinated beamforming is one of the crucial improvements for WiFi7. However, to provide sufficient Quality of Service, the corresponding beams have to be aligned accurately. Conventional approaches search for optimal beams in the available codebook to align the beams. However, this introduces considerable delays because of high search space. To address this issue, we utilize Ultra-Wide-Band (UWB) assisted localization to swiftly adjust the beams for users to provide accurate beams. Then by using Received Signal Strength Indicator (RSSI) and state estimation error of the Kalman filter in the position system, we propose a task oriented beamforming alignment system that uses UWB assisted localization only when necessary. Our approach improves beamforming gain by 11.6% compared to conventional beam scanning approaches. On top of this, the proposed solution improves communication effectiveness by 55.6% against naive UWB localization-assisted beam alignment.

关键词： Location awareness Communication effectiveness Array signal processing Ultra wideband communication Quality of service Delays Received signal strength indicator Kalman filters State estimation Land mobile radio

来源：评论

学校读者我要写书评

暂无评论

X-CBA: Explainability Aided CatBoosted Anomal-E for Intrusion Detection System

X-CBA: Explainability Aided CatBoosted Anomal-E for Intrusio...

引用

IEEE International Conference on Communications (ICC)

作者： Kiymet Kaya Elif Ak Sumeyye Bas Berk Canberk Sule Gunduz Oguducu Department of Computer Engineering Istanbul Technical University Istanbul Turkey BTS Group Istanbul Turkey School of Computing Engineering and Built Environment Edinburgh Napier University Edinburgh Department of Artificial Intelligence and Data Engineering Istanbul Technical University Istanbul Turkey

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

The effectiveness of Intrusion Detection Systems (IDS) is critical in an era where cyber threats are becoming increasingly complex. Machine learning (ML) and deep learning (DL) models provide an efficient and accurate solution for identifying attacks and anomalies in computer networks. However, using ML and DL models in IDS has led to a trust deficit due to their non-transparent decision-making. This transparency gap in IDS research is significant, affecting confidence and accountability. To address, this paper introduces a novel Explainable IDS approach, called X-CBA, that leverages the structural advantages of Graph Neural Networks (GNNs) to effectively process network traffic data, while also adapting a new Explainable AI (XAI) methodology. Unlike most GNN-based IDS that depend on labeled network traffic and node features, thereby overlooking critical packet-level information, our approach leverages a broader range of traffic data through network flows, including edge attributes, to improve detection capabilities and adapt to novel threats. Through empirical testing, we establish that our approach not only achieves high accuracy with 99.47% in threat detection but also advances the field by providing clear, actionable explanations of its analytical outcomes. This research also aims to bridge the current gap and facilitate the broader integration of ML/DL technologies in cybersecurity defenses by offering a local and global explainability solution that is both precise and interpretable.

关键词： Accuracy Explainable AI Computational modeling Image edge detection Intrusion detection Telecommunication traffic Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A YANG-Aided Unified Strategy for Black Hole Detection for Backbone Networks

A YANG-Aided Unified Strategy for Black Hole Detection for B...

引用

IEEE International Conference on Communications (ICC)

作者： Elif Ak Kiymet Kaya Eren Ozaltun Sule Gunduz Oguducu Berk Canberk Department of Computer Engineering Istanbul Technical University Istanbul Turkey BTS Group Istanbul Turkey Department of Artificial Intelligence and Data Engineering Istanbul Technical University Istanbul Turkey School of Computing Engineering and Built Environment Edinburgh Napier University Edinburgh

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Despite the crucial importance of addressing Black Hole failures in Internet backbone networks, effective detection strategies in backbone networks are lacking. This is largely because previous research has been centered on Mobile Ad-hoc Networks (MANETs), which operate under entirely different dynamics, protocols, and topologies, making their findings not directly transferable to backbone networks. Furthermore, detecting Black Hole failures in backbone networks is particularly challenging. It requires a comprehensive range of network data due to the wide variety of conditions that need to be considered, making data collection and analysis far from straightforward. Addressing this gap, our study introduces a novel approach for Black Hole detection in backbone networks using specialized Yet Another Next Generation (YANG) data models with Black Hole-sensitive Metric Matrix (BHMM) analysis. This paper details our method of selecting and analyzing four YANG models relevant to Black Hole detection in ISP networks, focusing on routing protocols and ISP-specific configurations. Our BHMM approach derived from these models demonstrates a 10% improvement in detection accuracy and a 13% increase in packet delivery rate, highlighting the efficiency of our approach. Additionally, we evaluate the Machine Learning approach leveraged with BHMM analysis in two different network settings, a commercial ISP network, and a scientific research-only network topology. This evaluation also demonstrates the practical applicability of our method, yielding significantly improved prediction outcomes in both environments.

关键词： Measurement Network topology Machine learning Ad hoc networks Routing protocols Topology Internet

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：