检索结果-内蒙古大学图书馆

28th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2023

作者： Ghinea, Liliana Maria Miron, Mihaela Ratnaweera, Harsha Electrical Engineering and Electronics Faculty of Automation Computers Department of Automatic Control and Electrical Engineering Department Galaţi Romania Computers Electrical Engineering and Electronics Faculty of Automation Department of Computer Science and Information Technology Galaţi Romania Norwegian University of Life Sciences Faculty of Science and Technology Oslo Norway

ISBN: (纸本)9798350339918

Fault diagnosis in wastewater treatment plants (WWTPs) is important to protect communities and ecosystems from toxic elements discharged into water. In this sense, fault identification of sensors plays an important role as they are the key components of the water plants control, especially because environmental legislation is very strict when referring to failures or anomalies in WWTPs. This paper analyzes the performances of two Deep Learning models, a Feedforward Neural Network (FFNN) and a 1D Convolution Neural Network (1DCNN) for identifying five operating states of the dissolved oxygen (DO) sensor: normal and faulty (bias, stuck, spike and precision degradation faults). The experiments were conducted on the Benchmark Simulator Model No 2 (BSM2) developed by the IWA Task Group. The performance of the Deep Learning (DL) classifiers was evaluated via accuracy, precision, recall, and F1-score metrics. The best overall classification accuracy was obtained by FFNN, 98.32% for training and 98.30% for testing. © 2023 IEEE.

关键词： Wastewater treatment

来源：评论

学校读者我要写书评

暂无评论

Distance Estimation of Fixed Objects in Driving Environments 9

Distance Estimation of Fixed Objects in Driving Environments

引用

9th Scholar's Yearly Symposium of Technology, engineering and Mathematics, SYSTEM 2023

作者： Leporoni, Giorgio Ponzi, Valerio Pro, Francesco Napoli, Christian Department of Computer Control and Management Engineering Sapienza University of Rome Via Ariosto 25 Roma00185 Italy Institute for Systems Analysis and Computer Science Italian National Research Council Via dei Taurini 19 Roma00185 Italy

Autonomous driving is a highly relevant topic today, particularly among major car manufacturers attempting to lead in technological innovation and enhance driving safety. An autonomous vehicle must possess the capability to sense its environment and navigate without human intervention. Thus, it serves as both a driver support system and, in some cases, a substitute. A crucial aspect involves identifying the positions of pedestrians, traffic signs, traffic lights, and other vehicles while computing distances from them. This enables the vehicle to emit alerts to the driver in potentially dangerous situations, such as impending obstacles due to external factors or driver distraction. In this paper, we introduce an approach for identifying traffic signs and determining the distance from them. Our method utilizes the YOLOv4 network for identification and a customized network for distance computation. This integration of AI technologies facilitates the timely detection of hazards and enables proactive alert mechanisms, thereby advancing the capabilities of autonomous vehicles and enhancing driving safety. © 2023 Copyright for this paper by its authors.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Pruning Dynamic Group Convolution with Static Substitute

Pruning Dynamic Group Convolution with Static Substitute

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Che, Jieyong Wang, Chong Chen, Weiwei Dai, Xinmiao Wang, Jun Wu, Jiafei Ningbo University Faculty of Electrical Engineering and Computer Science China School of Information and Control Engineering China University of Mining and Technology China SenseTime Research China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Deep learning networks are gradually deployed in edge applications, such as phones and cameras, which has a restriction of the computational resources. Thus, to improve the computational efficiency, numerous types of group convolution-based frameworks have been studied, including the dynamic group convolution (DGC). However, it is worth noting that sometimes the same channels are selected in different dynamic heads in DGC, which violates its original intention. It indicates the number of dynamic heads exceeds what is really needed. In this paper, a novel model by pruning dynamic group convolution with static substitute is proposed. Specifically, those channels pruned in the dynamic head can be reselected in the static head of the group convolution in the proposed model. In addition, a new polarization regularization is introduced to prune more useless channels with less accuracy loss. The experiment results on two image classification benchmarks (CIFAR-I00 and TinylmageNet-200) show promising performance. © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Energy Harvesting Integrated Sensor Node Architecture for Sustainable IoT Networks 5th

Energy Harvesting Integrated Sensor Node Architecture for S...

引用

5th International Conference on Advances in Distributed Computing and Machine Learning, ICADCML 2024

作者： Gopikrishnan, S. Kokila, M. Rivera, Marco Wheeler, Patrick School of Computer Science and Engineering VIT-AP University Andhra Pradesh Amaravati522237 India Power Electronics Machines and Control PEMC Research Group University of Nottingham Nottingham United Kingdom Universidad de Talca Curicó Chile

ISBN: (纸本)9789819735228

Internet of Things (IoT) is a life changing technology which is build on various devices which are connected to the Internet. Wireless sensor nodes (WSN) is one of such devices which plays a major role in deploying IoT in large scale of real-time even monitoring applications. But the energy limitations of those sensor nodes limits the features of IoT networks. Hence improving the energy limitations in WSN plays a vital role in last decade. This chapter presents the possibilities of enhance the energy limitations of sensor nodes with renewable energy resources. The proposed integrated architecture of this proposed model discusses the implementation of sensor node with flexible solar energy harvester module, multi mode communication capability and multi sensor data module. The special contribution in this chapter includes the hardware specification with budget analysis, sleep-awake strategy to effective use of energy and maximum possible data collection from the environment. The novelty and improvement of the proposed model has been proved with mathematical model as well as the real-time measurements from the prototype. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

NOVEL INSTANCE MINING WITH PSEUDO-MARGIN EVALUATION FOR FEW-SHOT OBJECT DETECTION 47

NOVEL INSTANCE MINING WITH PSEUDO-MARGIN EVALUATION FOR FEW-...

引用

2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022

作者： Liu, Weijie Wang, Chong Yu, Shenghao Tao, Chenchen Wang, Jun Wu, Jiafei Faculty of Electrical Engineering and Computer Science Ningbo University China School of Information and Control Engineering China University of Mining and Technology China SenseTime Research China

ISBN: (纸本)9781665405409

Few-shot object detection (FSOD) enables the detector to recognize novel objects only using limited training samples, which could greatly alleviate model's dependency on data. Most existing methods include two training stages, namely base training and fine-tuning. However, the unlabeled novel instances in the base set were untouched in previous works, which can be re-used to enhance the FSOD performance. Thus, a new instance mining model is proposed in this paper to excavate the novel samples from the base set. The detector is thus fine-tuned again by these additional free novel instances. Meanwhile, a novel pseudo-margin evaluation algorithm is designed to address the quality problem of pseudo-labels brought by those new novel instances. The experimental results on MS-COCO dataset show the effectiveness of the proposed model, which does not require any additional training samples or parameters. Our code is available at: https://***/liuweijie19980216/NimPme. © 2022 IEEE

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Attention Based Graph Neural Networks

Attention Based Graph Neural Networks

引用

Software engineering and Artificial Intelligence (SEAI), IEEE International Conference on

作者： MD Ibrahim Khalil Muhammad Affan Abbas Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Control Science and Engineering Tianjin University Tianjin China

The performance of graph neural networks (GNNs) in a variety of graph-related tasks, such as node categorization, has been remarkably good. Existing GNN models, especially when working with big and sparse graphs, are constrained in how well they can capture complicated graph topologies. In order to overcome this issue, we incorporate an attention mechanism into the GNN design in this study. During the message-passing phase, our proposed model, Attention-Based Graph Neural Networks (AB-GNN), uses a learned attention mechanism to differentially weight the significance of surrounding nodes. Using numerous benchmark datasets for node classification, we test the performance of the AB-GNN and demonstrate that it outperforms current state-of-the-art GNN models. Our tests specifically show that AB-GNN improves accuracy by up to 1% in comparison to the top baseline model. According to our findings, the attention mechanism enhances the model's capacity to detect critical aspects in the graph, resulting in more precise node classification on Cora and CiteSeer datasets in our case. Comprehensively, our work demonstrates the potential of attention mechanisms to enhance the functionality of GNN models and offers directions for further study in this field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Redirected Walking for Virtual Environments: Investigation and Evaluation 8

Redirected Walking for Virtual Environments: Investigation a...

引用

8th International Conference on Virtual Reality, ICVR 2022

作者： Gao, Yuze Li, Lin Wang, Jieke Zheng, Liping School of Computer Science and Information Engineering Hefei University of Technology Hefei China Research Center of Safety Critical Industrial Measurement and Control Technology School of Computer Science and Information Engineering Hefei University of Technology Ministry of Education Hefei China

ISBN: (数字)9781665479110

ISBN: (纸本)9781665479110

Redirected walking (RDW) is a significant technique to tackle the problem of limited physical space in the process of creating and experiencing an immersive virtual environment (VE). The classification and description of the RDW methods in the existing literature are biased toward the core concept, and the available evaluation system does not comprehensively consider the subjective and objective indicators. It is arduous to effectively guide the selection of solutions for practical development. This work classifies and compares the mainstream RDW technologies in virtual reality based on whether there exists a walking boundary in a VE. Four metrics from both objective and subjective aspects were selected including mean walking speed, mean reset distance, motion fidelity, and motion sickness index. An evaluation system was established based on a fuzzy comprehensive evaluation, and five groups of live user experiments were conducted to evaluate the representative RDW schemes. Sub-results analyzed the advantages and drawbacks of the RDW methods at both objective and subjective levels. Comprehensive results allowed for more intuitive outcomes that are hardly attainable with a single factor. © 2022 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Exploring the Diagnostic Potential of LLMs in Schizophrenia Detection through EEG Analysis

Exploring the Diagnostic Potential of LLMs in Schizophrenia ...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Guerra, Michele Milanese, Roberto Deodato, Michele Ciobanu, Madalina G. Fasano, Fausto University of Molise Mosaic Research Center DiBT Pesche Italy Politecnico di Torino Department of Control and Computer Engineering Torino Italy New York University Division of Science Abu Dhabi United Arab Emirates Fisciano Italy

ISBN: (纸本)9798350386226

Schizophrenia is a psychiatric disorder that presents significant diagnostic challenges due to its complex neurophysiological characteristics. This paper investigates the potential of Large Language Models (LLMs), such as OpenAI's GPT-4 and GPT-o1, in detecting schizophrenia through electroencephalography (EEG) analysis. Using the LMSU public ScZ EEG dataset, we conducted a series of experiments involving different types of input data, including raw EEG signals, frequency band summaries, and graphical representations of brain activity. Our findings demonstrate that LLMs can accurately classify schizophrenic and healthy individuals while offering interpretable, clinically relevant insights aligned with established EEG markers. By integrating these models into the diagnostic workflow, we explore the concept of Symbiotic AI, where LLMs act as cognitive collaborators, enhancing clinicians' ability to analyze complex data efficiently and transparently. This approach not only improves diagnostic accuracy but also facilitates real-time decision-making, paving the way for earlier and more precise detection of schizophrenia in clinical settings. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

A Multi-Source Heterogeneous Knowledge Injected Prompt Learning Method for Legal Charge Prediction

arXiv

引用

arXiv 2024年

作者： Sun, Jingyun Wei, Chi Li, Yang College of Computer and Control Engineering Northeast Forestry University Harbin China. College of Computer Science and Technology Harbin Engineering University Harbin China.

Legal charge prediction, an essential task in legal AI, seeks to assign accurate charge labels to case descriptions, attracting significant recent interest. Existing methods primarily employ diverse neural network structures for modeling case descriptions directly, failing to effectively leverage multi-source external knowledge. We propose a prompt learning framework-based method that simultaneously leverages multi-source heterogeneous external knowledge from a legal knowledge base, a conversational LLM, and related legal articles. Specifically, we match knowledge snippets in case descriptions via the legal knowledge base and encapsulate them into the input through a hard prompt template. Additionally, we retrieve legal articles related to a given case description through contrastive learning, and then obtain factual elements within the case description through a conversational LLM. We fuse the embedding vectors of soft prompt tokens with the encoding vector of factual elements to achieve knowledge-enhanced model forward inference. Experimental results show that our method achieved state-of-the-art results on CAIL-2018, the largest legal charge prediction dataset, and our method has lower data dependency. Case studies also demonstrate our method’s strong interpretability. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Efficient data-driven occupancy detection in office environments and feature impact analysis

引用

International Journal of Information Technology (Singapore) 2024年 1-11页

作者： Fouzi, Harrou Ramakrishna, Kini K. Madakyaru, Muddu Ying, Sun Electrical and Mathematical Sciences and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Computer Thuwal 23955-6900 Saudi Arabia Department of Instrumentation and Control Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal 576104 India Department of Chemical Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal 576104 India

Occupancy detection is crucial in optimizing building energy efficiency and enhancing occupant comfort. This study introduces an innovative data-driven approach for accurate occupancy detection in an office room environment. Specifically, the methodology combines the advantages of Independent Component Analysis (ICA) to extract essential features from multivariate data and Kantorovitch distance (KD)-based schemes for detection sensitivity. The KD scheme’s detection threshold is computed nonparametrically using kernel density estimation to enhance the sensitivity of occupancy detection. The efficacy of this strategy is evaluated utilizing publicly available data recorded during winter in Mons, Belgium, capturing vital environmental parameters such as temperature, humidity, light, and CO2 levels through specialized sensors. Results demonstrate that the ICA-KD approach achieves an averaged accuracy of 98.355%, surpassing conventional approaches like Principal Component Analysis (PCA)-based, ICA-based, and other state-of-the-art methods. Additionally, the study uses Shapley Additive exPlanations (SHAP) with XGBoost to explore the impact of input variables on occupancy detection, highlighting the influence of various factors under different testing conditions. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Building occupancy Data-driven Environmental data Occupancy detection Semi-supervised detection

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：