检索结果-内蒙古大学图书馆

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Liu, Xinpeng Du, Xiaocong Yang, Xianqiang Cai, Chao School of Artificial Intelligence Dalian University of Technology Dalian116024 China Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin150001 China School of Control Science and Engineering Dalian University of Technology Dalian116024 China

ISBN: (纸本)9798350331820

This paper presents an improved version of the stochastic recurrent networks (STORN) for identification of non-linear state space systems with more complex model structures, including long short-term memory network (LSTM) and bidirectional gated recurrent unit (BiGRU). Both LSTM and BiGRU are recurrent neural networks with multiple state variables, which can store different information in the modeling of sequential data. Applying such a priori information into the prediction of data distribution can lead to better model performance. In this paper, several information fusion techniques are compared, and the effectiveness of the method is verified on three benchmark identification datasets. Our model outperforms the state-of-the-art baseline by 0.3 percent with 8 times fewer parameters. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticket

arXiv

引用

arXiv 2024年

作者： Zhou, Zhaokun Che, Kaiwei Fang, Wei Tian, Keyu Zhu, Yuesheng Yan, Shuicheng Tian, Yonghong Yuan, Li Peking University School of Electronic and Computer Engineering Shenzhen Graduate School China PengCheng Laboratory China Peking University School of Computer Science China Peking University Center for Data Science China Beijing Academy of Artificial Intelligence China

Spiking Neural Networks (SNNs), known for their biologically plausible architecture, face the challenge of limited performance. The self-attention mechanism, which is the cornerstone of the high-performance Transformer and also a biologically inspired structure, is absent in existing SNNs. To this end, we explore the potential of leveraging both self-attention capability and biological properties of SNNs, and propose a novel Spiking Self-Attention (SSA) and Spiking Transformer (Spikformer). The SSA mechanism eliminates the need for softmax and captures the sparse visual feature employing spike-based Query, Key, and Value. This sparse computation without multiplication makes SSA efficient and energy-saving. Further, we develop a Spiking Convolutional Stem (SCS) with supplementary convolutional layers to enhance the architecture of Spikformer. The Spikformer enhanced with the SCS is referred to as Spikformer V2. To train larger and deeper Spikformer V2, we introduce a pioneering exploration of Self-Supervised Learning (SSL) within the SNN. Specifically, we pre-train Spikformer V2 with masking and reconstruction style inspired by the mainstream self-supervised Transformer, and then finetune the Spikformer V2 on the image classification on ImageNet. Extensive experiments show that Spikformer V2 outperforms other previous surrogate training and ANN2SNN methods. An 8-layer Spikformer V2 achieves an accuracy of 80.38% using 4 time steps, and after SSL, a 172M 16-layer Spikformer V2 reaches an accuracy of 81.10% with just 1 time step. To the best of our knowledge, this is the first time that the SNN achieves 80+% accuracy on ImageNet. The code will be available at Spikformer V2. Copyright © 2024, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

A Multi-Signal Perception Network for Textile Composition Identification 48

A Multi-Signal Perception Network for Textile Composition Id...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Peng, Bo He, Liren Wu, Dong Chi, Mingmin Chen, Jintao Shanghai Key Laboratory of Data Science Fudan University School of Computer Science Shanghai China Zhongshan PoolNet Technology Co. Ltd Zhongshan Fudan Joint Innovation Center Zhongshan China Shanghai Fabric Eyes Artificial Intelligence Technology Co. Ltd Shanghai China Zhengzhou Zhongke Institute of Integrated Circuit and System Application China

ISBN: (纸本)9781728163277

Textile composition identification (TCI) is an essential basic link in the textile industry. Methods based on computer vision or near-infrared (NIR) signal processing have shown potential for the nondestructive TCI task. However, these methods ignore that the integration of NIR signals and visual information may help the model learn a better representation through information complementarity. This paper propose a Multi-Signal Perception Network (MSPNet) for nondestructive textile composition identification, allowing the model to benefit from the advantages of multimodal data. Firstly, a two-way feature extraction network is used to obtain multi-modal features. After that, we propose a multimodal signal fusion module to control the aggregation granularity among multimodal data. Specifically, the target areas of the image are perceived by a target area perception module (TAP). Then a bi-gated aggregation (Bi-GFA) is designed to capture consistent semantic information from signal to image and image to signal. The quantitative and qualitative results of the proposed MSPNet are significantly improved compared to both single and multimodal approaches. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Model to Predict the Breast Cancer using Stacking and Bagging Model 3

A Hybrid Model to Predict the Breast Cancer using Stacking a...

引用

3rd IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： Yuvalatha, S. Nithyapriya, S. Prabhavathy, S. Priyadharshini, R. Savitha, S. Kayathri, S. Bannari Amman Institute of Technology Department of Computer Science and Business Systems Sathyamangalam India Bannari Amman Institute of Technology Department of Artificial Intelligence and Data Science Sathyamangalam India Christ the King Engineering College Department of Electronics and Communication Engineering Coimbatore India Sri Ranganathar Institute of Engineering Department of Computer Science and Engineering Coimbatore India PSR Engineering College Department of Computer and Science and Engineering Sivakasi India

ISBN: (纸本)9798350317022

Breast cancer is a malignant tumor that develops in the cells of the breast tissue. Breast cancer is one of the major causes of death for women globally. In the examination of medical data, breast cancer prediction is a difficult task. To make decisions and accurately distinguish between benign and malignant tumors, physicians and pathologists need certain automated technologies. In this paper, hybrid ensemble technique (Bagging and Stacking) is used to predict the breast tumors as benign and malignant tumors. In the proposed work, the subset of data is created from the initial Wisconsin (Diagnostic) data Set by bootstrapping technique. Each bootstrap dataset is used to train the weak learner. The weak learners are K-Nearest Neighbors (KNN) Random Forest (RF), Decision Tree (DT) and Support Vector Machine (SVM). The Logistic Regression (LR) is used as the Meta Learner. The Meta Learner uses the predictions of weak learners as its training data. The proposed hybrid ensemble model obtains an accuracy 98.7%, Precision 98.83%, Recall 98.54%, F1 Score 98.68% and 0.012% error. © 2023 IEEE.

关键词： Bagging Bootstrapping Ensemble Malignant Meta Learner Stacking

来源：评论

学校读者我要写书评

暂无评论

Attention Mechanism Assisted Deep Learning Algorithm for Multi-Category Household Waste Classification

Attention Mechanism Assisted Deep Learning Algorithm for Mul...

引用

IEEE International Conference on Networking, Sensing and Control

作者： Shoufei Han Xu Liu Xiaojing Liu Honghao Zhu Ruyi Han School of Artificial Intelligence Anhui University of Science and Technology Huainan China Department of Computer Science Bengbu University Bengbu China School of Mathematics Shandong University Jinan China

ISBN: (数字)9798350365221

ISBN: (纸本)9798350365238

With the improvement of people's living standards, the annual global production of waste continues to rise, but the traditional household waste classification methods are burdened with a heavy task due to the wide variety of waste types and the difficulty of identifying them. Deep learning based waste image classification methods can accurately classify the waste images. In this paper, Visual Geometry Group (VGG16) is used to handle multi-category household waste classification. In order to further improve its classification accuracy, an attention mechanism is incorporated into it, and thus a VGG16 deep learning model with attention mechanism (VGG16-AM) is proposed. Experimental results show that the classification accuracy of our proposed model on the waste dataset is significantly improved to 93 % compared to other deep learning algorithms.

关键词： Deep learning Geometry Visualization Attention mechanisms Accuracy Production Classification algorithms Sensors Standards Image classification

来源：评论

学校读者我要写书评

暂无评论

Design of wirelessly charged temperature and humidity monitoring system for large-scale facilities 4

Design of wirelessly charged temperature and humidity monito...

引用

4th IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2022

作者： Wei, Yue Lei, Yang Ruitong, Wei School of Computer Science and Technology Dongguan University of Technology Dongguan China School of Electronic Engineering and Intelligence Dongguan University of Technology Dongguan China

ISBN: (数字)9781665467735

ISBN: (纸本)9781665467735

In a large-scale scientific facility experiment, it is crucial to monitor the temperature and humidity around the plexiglass when it is polymerized. The monitoring system is equipped with a lithium-ion battery, which is wirelessly recharged when the power is too low and can work continuously for 175 days in a fully charged state. Based on these, a wireless temperature and humidity monitoring system with wireless charging is designed in this paper. The system mainly includes a 433Mhz wireless communication module, a wireless charging module, and a temperature and humidity collection module. The temperature and humidity collection module collects the data and sends it to the host computer through the 433Mhz wireless communication module to realize real-time monitoring. After testing, the system can work normally in a fully charged state and ensure no data loss to meet the needs of large-scale scientific facility experiments. © 2022 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Design of Graphic Interactive Experimental Platform Based on MATLAB 12

Design of Graphic Interactive Experimental Platform Based on...

引用

12th International Conference on Information technology in Medicine and Education, ITME 2022

作者： Meilong, Chen Xiehua, Yu Shaozi, Li Fengfei, Kuang MinNan Science and Technology University Key Laboratory of Big Data and Artificial Intelligence University of Fujian Province Quanzhou China Xiamen University School of Informatics Xiamen China

ISBN: (纸本)9798350310153

Aiming at consolidating theoretical knowledge and improving actual ability, the paper directs at solving the unreadability of digital signal processing courses, such as intricate abstract concepts, various mathematical formulas, disable learning difficulties and so on. The paper puts forward to designing a platform based on MATLAB digital processing. Easy-operating, direct and perceptual platform improves the teaching quality and effects of the courses to a certain degree. It can also be extended as an experimental platform for other courses. © 2022 IEEE.

关键词： Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

Magnetic Levitation Control Using Deep Reinforcement Learning and Prioritized Experience Replay with Action Noise Variations 4

Magnetic Levitation Control Using Deep Reinforcement Learnin...

引用

4th International Conference on Power, Control and Computing Technologies, ICPC2T 2025

作者： Pare, Gopala Shil, Manas Pillai, G.N. Dey, Arnab Department of Electrical Engineering Indian Institute of Technology Roorkee India Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Roorkee India

ISBN: (纸本)9798331530402

In recent years, Reinforcement Learning (RL) has emerged as a promising approach for addressing control problems in complex, nonlinear environments. The ability of RL algorithms to autonomously learn optimal control policies without requiring an explicit system model makes them particularly suited for real-time applications in fields like robotics and industrial automation. This paper investigates the application of RL algorithms for controlling a magnetic levitation (maglev) system, which presents significant challenges due to its nonlinear dynamics. The Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm and the integration of Prioritized Experience Replay (PER) are employed to enhance learning efficiency. The impact of varying action noise (random perturbations added to actions) for exploration and system performance is explored;results demonstrate that TD3 with PER achieves superior stability, faster convergence, and reduced rise and settling times without overshoot. These findings emphasize the importance of tailored exploration strategies in optimizing control policies for complex environments, highlighting the potential of advanced RL techniques for real-time control applications. © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deep demonstration tracing: learning generalizable imitator policy for runtime imitation from a single demonstration 24

Deep demonstration tracing: learning generalizable imitator ...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Xiong-Hui Chen Junyin Ye Hang Zhao Yi-Chen Li Xu-Hui Liu Haoran Shi Yu-Yan Xu Zhihao Ye Si-Hang Yang Yang Yu Anqi Huang Kai Xu Zongzhang Zhang National Key Laboratory for Novel Software Technology & School of Artificial Intelligence Nanjing University China and Polixir Technologies School of Computer Science National University of Defense Technology and Polixir Technologies Polixir Technologies Nanjing University of Science and Technology and Polixir Technologies School of Computer Science National University of Defense Technology National Key Laboratory for Novel Software Technology & School of Artificial Intelligence Nanjing University China

One-shot imitation learning (OSIL) is to learn an imitator agent that can execute multiple tasks with only a single demonstration. In real-world scenario, the environment is dynamic, e.g., unexpected changes can occur after demonstration. Thus, achieving generalization of the imitator agent is crucial as agents would inevitably face situations unseen in the provided demonstrations. While traditional OSIL methods excel in relatively stationary settings, their adaptability to such unforeseen changes, which asking for a higher level of generalization ability for the imitator agents, is limited and rarely discussed. In this work, we present a new algorithm called Deep Demonstration Tracing (DDT). In DDT, we propose a demonstration transformer architecture to encourage agents to adaptively trace suitable states in demonstrations. Besides, it integrates OSIL into a meta-reinforcement-learning training paradigm, providing regularization for policies in unexpected situations. We evaluate DDT on a new navigation task suite and robotics tasks, demonstrating its superior performance over existing OSIL methods across all evaluated tasks in dynamic environments with unforeseen changes. The project page is in https://***.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Forecasting Method of Meteorological Drought Index Based on Time Series Analysis 4

Research on Forecasting Method of Meteorological Drought Ind...

引用

4th International Conference on artificial intelligence and computer Engineering, ICAICE 2023

作者： Gao, Chao Hu, Xiangyu Bai, Mengting Mi, Jiachen Lian, Xiaoqin Li, Jin School of Computer and Artificial Intelligence Beijing Technology and Business University Beijing100048 China Key Laboratory of Industrial Internet and Big Data China National Light Industry Beijing Technology and Business University Beijing100048 China

ISBN: (纸本)9798400708831

Drought is a kind of natural disaster, which has adverse effects on agricultural production, water supply and environmental ecosystem. Thus it is of great practical significance to accurately forecast meteorological drought index. In this study, the scPDSI was selected as the evaluation indicator of meteorological drought, and the scPDSI of the Greater Khingan Mountains forest area in China was predicted based on ARIMA model. The experimental results show that the ARIMA model with the optimal order is ARIMA (3,1,3). The correlation coefficient of each ARIMA (3,1,3) model is greater than 0.910, the MAE is less than 0.470, and the MSE is less than 0.520 both on the training set and the test set, indicating that there is a strong correlation between the predicted value and the actual value and each model has high prediction accuracy. Therefore, the ARIMA model can be used for accurate prediction of scPDSI, and then provide technical support for drought early warning. © 2023 ACM.

关键词： Time series analysis

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：