检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Li, Nan Wang, Longbiao Ge, Meng Unoki, Masashi Li, Sheng Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Japan Advanced Institute of Science and Technology Ishikawa Japan Kyoto Japan

Deep learning has revolutionized voice activity detection (VAD) by offering promising solutions. However, directly applying traditional features, such as raw waveforms and Mel-frequency cepstral coefficients, to deep neural networks often leads to degraded VAD performance due to noise interference. In contrast, humans possess the remarkable ability to discern speech in complex and noisy environments, which motivated us to draw inspiration from the human auditory system. We propose a robust VAD algorithm called auditory-inspired masked modulation encoder based convolutional attention network (AMME-CANet) that integrates our AMME with CANet. Firstly, we investigate the design of auditory-inspired modulation features as a deep-learning encoder, effectively simulating the process of sound-signal transmission to inner ear hair cells and subsequent modulation filtering by neural cells. Secondly, building upon the observed masking effects in the human auditory system, we enhance our auditory-inspired modulation encoder by incorporating a masking mechanism resulting in the AMME. The AMME amplifies cleaner speech frequencies while suppressing noise components. Thirdly, inspired by the human auditory mechanism and capitalizing on contextual information, we leverage the attention mechanism for VAD. This methodology uses an attention mechanism to assign higher weights to contextual information containing richer and more informative cues. Through extensive experimentation and evaluation, we demonstrated the superior performance of AMME-CANet in enhancing VAD under challenging noise conditions. © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Toward Efficient Automated Feature Engineering 39

Toward Efficient Automated Feature Engineering

引用

39th IEEE International Conference on Data Engineering, ICDE 2023

作者： Wang, Kafeng Wang, Pengyang Xu, Chengzhong Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences University of Macau China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen China State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau China

ISBN: (纸本)9798350322279

Automated Feature Engineering (AFE) refers to automatically generate and select optimal feature sets for downstream tasks, which has achieved great success in real-world applications. Current AFE methods mainly focus on improving the effectiveness of the produced features, but ignoring the low-efficiency issue for large-scale deployment. Therefore, in this work, we propose a generic framework to improve the efficiency of AFE. Specifically, we construct the AFE pipeline based on reinforcement learning setting, where each feature is assigned an agent to perform feature transformation and selection, and the evaluation score of the produced features in downstream tasks serve as the reward to update the policy. We improve the efficiency of AFE in two perspectives. On the one hand, we develop a Feature Pre-Evaluation (FPE) Model to reduce the sample size and feature size that are two main factors on undermining the efficiency of feature evaluation. On the other hand, we devise a two-stage policy training strategy by running FPE on the pre-evaluation task as the initialization of the policy to avoid training policy from scratch. We conduct comprehensive experiments on 36 datasets in terms of both classification and regression tasks. The results show 2.9% higher performance in average and 2x higher computational efficiency comparing to state-of-the-art AFE methods. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Adapter Learning in Pretrained Feature Extractor for Continual Learning of Diseases

arXiv

引用

arXiv 2023年

作者： Zhang, Wentao Huang, Yujun Zhang, Tong Zou, Qingsong Zheng, Wei-Shi Wang, Ruixuan School of Computer Science and Engineering Sun Yat-sen Univerisity Guangzhou China Peng Cheng Laboratory Shenzhen China Guangdong Province Key Laboratory of Computational Science Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing MOE Guangzhou China

Currently intelligent diagnosis systems lack the ability of continually learning to diagnose new diseases once deployed, under the condition of preserving old disease knowledge. In particular, updating an intelligent diagnosis system with training data of new diseases would cause catastrophic forgetting of old disease knowledge. To address the catastrophic forgetting issue, an Adapter-based Continual Learning framework called ACL is proposed to help effectively learn a set of new diseases at each round (or task) of continual learning, without changing the shared feature extractor. The learnable lightweight task-specific adapter(s) can be flexibly designed (e.g., two convolutional layers) and then added to the pretrained and fixed feature extractor. Together with a specially designed task-specific head which absorbs all previously learned old diseases as a single ‘out-of-distribution’ category, task-specific adapter(s) can help the pretrained feature extractor more effectively extract discriminative features between diseases. In addition, a simple yet effective fine-tuning is applied to collaboratively fine-tune multiple task-specific heads such that outputs from different heads are comparable and consequently the appropriate classifier head can be more accurately selected during model inference. Extensive empirical evaluations on three image datasets demonstrate the superior performance of ACL in continual learning of new diseases. The source code is available at https: //***/GiantJun/CL_Pytorch. 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

A Feature Reduction-Induced Subspace Multiple Kernel Fuzzy Clustering Algorithm 17th

A Feature Reduction-Induced Subspace Multiple Kernel Fuzzy C...

引用

17th CCF Conference on Computer Supported Cooperative Work and Social computing, ChineseCSCW 2022

作者： Tang, Yiming Li, Bing Pan, Zhifu Sun, Xiao Chen, Renhao Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer and Information Hefei University of Technology Anhui Hefei230601 China Engineering Research Center of Safety Critical Industry Measure and Control Technology Ministry of Education Hefei University of Technology Anhui Hefei230601 China

ISBN: (纸本)9789819923847

High-dimensional data poses a great challenge to clustering, and subspace clustering algorithms have unique advantages when working with high-dimensional data. However, there are still some difficulties in adapting the nonlinear feature dimension, the selection and collaborative settings of kernel functions. Therefore, in this study, we come up with a feature reduction-induced subspace multiple kernel fuzzy clustering. Firstly, in order to solve the information loss caused by the nonlinear characteristics of the data, the multiple kernel clustering method is introduced, and some nonlinear features of the data are collaboratively mapped to the high-dimensional linear space, so as to better understand the characteristic information of the data. Secondly, due to the complexity of subspace and multiple kernel learning, we introduce the idea of feature reduction, and reduce the data dimension according to the importance of information, which can reduce the complexity of the algorithm on the one hand, and improve the role of important feature attributes in clustering on the other hand. Finally, the proposed RS-MKFC algorithm and the related 6 algorithms are compared on 6 ordinary datasets and 4 high-dimensional datasets, and it is found that the proposed algorithms are superior over the other 6 algorithms. At the same time, we discover the ability of RS-MKFC algorithm to screen important features as well as the function of feature reduction, and good results are achieved. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

SEMG-based gesture recognition by rotation forest-based extreme learning machine

SEMG-based gesture recognition by rotation forest-based extr...

引用

2021 IEEE International Conference on Real-Time computing and Robotics, RCAR 2021

作者： Peng, Fulai Chen, Cai Zhang, Xikun Wang, Xingwei Wang, Changpeng Wang, Lin Chinese Academy of Sciences Shandong Institute of Advanced Technology Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China

ISBN: (纸本)9781665436786

The motion information contained in surface electromyography (sEMG) signals contributes significantly to the prosthetic hand control. However, the accuracy and speed of gesture recognition from sEMG signals are still insufficient for natural control. In order to alleviate this problem, this paper propose a rotation forest-based extreme learning machine method (RoF-ELM) to improve the recognition performance based on sEMG signals. Firstly, the active motion segments were picked out and pre-processed by sliding window. Then, 104 features were extracted from each sample, and SVM-RFE method was used to reduce the feature space dimension. Finally, the RoF-ELM classification model was constructed and tested based on the EMG data for gestures Data Set containing a total of 72 recordings, each of which consists of six basic gestures. 100 trials were implemented to validate the performance of the proposed method, the results show that the RoF-ELM method have the highest accuracy (91.11%) across different subjects with relatively short runtime compared with decision tree (DT), ELM, random forest (RF), and RoF methods. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Preparation and Simulation of Quantum States of Matrices 22

Preparation and Simulation of Quantum States of Matrices

引用

Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering

作者： Zhengyu Liu Xiaonan Liu Haoshan Xie Chenyan Zhao School of Computer and Artificial Intelligence of Zhengzhou University China State Key Laboratory of Mathematical Engineering and advanced computing Information Engineering University China

ISBN: (纸本)9781450397148

A basic problem of quantum computing is how to effectively express classical data in quantum systems. This problem is called state preparation problem, and the process of preparing quantum states is called coding. In this paper, the classical data of matrix is transformed into quantum states in the form of amplitude coding and simulated. This paper first introduces the detailed process of matrix transformation into the linear combination of quantum ground state, then designs a quantum circuit model to realize amplitude coding according to the idea of binary tree model and quantum random walk algorithm, and finally simulates the three matrices on IBM quantum cloud platform, and analyzes and introduces many situations. The experimental results verify the feasibility of converting the matrix into quantum states by amplitude coding, analyze the causes of errors in the experimental process, and put forward the corresponding solutions. This paper introduces in detail the whole process of matrix conversion to quantum states and the construction of quantum circuits for simulation. Compared with the existing experiments, the quantum circuits constructed in this paper are shorter in length, less in number of quantum gates, and more versatile.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Circuit Simulation and Optimization of Quantum Search Algorithm 22

Circuit Simulation and Optimization of Quantum Search Algori...

引用

Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering

作者： Xiaonan Liu Chenyan Zhao Haoshan Xie Zhengyu Liu State Key Laboratory of Mathematical Engineering and Advanced Computing Information Engineering University China School of Computer and Artificial Intelligence ZhengZhou University China

ISBN: (纸本)9781450397148

At present, the scale of quantum computers in the real sense is still small, and quantum simulation has become one of the important ways of quantum theory research, grover quantum search algorithm is suitable for the search problem of disordered database. Firstly, according to the implementation principle of Grover algorithm and Boolean logic relationship, the design idea of multi-objective Oracle is analyzed, based on IBMQ quantum cloud platform, the quantum circuit of Grover algorithm with multi-objective items is simulated. Based on the characteristics of Grover algorithm and the simulation process of quantum gate, the action of multiple identical quantum gates is combined to reduce the update times of probability amplitude and improve the simulation efficiency. The libquantum quantum simulator is used for experiments and the target item is successfully searched, which proves the feasibility of the optimization method and provides reference for the simulation and optimization of other quantum algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural Manifold Learning Based on 40 nm Dual-Mode PCM Compute-in-Memory Chip with Hardware Adaptive Drift Compensation

Neural Manifold Learning Based on 40 nm Dual-Mode PCM Comput...

引用

2024 IEEE International Electron Devices Meeting, IEDM 2024

作者： Yan, Longhao Li, Yuqi Li, Xi Pan, Zelun Wang, Zeyu Wang, Xile Wang, Bowen Zhan, Zhe Tang, Xiyuan Tao, Yaoyu Ge, Woo-Ping Song, Zhitang Huang, Ru Yang, Yuchao Beijing Advanced Innovation Center for Integrated Circuits School of Integrate Circuits Peking University Beijing China Beijing China Center for Brain Inspired Chips Institute for Artificial Intelligence Peking University Beijing China Guangdong Provincial Key Laboratory of In-Memory Computing Chips School of Electronic and Computer Engineering Peking University Shenzhen China State Key Laboratory of Functional Materials for Informatics Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences China

ISBN: (纸本)9798350365429

Neural manifold learning (NML), as a significant research topic in the field of neuroscience, plays a vital role in the realization of intelligent brain-computer interface (BCI) at the edge. However, traditional edge computing platforms fall short in meeting the demands for the huge computing power needed to process massive neural data. Here, we design a 288Kb dual-mode phase change memory (PCM) compute-in-memory chip in 40nm technology and utilize its two cores for two fundamental kernels in NML, vector matrix multiplication (VMM) and true random number generation, and develop a PCM-based NML system for the first time. In particular, in order to mitigate the performance degradation caused by PCM conductance drift, we propose a novel adaptive-PCM-drift-compensation scheme that significantly improves the accuracy of VMM results. Compared with CPU platforms running the same tasks, the resulting chip improves the computing energy efficiency and throughput by 476× and 264×, respectively. © 2024 IEEE.

关键词： Random number generation

来源：评论

学校读者我要写书评

暂无评论

Implicit Feature Augmentation with Feature Transfer For Class-Imbalanced Medical Image Classification

Implicit Feature Augmentation with Feature Transfer For Clas...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Mei Yu Hao Zheng Xuewei Li Jie Gao Xuzhou Fu Zhiqiang Liu Ruiguo Yu College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Tianjin Key Laboratory of Advanced Networking Tianjin China School of Feature Technology Tianjin University Tianjin China

The class imbalance problem, which is prevalent in medical image datasets, seriously affects the diagnostic effectiveness of deep learning-based network models. To alleviate this problem, data re-sampling and loss re-weighting techniques are often used to reshape the decision boundary of the classifier. However, these techniques still lead to biased decision boundary due to the lack of sufficient and diversified samples in the tail classes of medical image datasets. In this paper, we propose an implicit feature augmentation with feature transfer (FT-IFA) method which solves the class imbalance problem by expanding the feature space of tail classes to reshape the decision boundary of the classifier. FT-IFA utilizes prototype similarity to transfer the rich transformation information from the head classes to tail classes on the basis of the balanced feature space, enriching the intra-class diversity of tail classes. Experimental results on two class-imbalanced medical image datasets show that FT-IFA outperforms the current state-of-the-art methods and effectively solves the class imbalance problem.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AGA-RFNN: Adaptive Genetic Algorithm-based Random Forest Neural Network for Pavement Deterioration Prediction

AGA-RFNN: Adaptive Genetic Algorithm-based Random Forest Neu...

引用

2023 IEEE International Conference on Real-Time computing and Robotics, RCAR 2023

作者： Xu, Zhenyu Meng, Lenian Zhang, Qieshi Cheng, Jun Philip, Babitha Aljassmi, Hamad Yang, Zhiyong Chinese Academy of Sciences Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Shenzhen China China University of Geosciences School of Economics and Management Wuhan China United Arab Emirates University Department of Civil and Environmental Engineering Al Ain United Arab Emirates Yantai Institute of Technology School of Artificial Intelligence Shandong China

ISBN: (纸本)9798350327182

Pavement deterioration prediction is an important task of road inspection mobile robots. Tree-based deep learning models perform well in this prediction but their accuracy remains unsatisfactory. In this paper, to enhance the prediction accuracy of pavement deterioration, we propose a SELECTOR module and Adaptive Genetic Algorithm-based Random Forest Neural Networks (AGA-RFNNs). The SELECTOR module is first used to refine the input data by exploiting correlation analysis, then the RFNNs are designed to make superior accurate and general predictions by learning predictions from random forests, and finally the AGA is applied to train the RFNNs, which considers both the average and maximum fitness of the population and thereby obtaining the optimal solution. Integrating AGA and RFNN, the proposed AGA-RFNN enhances the accuracy of pavement deterioration prediction systems. Experimental results demonstrate that AGA-RFNN outperforms existing models on four deterioration datasets related to cracking, deflection, international roughness index and rutting, respectively. © 2023 IEEE.

关键词： Forecasting

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：