检索结果-内蒙古大学图书馆

International Conference on Control, Automation and Information Sciences (ICCAIS)

作者： Alvaro Deibe Díaz José A. Antón Nacimiento Jesús Cardenal Fernando López Peña Ferrol Industrial Campus Universidade da Coruña Ferrol Spain Observatory for Design and Innovation in Mobility Transportation and Automotion Universidade da Coruña Ferrol Spain Marine & Industrial Technologies Research Center Ferrol Industrial Campus Universidade da Coruña Ferrol Spain

ISBN: (数字)9798331542047

ISBN: (纸本)9798331542054

The time-varying Kalman attitude estimator (TVKAE) previously developed by the authors has a state vector made by some measurable physical quantities, including acceleration. A second published version of this estimator, adapted to low acceleration motion, includes a weighting parameter for acceleration that can be unity or zero. The first value preserves the original algorithm, and the second leads to a version of the estimator adapted to low accelerations. This work analyzes the operation and performance of the TVKAE when varying this weight.

关键词： Accelerometers Force measurement Dead reckoning filtering algorithms Vectors Time measurement Kalman filters Noise measurement Gravity Sports

来源：评论

学校读者我要写书评

暂无评论

Pattern-Invariant Unrolling for Robust Demosaicking

Pattern-Invariant Unrolling for Robust Demosaicking

引用

European Signal Processing Conference (EUSIPCO)

作者： Matthieu Muller Daniele Picone Mauro Dalla Mura Magnus O. Ulfarsson GIPSA-Lab Univ. Grenoble Alpes CNRS Grenoble INP Grenoble France Faculty of Electrical and Computer Engineering University of Iceland Iceland

ISBN: (数字)9789464593617

ISBN: (纸本)9798331519773

To acquire color images, most commercial cameras rely on color filter arrays (CFAs), which are a pattern of color filters overlaid over the sensor's focal plane. Demosaicking describes the processing techniques to reconstruct a full color image for all pixels on the focal plane array. Most demosaicking methods are tailored for a specific CFA, and tend to work poorly for others. In this work we present an algorithm for demosaicking a wide variety of CFAs. The proposed method allows to blend the knowledge of the CFA with information coming from data, employing a novel transformation and pattern-invariant loss function. The method is based on the unrolling of an algorithm based on a neural network learned on available examples. Preliminary experiments over RGB and RGBW CFAs show that the method performs well over a range of CFAs and is competitive for CFAs for which competing methods were tailored to work well on.

关键词： Image color analysis Neural networks Signal processing algorithms Europe Color filtering algorithms Parallel processing Data models Image reconstruction Sensor arrays

来源：评论

学校读者我要写书评

暂无评论

Research on Postgraduate Examination Question Extraction algorithms Based on Multilayer filtering and Dynamic Probability Model

Research on Postgraduate Examination Question Extraction Alg...

引用

Electrical Engineering and Automation (IFEEA), International Forum on

作者： Mian Fu Dandan Wang Business School Xinhua University of Anhui Province

ISBN: (数字)9781728196275

ISBN: (纸本)9781728196282

In view of the characteristics of postgraduate education, such as more courses, quicker content updating, flexible examination methods, and multiple courses compounding questions, a random test question extraction algorithm based on multi-layer filtering model and dynamic probability model is proposed, which strengthens the pertinence of the test question extraction process and improves the efficiency of the algorithm. The results show that the parameters can better approximate the set requirements, the distribution of the problem is reasonable, the versatility is good, and can meet the needs of personalized questions.

关键词： Electrical engineering filtering Heuristic algorithms Education filtering algorithms Approximation algorithms Nonhomogeneous media

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Architecture for Brain Tumor Segmentation with a Novel Hybrid NF-RCNN and Adam Optimizer

An Enhanced Architecture for Brain Tumor Segmentation with a...

引用

Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI), International Conference on

作者： N. Lavanya S. Nagasundaram Vels Institute of Science Technology and Advanced Studies Chennai

ISBN: (数字)9798350354539

ISBN: (纸本)9798350354546

Magnetic resonance imaging (MRI) of the brain for the purpose of manual tumor diagnosis is laborious and timeconsuming. A diagnostic by an expert is also necessary in every case. The need for accurate diagnosis and classification of brain tumors led to the development of several computer- controlled procedures. In order to segregate brain tumors, this research suggests a new filter. The approach used a hybrid model that included NasNet and FRCNN for segmentation of the brain tumor image, and it was optimized using Adam optimizer. For image filtering, SWT enhanced Median filter was utilized. Outperforming state-of-the-art approaches presented in literature, the suggested strategy shows promising outcomes. The proposed model segments brain tumor image with 92.19% accuracy on tumor region and 99.79% accuracy on background region.

关键词： Deep learning Image segmentation Magnetic resonance imaging Manuals Computer architecture filtering algorithms Brain modeling

来源：评论

学校读者我要写书评

暂无评论

EEG-Based Emotion Recognition Using Optimum Number of Channels

EEG-Based Emotion Recognition Using Optimum Number of Channe...

引用

Smart Power Control and Renewable Energy (ICSPCRE), IEEE International Conference on

作者： Amit Kumar Dwivedi Om Prakash Verma Sachin Taran Department of Electronics and Communication Delhi Technological University Delhi India

ISBN: (数字)9798350377002

ISBN: (纸本)9798350377019

Electroencephalography (EEG) signals can detect an individual's emotional state, as emotions significantly influence communication. Brain-computer interfaces, or BCIs, use EEG signals to improve human-machine communication. By deciphering EEG data and applying it to various scenarios, emotion detection via EEG signals can efficiently ascertain the activity of particular brain areas. Using all EEG channels for categorization may lead to feature confusion and redundancy due to the specificity of these activation zones. This paper suggests a novel technique that uses the fewest possible EEG channels to accurately identify emotions. The suggested approach uses Pearson's correlation coefficient cutoff value to filter electrodes pertinent to emotion classification. The EEG data from the filtered electrodes is decomposed into sub-bands using Volt-Kalman order filtering. The decomposed EEG sub-bands are used to extract certain statistical properties, such as mean, skewness, kurtosis, and entropy. The MRMR (Minimum Redundancy Maximum Importance) algorithm was used to choose these features based on their importance. Several classification techniques were used to classify the retrieved information into four emotions further. The suggested framework outperforms both deep and shallow machine learning techniques, with cross-validation results demonstrating an 88% classification accuracy. A statistical analysis validates the importance of certain variables for emotion classification by confirming their significance with p-values < 0.05.

关键词： Electrodes Correlation coefficient Emotion recognition Accuracy filtering Redundancy filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

Efficient Architecture for 2-Dimensional Discrete Wavelet Transform with Novel Lifting Algorithm*

引用

Chinese Journal of Electronics 2023年第1期19卷 1-6页

作者： Chao Wang Peng Cao National ASIC System Engineering Research Center Southeast University Nanjing China

In commonly-used line-based implementation for Two-dimensional Discrete wavelet transform (2D DWT), data buffer is required between the row DWT processor and the column DWT processor to reorder the data flow into consistent sequence, which increases the on-chip memory size, output latency and control complexity. Based on the proposed Decomposed lifting algorithm (DLA), image data is processed in raster scan manner both in row processor and column processor. Theoretical analysis indicates that the precision of DLA outperforms other lifting-based algorithms in terms of round-off noise and internal word-length. An efficient line-based architecture is designed to perform 2D DWT based on DLA with high performance and low memory by eliminating the implementation of data buffer. For an N × N image, only 4N internal memory is required for 9/7 filter with output latency of 2N clock cycles. Compared with related 2D DWT architectures, the size of on-chip memory and output latency are reduced significantly under the same arithmetic cost, memory bandwidth and timing constraint. This design was implemented in SMIC 0.18µm CMOS logic fabrication with 32K bits dual-port RAM and 20K equivalent 2-input NAND gates in a 1.2mm×1.1mm die, which can perform 5-level Mallat decomposition at 36.17frames/s with image resolution up to 1920 × 1080 pixels in YUV422 full color format under 100MHz.

关键词： Costs Memory management Random access memory Process control Transforms Logic gates filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimized Defogging Algorithm for Dark Channel Based on Multi-Scale Convolutional Neural Network

Optimized Defogging Algorithm for Dark Channel Based on Mult...

引用

Smart Grid and Artificial Intelligence (SGAI), International Conference on

作者： Zhaochuan Wei Rongtian Yang Somsack Inthasone Jundao Pan Guangxi Key Laboratory of Precision Navigation Technology and Application Guilin University of Electronic Technology Guilin China Computer Science Department Faculty of Natural Nayional University of Laos Vientiane Capital Lao PDR Chinese Academy of Sciences Institute of Space and Astronautical Information Innovation Beijing China

ISBN: (数字)9798331518806

ISBN: (纸本)9798331518813

To address the issue of significant discrepancies between the estimated transmission in traditional single-image dehazing algorithms and the actual scenario, a multi-scale convolutional neural network-based dehazing algorithm optimized by dark channel prior is proposed. The algorithm utilizes guided filtering, which preserves edge smoothness, to filter the feature transmission map extracted by the convolutional neural network, making the processed transmission closer to the actual transmission of the input hazy image. Subsequently, the dark channel prior theory is employed to obtain the global atmospheric light value of the hazy image, and finally, The atmospheric scattering model serves as a crucial tool when engaging in the operation of image dehazing, effectively enhancing the clarity of images affected by haze. The outcomes of the experiments indicate that this algorithm surpasses the latest approaches in both qualitative and quantitative evaluations. The algorithm put forward shows remarkable enhancements in peak signal - to - noise ratio and structural similarity, leading to significantlyenhanced dehazing performance.

关键词： filtering Atmospheric modeling Noise Channel estimation Scattering Estimation filtering algorithms Feature extraction filtering theory Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Feedback Cancellation for Hearing Aids with Improved System Stability and Sound Quality

Deep Feedback Cancellation for Hearing Aids with Improved Sy...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Eleftheria Lydaki Zheng-Hua Tan Jesper Jensen Meng Guo Oticon A/S Denmark Aalborg University Denmark

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Acoustic feedback cancellation is an important task in audio processing systems, aiming to mitigate the effects of feedback loops on system stability and sound quality. State-of-the-art methods rely on adaptive filtering algorithms and face challenges in balancing between rapid convergence and low steady-state error. In this work, we introduce a novel approach inspired by traditional adaptive filtering and deep learning techniques to achieve a significantly faster convergence and lower steady-state errors at the same time. Our proposed system, termed Deep Feedback Cancellation (DFC), leverages deep neural networks to predict the impulse response of the feedback path directly. Hence, it replaces traditional gradient based adaptive estimation of the impulse responses. Experimental evaluation, in a hearing aid setting, conducted on real-world data demonstrates the superiority of DFC over traditional methods. Specifically, in a practically very important situation, where the feedback path undergoes rapid changes, the proposed DFC achieves increased convergence rate by a factor of 30, while decreasing the steady-state error by 2 dB. Generally, DFC leads to very significant improvements over traditional methods. These improvements are confirmed by objective evaluations and subjective listening tests. Our findings suggest that DFC presents a promising alternative for acoustic feedback cancellation in hearing aid applications.

关键词： Deep learning filtering Signal processing filtering algorithms Hearing aids Acoustics Steady-state Transient analysis Speech processing Convergence

来源：评论

学校读者我要写书评

暂无评论

Short-time quantum Fourier transform processing

Short-time quantum Fourier transform processing

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Sreeraj Rajindran Nair Benjamin Southwell Christopher Ferrie Dolby Laboratories University of Technology Sydney Sydney Australia Dolby Laboratories Sydney Australia University of Technology Sydney Sydney Australia

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

algorithms for processing data in short-time batches are critical for both online and offline processing of streamed and large data respectively due to the quadratic relation between signal length and computational cost of convolution-based processing schemes. Whilst quantum analogs to some digital signal processing algorithms have been discovered, including the quantum Fourier transform (QFT), there has been no development of short-time processing techniques in the quantum domain. In this manuscript, we introduce the short-time QFT (STQFT) processing technique to bridge this gap in research. We develop a novel overlap-add reconstruction technique in the quantum domain using a permutation gate to combine subsequent windows. With this in mind, we discuss convolution under our novel STQFT processing scheme. We demonstrate filtering in the quantum Fourier domain with a filter stored in a quantum register as well as in a block encoded unitary gate. Throughout the paper, we elaborate upon implementation details such as applying DC offsets to input signals, skipping input data frames whenever necessary, the use of overlap-save as a reconstruction technique and mitigating time-varying scaling due to normalization of the windowed input data and filters.

关键词： Fourier transforms Convolution filtering Signal processing algorithms Digital signal processing Logic gates filtering algorithms Real-time systems Registers Speech processing

来源：评论

学校读者我要写书评

暂无评论

Regularized Affine Projection Algorithm for Stereophonic Acoustic Echo Cancellation

Regularized Affine Projection Algorithm for Stereophonic Aco...

引用

Measurement and Simulation (ATOMS), Advanced Topics on

作者： Cristian-Lucian Stanciu Cristian Anghel Laura-Maria Dogariu Ionuţ-Dorinel Fîciu Lucian Stanciu Telecommunications Department National University of Science and Technology POLITEHNICA Bucharest Romania Academy of Romanian Scientists Bucharest Romania

ISBN: (数字)9798350358377

ISBN: (纸本)9798350358384

Stereophonic acoustic echo cancellation (SAEC) requires the estimation of four unknown impulse responses by using four corresponding adaptive filters. The affine projection algorithm (APA) is an attractive solution, which has improved tracking speeds with respect to the classical alternatives. It can be employed by reinterpreting the SAEC setup and using a single complex valued adaptive filter. In this paper, we propose a regularization technique for the APA designed to mitigate the effects of double-talk situations on the adaptive process.

关键词： Echo cancellers Noise Adaptive filters Adaptive algorithms Interference filtering algorithms Acoustics Projection algorithms Speech processing Standards

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：