检索结果-内蒙古大学图书馆

23rd IEEE International Conference on Machine Learning and Applications, ICMLA 2024

作者： Adigun, Olaoluwa Kosko, Bart Signal and Image Processing Institute Department of Electrical and Computer Engineering Los AngelesCA90089-2564 United States

ISBN: (纸本)9798350374889

We introduce new soft diamond regularizers that both improve synaptic sparsity and maintain classification accuracy in deep neural networks. These parametrized regularizers outperform the state-of-the-art hard-diamond Laplacian regularizer of Lasso regression and classification. They use thick-tailed symmetric alpha-stable (Sa S) bell-curve synaptic weight priors that are not Gaussian and so have thicker tails. The geometry of the diamond-shaped constraint set varies from a circle to a star depending on the tail thickness and dispersion of the prior probability density function. Training directly with these priors is computationally intensive because almost all Sa S probability densities lack a closed form. A precomputed lookup table removed this computational bottleneck. We tested the new soft diamond regularizers with deep neural classifiers on the three datasets CIFAR-10, CIFAR-100, and Caltech-256. The regularizers improved the accuracy of the classifiers. The improvements included 4.57% on CIFAR-10, 4.27% on CIFAR-100, and 6.69% on Caltech-256. They also outperformed L2 regularizers on all the test cases. Soft diamond regularizers also outperformed L1 lasso or Laplace regularizers because they better increased sparsity while improving classification accuracy. Soft-diamond priors substantially improved accuracy on CIFAR-10 when combined with dropout, batch, or data-augmentation regularization. © 2024 IEEE.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

Improved Distance vector based Kalman Filter localization algorithm for wireless sensor network

Improved Distance vector based Kalman Filter localization al...

引用

2023 International Conference on Control, Automation and Diagnosis, ICCAD 2023

作者： Mani, Rahma Messous, Sana Campobello, Giuseppe Battaglia, Filippo Liouane, Noureddine University of Monastir Laboratory of Automatic Signal and Image Processing Monastir5019 Tunisia University of Messina Department of Engineering Messina Italy National Engineering School of Monastir University of Monastir Laboratory of Automatic Signal and Image Processing Tunisia

ISBN: (纸本)9798350347074

Localization is a crucial concern in many wireless sensor networks (WSN) applications. Moreover, getting accurate information about the geographic positions of nodes in the sensing field is necessary in order to make the collected data useful and meaningful. In this context, the heuristic distance vector called DV-Distance is widely used for range-free localization in multi-hop WSN thanks to its advantages such as its simplicity and good accuracy. However, its localization accuracy may be relatively low due to environmental conditions. In this paper, we propose an improvement of the DV-Hop algorithm based on distance computation via a received signal strength indicator (RSSI) and a simple polynomial approximation technique. The proposed technique consists of RSSI measurement for distance estimation between sensor nodes thanks to low cost and simplicity compared to other techniques based on time and angle of arrival, i.e. TOA, AOA and TDOA which require more specialized equipment. However, as RSSI values may be affected by conditions environment such as noise, we propose to use the Kalman Filter in order to deal with this issue and improve localization accuracy. Test results proved that the proposed technique has a higher localization accuracy than DV-Distance by up to 50% and by up to 18% when compared with the state-of-the-art algorithms cited above and other DV-Hop-based localization methods. © 2023 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Smart weather station using development boards for environmental applications

Smart weather station using development boards for environme...

引用

2023 International Conference on Advances in Electronics, Control and Communication Systems, ICAECCS 2023

作者： Adane, Amar Haicheur, Ichrak Amani Lebza, Amani Rezzag Faculty of Electrical Engineering Usthb Laboratory Laboratory of Image Processing and Radiation Telecommunication Department Algiers Algeria

ISBN: (纸本)9781665463102

In this paper, a smart system suitable for environmental studies, is presented. This weather acquisition system is built using an Arduino uno and Raspberry Pi3. It is equipped with temperature, humidity, air quality, and solar radiation detector. The Arduino card controls the instrumentation made of the four weather sensors and the experimental data are stored using specific software developed around the Raspberry Pi3. This system can be managed via internet with a smartphone or laptop. Experimental results are obtained with this smart system. In particular, they are used to estimate the risk of fire in the region under study. © 2023 IEEE.

关键词： Risk perception

来源：评论

学校读者我要写书评

暂无评论

Improvement of the 2.4 GHz SDR Radar- range using optimised Cantennas

Improvement of the 2.4 GHz SDR Radar- range using optimised ...

引用

2023 International Conference on Advances in Electronics, Control and Communication Systems, ICAECCS 2023

作者： Adane, Amar Himene, Sofia Cherfi, Djamila Faculty of Electrical Engineering Usthb Laboratory Laboratory of Image Processing and Radiation Telecommunication Department Algiers Algeria

ISBN: (纸本)9781665463102

In this paper, a Doppler SDR Radar equipped with Adalm-Pluto SDR and Cantennas, is presented. This Radar works around 2.4 GHz. The Cantennas are made of cans acting as circular antennas. In order to improve the range of the Radar, a parametric study is implemented to optimize the matching and radiation features of these antennas. This study mainly consists in tuning the length and the width of the Cantennas so as to reduce the return loss (S11). These antennas were tested with the Doppler SDR radar. These tests allow getting the antenna which can yield accurate evaluation of the velocity of a fan propeller in a large range. Finally, two ameliorated Cantennas where built and experimented, showing that they can account for such a velocity. © 2023 IEEE.

关键词： Doppler radar

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Backpropagation Autoencoding Networks for image Compression and Denoising 22

Bidirectional Backpropagation Autoencoding Networks for Imag...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Adigun, Olaoluwa Kosko, Bart Signal and Image Processing Institute Department of Electrical and Computer Engineering Los AngelesCA90089-2564 United States

ISBN: (纸本)9798350345346

A bidirectional autoencoder learns or approximates an identity mapping as it trains a single network with a version of the new bidirectional backpropagation algorithm. Ordinary unidirectional autoencoders find many uses in image processing and in large language models. But they use separate networks for encoding and decoding. Bidirectional auto encoders use the same synaptic weights for encoding and decoding. The forward pass encodes while the backward pass decodes. Bidirectional auto encoders improved network performance and significantly reduced memory usage and used fewer parameters. Simulations compared unidirectional with bidirectional autoencoders for image compression and de noising. The models trained on the MNIST handwritten-digit and CIFAR-IO image datasets. The performance measures were the peak signal-to-noise ratio and the index of structural similarity. Bidirectional autoencoders outperformed unidirectional autoencoders and still reduced the number of trainable synaptic parameters by about 50%. © 2023 IEEE.

关键词： autoencoders bidirectional au-toencoders Bidirectional backpropagation bidirectional networks large language models variational autoencoders

来源：评论

学校读者我要写书评

暂无评论

Maintenance dynamic scheduling for a Tunisian railway transport system

Maintenance dynamic scheduling for a Tunisian railway transp...

引用

2024 International Conference on Control, Automation and Diagnosis, ICCAD 2024

作者： Mellouli, Sarra Mhalla, Anis Dutilleul, Simon Collart Messaoud, Hassani Laboratory of Automatic Signal and Image Processing Laratsi Monastir Tunisia Laboratory of Automation Electrical Systems Environment Laese Monastir Tunisia Estas Laboratory University Gustave Eiffel Cosys Department Lille France

ISBN: (纸本)9798350361025

The developments reported in this paper are devoted to the dynamic scheduling of rail transport systems. In this context, our study focuses on implementing an algorithm for solving railway planning with predictable or unexpected demands. The system modeling process uses P-time stochastic Petri nets. In order to improve the efficiency and punctuality of rail transport. A method for minimizing disruptions by managing maintenance is proposed. The paper's contribution is a scheduling algorithm that prioritizes maintenance tasks according to a dynamic criticality. This dynamic criterion incorporates real-time information provided by a supervisory rail system layer (a SCADA system). The STPN is used for modeling system operation. It supplies a mathematical framework for disturbance detection and prognosis. The presented work constitutes a first step towards adapting the digital twin concepts for the maintenance of weakly instrumented railway infrastructures. © 2024 IEEE.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

Sign Language Recognition using Spiking Neural Networks 2

Sign Language Recognition using Spiking Neural Networks

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Chaudhari, Pranav Vicente-Sola, Alex Basu, Amlan Manna, Davide L. Kirkland, Paul Caterina, Gaetano Di Department of Information and Communication Technology Manipal Institute of Technology Manipal Academy of Higher Education Manipal576104 India Neuromorphic Sensor Signal Processing Lab Centre for Image and Signal Processing Electrical and Electronic Engineering Department University of Strathclyde Glasgow United Kingdom

In recent years, research in automatic Sign Language Recognition (SLR) has undergone significant progress, serving as a founda-tional base for developing applications that aim to promote the integration of deaf individuals into society. Most of this progress is owed to the recent developments in deep learning. However, the deployment of conventional Artificial Neural Networks (ANNs) can be hindered by their requirements in terms of computational power and energy consumption. Therefore, to improve the ef-ciency of current SLR systems, in this work, we propose the use of the increasingly popular Spiking Neural Networks (SNNs), which, on the one hand, provide more energy-efficient computations than conventional ANNs and, on the other hand, are able to process temporal sequences with simpler architectures thanks to their temporal dynamics. To evaluate our method, we utilize WLASL300, the 300-word (300 classes of signs) dataset from Word-Level American Sign Language, and achieve an improvement in accuracy with the SNN (+2.70%) over the previous state-of-the-art, when working with energy-efficient spiking neurons. Furthermore, we construct a non-spiking version of the same network and evaluate it in a similar manner. Our results demonstrate how the SNN has sparser activations (25% less), thanks to the use of spiking neurons, and therefore can be implemented with a lower power requirement than an ANN version of the same architecture. This work thus demonstrates the possibility of performing SLR in a very effective and efficient way, thus opening up the development of applications that span from the automatic real-time translation of dynamic signs to remote control utilizing sign languages. © 2024 Elsevier B.V.. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Isolation Forest-Based Target Detection Algorithm for Airborne Radar 9

Machine Learning Isolation Forest-Based Target Detection Alg...

引用

9th International Conference on Intelligent Computing and signal processing, ICSP 2024

作者： Liu, Jing Zeng, Cao Juwono, Filbert H. Huang, Pengcheng Tao, Haihong Xidian University National Key Laboratory of Radar Signal Processing Xi'an China Xi'an Jiaotong-Liverpool University Department of Electrical and Electronic Engineering Suzhou China

ISBN: (纸本)9798350376548

While the advantages of airborne radar are widely recognized, it is prone to target overwhelm by clutter during detection tasks, and most traditional detectors rely on clutter mathematical models to obtain detection thresholds. This paper proposes a new machine learning isolation forest-based airborne radar target detection algorithm, fully exploiting the advantages of ensemble decision trees. The proposed algorithm first designs new feature data with feature extraction and space-time weight vector, and the new data enable separate utilization of multidimensional features, serving as inputs for the target and clutter classifier to be constructed. Then, the proposed algorithm designs a unique isolation forest-based target and clutter detector, constructing isolation forest anomaly scores for each designed feature data, and determining the presence of targets for airborne radar based on score discrimination criteria. Compared with various classical detectors, the proposed algorithm significantly enhances target detection performance, providing higher detection probabilities, and offering a new idea and direction for radar target detection. The proposed algorithm is confirmed by simulations to be effective and advantageous. © 2024 IEEE.

关键词： Radar clutter

来源：评论

学校读者我要写书评

暂无评论

Real Time Face Recognition System using Raspberry Pi4 3

Real Time Face Recognition System using Raspberry Pi4

引用

3rd International Conference on Advanced electrical engineering, ICAEE 2024

作者： Boukerche, Alaa Eddine Chelali, Fatma Zohra University of Science and Technology Houari Boumediene Usthb Faculty of Electrical Engineering Telecommunications Department Algeria University of Science and Technology Houari Boumediene Usthb Speech Communication and Signal Processing Laboratory Faculty of Electrical Engineering Algeria

ISBN: (数字)9798350349351

ISBN: (纸本)9798350349351

Modern technologies like computer vision (CV), Artificial Intelligence (AI), the internet of things (IoT), and (AIoT) Artificial Intelligence of Things have advanced in many fields, particularly surveillance systems, which need to process faces in real time to guarantee security. This paper proposed a comparative analysis for a real time face recognition system from video sequences with two architectures including traditional application using a personal computer and a Raspberry Pi, respectively. Our study offers an implementation for a real-time face recognition system employing Viola-Jones algorithm and Deep neural networks techniques such as Convolutional Neural Networks (CNN) for face detection and face recognition. Our face recognition system seeks to replace the conventional approach of keeping track of attendance by implementing a Raspberry Pi-based attendance monitoring system that can be utilized by all institutions and organizations. Significant progress has been made thanks to the use of CNN models which has allowed an accuracy rate of 94%. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Supervised machine learning-based salp swarm algorithm for fault diagnosis of photovoltaic systems

引用

Journal of engineering and Applied Science 2024年第1期71卷 12页

作者： Hichri, Amal Hajji, Mansour Mansouri, Majdi Nounou, Hazem Bouzrara, Kais Research Unit Advanced Materials and Nanotechnologies Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Kairouan Tunisia Electrical and Computer Engineering Program Texas A&M University at Qatar Doha Qatar Laboratory of Automatic Signal and Image Processing National School of Engineers of Monastir University of Monastir Monastir5019 Tunisia

The diagnosis of faults in grid-connected photovoltaic (GCPV) systems is a challenging task due to their complex nature and the high similarity between faults. To address this issue, we propose a wrapper approach called the salp swarm algorithm (SSA) for feature selection. The main objective of SSA is to extract only the most important features from the raw data and eliminate unnecessary ones to improve the classification accuracy of supervised machine learning (SML) classifiers. Subsequently, the selected features are used to train supervised machine learning (SML) techniques in distinguishing between various operating modes. To evaluate the efficiency of the technique, we used healthy and faulty data from GCPV systems that have been injected with frequent faults, 20 different types of faults were introduced, including line-to-line, line-to-ground, connectivity faults, and those affecting the operation of bay-pass diodes. These faults present diverse conditions, such as simple and multiple faults in the PV arrays and mixed faults in both arrays. The performances of the developed SSA-SML are compared with those using principal component analysis (PCA) and kernel PCA (KPCA) based SML techniques through different criteria (i.e., accuracy, recall, precision, F1 score, and computation time). The experimental findings demonstrated that the proposed diagnosis paradigm outperformed the other techniques and achieved a high diagnostic accuracy (an average accuracy greater than 99%) while significantly reducing computation time. © 2023, The Author(s).

关键词： Failure 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：