检索结果-内蒙古大学图书馆

51st International Symposium ELMAR

作者： Vilovic, Ivan Burum, Niksa Milic, Dorde Univ Dubrovnik Dubrovnik Croatia

ISBN: (纸本)9789537044107

This paper presents a comparison of results obtained from neural network training by backpropagation and particle swarm optimization (PSO) algorithms. The neural network model has been developed for field strength prediction in indoor environments. It has been already shown for neural networks as powerful tool in RF propagation prediction. It is very important to choose proper algorithm for training a neural network, so we compared BP training algorithms: gradient descent method and Levenberg- Marquardt algorithm with PSO algorithm. PSO algorithm has been shown as powerful method for global optimization in several applications. A floor of university building in Dubrovnik has been used as case for simulation and measurement of signal strength. The results show that the neural network weights converge faster with PSO than with standard BP algorithms.

关键词： Neural network Multilayer Perceptron Training algorithm backpropagation algorithm Gradient descent algorithm Levenberg-Marquardt algorithm Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Training a network of mobile neurons

Training a network of mobile neurons

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Apolloni, Bruno Bassis, Simone Valerio, Lorenzo Univ Milan Dept Comp Sci I-20122 Milan Italy Univ Milan Dept Math I-20122 Milan Italy

ISBN: (纸本)9781424496365

We introduce a new paradigm of neural networks where neurons autonomously search for the best reciprocal position in a topological space so as to exchange information more profitably. The idea that elementary processors move within a network to get a proper position is borne out by biological neurons in brain morphogenesis. The basic rule we state for this dynamics is that a neuron is attracted by the mates which are most informative and repelled by ones which are most similar to it. By embedding this rule into a Newtonian dynamics, we obtain a network which autonomously organizes its layout. Thanks to this further adaptation, the network proves to be robustly trainable through an extended version of the back-propagation algorithm even in the case of deep architectures. We test this network on two classic benchmarks and thereby get many insights on how the network behaves, and when and why it succeeds.

关键词： Acceleration Benchmark testing Biological neural networks Dynamics Layout Neurons Newtonian dynamics Training backpropagation backpropagation algorithm mobile neurons multilayer neural network multilayer perceptrons neural network training topological space

来源：评论

学校读者我要写书评

暂无评论

Utilizing Machine Learning for Indoor Localization with Multiple Wi-Fi Assistance

Utilizing Machine Learning for Indoor Localization with Mult...

引用

IEEE VTS Asia Pacific Wireless Communications Symposium (APWCS)

作者： Huang, Chung-Ruei Tsai, Ang-Hsun Lee, Chao-Yang Feng Chia Univ Dept Commun Engn Taichung Taiwan Natl Yunlin Univ Sci & Technol Dept Comp Sci & Informat Engn Touliu Yunlin Taiwan

ISBN: (纸本)9798350361711;9798350361704

This paper evaluates the efficacy of diverse indoor positioning methods, highlighting the superior performance of the backpropagation (BP) algorithm. Through extensive experimentation, we compared the Mean Square Error (MSE) and Cumulative Distribution Function (CDF) of positioning errors across different algorithms, including Fingerprinting and Triangulation. The BP algorithm exhibited significantly higher accuracy and stability, with a CDF of approximately 0.92 at a 1-meter MSE, surpassing Fingerprinting and Triangulation, which achieved CDFs of 0.77 and 0.06, respectively. Moreover, we examined the impact of varying K values in the Fingerprinting method based on K-Nearest Neighbors (KNN) and different configurations of hidden layers and neurons in the BP algorithm. Optimal performance was observed with K = 2 for Fingerprinting, yielding an MSE of 1.5 meters, and with 22 hidden layers and 47 neurons for the BP algorithm, resulting in an MSE of 0.84 meters. These findings underscore the significance of parameter optimization for enhancing positioning accuracy and suggest potential avenues for future research aimed at further enhancing indoor positioning systems.

关键词： Indoor Localization Wi-Fi Triangulation Fingerprinting backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Forecasting Indian Stock Market Using Artificial Neural Networks 4

Forecasting Indian Stock Market Using Artificial Neural Netw...

引用

4th International Conference on Computing Communication Control and Automation (ICCUBEA)

作者： Kale, Ashutosh Khanvilkar, Omkaar Jivani, Hardik Kumkar, Prathamesh Madan, Ishan Sarode, Tanuja Thadomal Shahani Engn Coll Dept Comp Engn Mumbai Maharashtra India

ISBN: (纸本)9781538652572

The objective of this research is to predict the next day's opening value of Nifty-100 index of the National Stock Exchange (NSE) using Artificial Neural Networks (ANNs). The ANN is trained using Error backpropagation Training algorithm (EBPTA). The multilayer feedforward network is trained using the present day's closing values of seven input parameters which are Gold, Silver, Copper, Crude Oil, Natural Gas and Foreign Exchange (FOREX) rates. In addition to these six rates, the closing value of Nifty-100 index was incorporated as input using Simple Moving Average (SMA) model. The relationship between each input parameter and Nifty-100 index was studied and analyzed using correlation technique. This research proves that Nifty-100 index can be predicted using ANNs.

关键词： Nifty-100 Index Artificial Neural Networks backpropagation algorithm Cross-validation Forecasting Indian Stock Market

来源：评论

学校读者我要写书评

暂无评论

Robust modulation classification techniques using cumulants and hierarchical neural networks

Robust modulation classification techniques using cumulants ...

引用

Conference on Signal Processing, Sensor Fusion, and Target Recognition XVI

作者： DeClouet, John A. Naraghi-Pour, Mort Louisiana State Univ Dept Elect & Comp Engn Baton Rouge LA 70803 USA

ISBN: (纸本)9780819466891

The problem of automatic modulation classification is to identify the modulation type of a received signal from the signal parameters. Modulation classification has both military and civilian applications and has been the subject of intensive research for more than two decades. In this paper we use a hierarchical neural network in which the first network identifies the modulation class while a second set of networks identify the constellation size (order) of that modulation class. The set of features we use include normalized standard deviations of amplitude, phase and frequency, as well as the fourth and sixth order cumulants of the signal samples. Identifying the constellation size of quadrature amplitude modulation (QAM) has been particularly difficult in the past. In this paper we introduce two new approaches for computing the features of a QAM signal. The first uses the concatenated inphase and quadrature components of the signal to compute the features. The second method maps the in-phase and quadrature components to the first quadrant of the constellation by calculating the absolute value of each separately. The mean of the resulting constellation points is then subtracted before calculating the features. Simulation results are presented for classification of several digital modulation schemes including FSK, PSK, ASK and QAM. Our results show that the proposed method significantly improves the classification error.

关键词： modulation classification backpropagation algorithm hierarchical neural networks

来源：评论

学校读者我要写书评

暂无评论

Classification Techniques for Texture Images Using Neuroph Studio 5th

Classification Techniques for Texture Images Using Neuroph S...

引用

5th International Conference on Soft Computing for Problem Solving (SocProS)

作者： Mahani, Priyanka Kulshreshtha, Akanksha Goswami, Anil Kumar Dronacharya Coll Engn Elect & Comp Engn Dept Gurgaon India DRDO DTRL Lab Metcalfe House New Delhi India

ISBN: (纸本)9789811004513;9789811004506

With the widespread scope of image processing in fields such as ground classification, segmentation of satellite images, biomedical surface inspection and content-based image retrieval (CBIR), texture analysis is an important domain with a wide scope. The process of texture analysis comprises the following important steps: texture classification, segmentation and synthesis. Texture is a significant property of images which is difficult to define even though the human eye may recognize it with ease. Texture classification has remained an intangible pattern recognition task despite numerous studies. The prime issue in any texture classification application is how to select the features and which features to consider for representing texture. Another major issue remains the type of metric to be used for comparing the feature vectors. The traditional way of texture classification is to convert the texture image into a vector representing the features using a set of filters. This is followed by classification with a few smoothening steps involved in between. This paper outlines a picture of the basic features of an image as texture, colour and shape which are to be extracted to form the feature vector. The concept of applying Machine learning for the purpose of classification is explored and implemented. The use of Soft Computing Technique-Artificial Neural Networks is illustrated for the purpose of classification. The texture features are extracted using the GLCM method and used as input and fed to the neural network. The algorithm used in training the neural networks is the traditional backpropagation algorithm. The results show which configuration of the multi-layer feedforward architecture is best suited according to our experimental set-up.

关键词： Content-based image retrieval Classification Artificial neural networks backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Signal Processing of Distributed Optoacoustic Sensors by Means of Neural Networks in the Automotive Transport Monitoring Problem

引用

Mathematical Models and Computer Simulations 2024年第5期16卷 667-675页

作者： Nazarenko, P.A. Levashkin, S.P. Zakharova, O.I. Ivanov, K.N. Kushukov, S.V. Artificial Intelligence Research Lab (AIRL) Povolzhskiy State University of Telecommunications and Informatics (PSUTI) Samara Russian Federation

Artificial neural network (ANN) models are used as a tool for an automotive transport monitoring. The solution of the problem of recognition of distributed optoacoustic sensor signals generated by vehicles using ANNs is considered. Signals features and signals preliminary processing are described. The ANN architecture for the vehicles generated signals recognition is selected. The architecture of the ANN of vehicles signal recognition, including heavy tracks signals, has single layer with two hundred and one input and one or two outputs. The ANN is designed using the Python programming language, Scikit-Learn, Keras and NumPy libraries. The ANN training patterns, the training results and the trained ANN practical application are described. The recommendations for further research in the field of using ANNs of various architectures for recognizing vehicle signals using distributed optoacoustic sensors are given. The study results are important for road traffic monitoring, as well as other areas of the distributed optoacoustic sensor applications. © Pleiades Publishing, Ltd. 2024.

关键词： artificial neural networks backpropagation algorithm big data space dimensionality reduction Keras machine learning pattern recognition perceptron Python Tens-orFlow training patterns

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE APPROACH FOR SPARSE REPRESENTATIONS USING THE LOCALLY COMPETITIVE algorithm FOR AUDIO 31

ADAPTIVE APPROACH FOR SPARSE REPRESENTATIONS USING THE LOCAL...

引用

IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)

作者： Bahadi, Soufiyan Rouat, Jean Plourde, Eric Univ Sherbrooke NECOTIS Res Lab Sherbrooke PQ Canada

ISBN: (纸本)9781728163383

Gammachirp filterbank has been used to approximate the cochlea in sparse coding algorithms. An oriented grid search optimization was applied to adapt the gammachirp's parameters and improve the Matching Pursuit (MP) algorithm's sparsity along with the reconstruction quality. However, this combination of a greedy algorithm with a grid search at each iteration is computationally demanding and not suitable for real-time applications. This paper presents an adaptive approach to optimize the gammachirp's parameters but in the context of the Locally Competitive algorithm (LCA) that requires much fewer computations than MP. The proposed method consists of taking advantage of the LCA's neural architecture to automatically adapt the gammachirp's filterbank using the backpropagation algorithm. Results demonstrate an improvement in the LCA's performance with our approach in terms of sparsity, reconstruction quality, and convergence time. This approach can yield a significant advantage over existing approaches for real-time applications.

关键词： Gammachirp Sparse coding Locally Competitive algorithm Spikegram backpropagation algorithm Real-time application

来源：评论

学校读者我要写书评

暂无评论

Training quasi-ARX neural network model by homotopy approach

Training quasi-ARX neural network model by homotopy approach

引用

SICE 2004 Annual Conference

作者： Hu, JL Lu, XB Hirasawa, K Waseda Univ Grad Sch Informat Prod & Syst Wakamatsu Ku Fukuoka 8080135 Japan

ISBN: (纸本)4907764227

Quasi-ARX neural networks (NN) are NN based nonlinear models that not only have linear structures similar to linear ARX models, but also have useful interpretation in part of their parameters. However when applying an ordinary backpropagation (BP) for the training, it has potential risk that the BP algorithm is stuck at a local minimum, which results in a poorly trained model. In this paper, a homotopy continuation method is introduced to improve the convergence performance of BP training. The idea is to start the BP training with the criterion function for linear ARX model, which is gradually deformed first into one for quasi-ARX NN model with linear node functions, and then into the actual one for quasi-ARX NN with sigmoid node functions. By building the deformation into a usual recursive procedure for BP training of quasi-ARX NN model with adaptable node functions so that the proposed homotopy based BP algorithm is able to achieve improved convergence performance without much increase in the computation load. Numerical simulation results show that the proposed homotopy based BP has better performance than an ordinary BP.

关键词： neural network linear ARX model homotopy continuation method local minimum backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Analysis and Forecasting of Individual Stock Prices of Various Constituents in NIFTY 50 1

Analysis and Forecasting of Individual Stock Prices of Vario...

引用

1st International Conference on Secure Cyber Computing and Communications (ICSCCC)

作者： Gupta, Deepak Kumar Singh, Raj Mohan Jain, Vikalp Ravi Dr BR Ambedkar NIT Dept CSE Jalandhar Punjab India

ISBN: (纸本)9781538663738

Financial forecasting is one of the trending research going on in the current market. Researchers are mainly focused on the parameters that are affecting share market. Presently researchers are able to discover the relation between macroeconomic variables and different indices. We are driving our research by discovering the relationship between macroeconomic variables and individual share prices, but before proceeding for the prediction, we firstly analyze each individual company and their dependence on raw products for the improvement in predicting the individual share prices. Each individual companies produce different units used by consumers. To compose those elements companies necessitate raw materials and because of those materials their share prices are being affected. We did an analysis that how strongly they need those raw materials in their production and how these companies are related. From that relation, we are able to parameterize our neural network for the prediction of different individual companies share prices.

关键词： Artificial Neural Network Share price prediction NIFTY50 backpropagation algorithm

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：