scholarly journals An Effective Optimization-Based Neural Network for Musical Note Recognition

2019 ◽  
Vol 28 (1) ◽  
pp. 173-183
Author(s):  
Allabakash Isak Tamboli ◽  
Rajendra D. Kokate
Keyword(s):  
Neural Network ◽  
Fundamental Frequency ◽  
Audio Signal ◽  
Musical Note ◽  
Pitch Estimation ◽  
Musical Pitch ◽  
Classification Framework ◽  
Sound Separation

Abstract Musical pitch estimation is used to recognize the musical note pitch or the fundamental frequency (F0) of an audio signal, which can be applied to a preprocessing part of many applications, such as sound separation and musical note transcription. In this work, a method for musical note recognition based on the classification framework has been designed using an optimization-based neural network (OBNN). A broad range of survey and research was reviewed, and all revealed the methods to recognize the musical notes. An OBNN is used here in recognizing musical notes. Similarly, we can progress the effectiveness of musical note recognition using different methodologies. In this document, the most modern investigations related to musical note recognition are effectively analyzed and put in a nutshell to effectively furnish the traits and classifications.

scholarly journals Using a Low-Power Spiking Continuous Time Neuron (SCTN) for Sound Signal Processing

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1065
Author(s):  
Moshe Bensimon ◽  
Shlomo Greenberg ◽  
Moshe Haiut
Keyword(s):  
Neural Network ◽  
Network Structure ◽  
Analog Circuits ◽  
Continuous Time ◽  
Spiking Neurons ◽  
Spiking Neural Network ◽  
Sound Classification ◽  
Classification Framework ◽  
Neural Network Structure ◽  
Simple Analog

This work presents a new approach based on a spiking neural network for sound preprocessing and classification. The proposed approach is biologically inspired by the biological neuron’s characteristic using spiking neurons, and Spike-Timing-Dependent Plasticity (STDP)-based learning rule. We propose a biologically plausible sound classification framework that uses a Spiking Neural Network (SNN) for detecting the embedded frequencies contained within an acoustic signal. This work also demonstrates an efficient hardware implementation of the SNN network based on the low-power Spike Continuous Time Neuron (SCTN). The proposed sound classification framework suggests direct Pulse Density Modulation (PDM) interfacing of the acoustic sensor with the SCTN-based network avoiding the usage of costly digital-to-analog conversions. This paper presents a new connectivity approach applied to Spiking Neuron (SN)-based neural networks. We suggest considering the SCTN neuron as a basic building block in the design of programmable analog electronics circuits. Usually, a neuron is used as a repeated modular element in any neural network structure, and the connectivity between the neurons located at different layers is well defined. Thus, generating a modular Neural Network structure composed of several layers with full or partial connectivity. The proposed approach suggests controlling the behavior of the spiking neurons, and applying smart connectivity to enable the design of simple analog circuits based on SNN. Unlike existing NN-based solutions for which the preprocessing phase is carried out using analog circuits and analog-to-digital conversion, we suggest integrating the preprocessing phase into the network. This approach allows referring to the basic SCTN as an analog module enabling the design of simple analog circuits based on SNN with unique inter-connections between the neurons. The efficiency of the proposed approach is demonstrated by implementing SCTN-based resonators for sound feature extraction and classification. The proposed SCTN-based sound classification approach demonstrates a classification accuracy of 98.73% using the Real-World Computing Partnership (RWCP) database.

Motor Broken-Bar Fault Diagnosis Based on Park Vector and Wavelet Neural Network

2011 ◽  
Vol 382 ◽  
pp. 163-166
Author(s):  
Qing Xin Zhang ◽  
Jin Li ◽  
Hai Bin Li ◽  
Chong Liu
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Fundamental Frequency ◽  
Wavelet Packet ◽  
Frequency Component ◽  
Wavelet Neural Network ◽  
Simulation Software ◽  
Monitoring Methods ◽  
Stator Current ◽  
Fundamental Frequency Component

In the technology of motor fault diagnosis, current monitoring methods have become a new trend in motor fault diagnosis. This paper presents a motor fault diagnosis method based on Park vector and wavelet neural network. This method uses the stator current as the object of study. Firstly, it uses Park vector to deal with the stator current and filter out fundamental frequency component, thus the characteristics component of motor broken-bar will be separated from fundamental frequency component; Secondly, it uses five layers wavelet packet decomposition to pick up fault characteristic signal; Finally, we distinguish the fault by BP neural network, and use the simulation software of MATLAB to realize it. The test results show that: This method can detect the existence of motor broken-bar fault, and has a good value in engineering.

scholarly journals Robot Communication: Network Traffic Classification Based on Deep Neural Network

2021 ◽  
Vol 15 ◽  
Author(s):  
Mengmeng Ge ◽  
Xiangzhan Yu ◽  
Likun Liu
Keyword(s):  
Neural Network ◽  
Network Traffic ◽  
Short Term Memory ◽  
Traffic Classification ◽  
Classification Framework ◽  
Network Traffic Classification ◽  
Scalar Input ◽  
Memory Network ◽  
Encrypted Traffic ◽  
Robot Communication

With the rapid popularization of robots, the risks brought by robot communication have also attracted the attention of researchers. Because current traffic classification methods based on plaintext cannot classify encrypted traffic, other methods based on statistical analysis require manual extraction of features. This paper proposes (i) a traffic classification framework based on a capsule neural network. This method has a multilayer neural network that can automatically learn the characteristics of the data stream. It uses capsule vectors instead of a single scalar input to effectively classify encrypted network traffic. (ii) For different network structures, a classification network structure combining convolution neural network and long short-term memory network is proposed. This structure has the characteristics of learning network traffic time and space characteristics. Experimental results show that the network model can classify encrypted traffic and does not require manual feature extraction. And on the basis of the previous tool, the recognition accuracy rate has increased by 8%

Abstract P365: Blood Pressure Evaluation From Ppg Signal Analysis and Artificial Neural Network

Hypertension ◽  
2017 ◽  
Vol 70 (suppl_1) ◽  
Author(s):  
Francesco Lamonaca ◽  
Vitaliano Spagnuolo ◽  
Serena De Prisco ◽  
Domenico L Carnì ◽  
Domenico Grimaldi
Keyword(s):  
Neural Network ◽  
Blood Pressure ◽  
Artificial Neural Network ◽  
Audio Signal ◽  
Hardware Interface ◽  
Validation Procedure ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
The Time Domain ◽  
And Storage

The analysis of the PPG signal in the time domain for the evaluation of the blood pressure (BP) is proposed. Some features extracted from the PPG signal are used to train an Artificial Neural Network (ANN) to determine the function that fit the target systolic and diastolic BP. The data related to the PPG signals and BP used in the analysis are provided by the Multi-parameter Intelligent Monitoring in Intensive Care (MIMIC II) database. The pre-analysis of the signal to remove inconsistent data is also proposed. A set of 1750 valid pulse is considered. The 80% of the input samples is used for the training of the network. Instead, the 10% of the input data are used for the validation of the network and 10% for final test of this last. The results show as the error for both the systolic and diastolic BP evaluation is included in the range of ±3 mmHg. Tab.1 shows the results for 20 PPG pulses randomly selected analyzed together with the systolic and diastolic blood pressure furnished by MIMC and evaluated by the trained ANN. Tab.1 experimental results comparing MIMIC and the ANN results. Moreover, a suitable hardware to validate the ANN with the sphygmomanometer is designed and realized. This hardware allows clinicians to collect data according to the requirements of the validation procedure. With the sphygmomanometer the systolic and diastolic values are referred to two different PPG pulses. As a consequence, it is proposed a new hardware interface allowing the synchronized acquisition and storage of the PPG signal and clinician voice. For the validation, the clinician: (i) evaluates the BP on both the arms and assesses that no significant differences occur; (ii) plugs the PPG sensor on the finger of one arm; (iii) starts the recording of both the PPG signal and the audio signal; (iv) evaluates the BP on the other arm with sphygmomanometer and says the systolic and diastolic values when detected. Through suitable post processing algorithm, the Systolic and Diastolic values are associated to the corresponding PPG Pulses. Following this procedure, the dataset to further validate the ANN according the standard is obtained. Once the ANN is validated it will be implemented on smartphone to have always in the pocket a reliable measurement system for Blood Pressure, oximetry and heart rate.

scholarly journals Development of a smart system for diagnosing the operating conditions of a helicopter prototype via vibrations analysis

2021 ◽  
Vol 10 (12) ◽  
pp. e304101220546
Author(s):  
João Manoel de Oliveira Neto ◽  
Andersson Guimarães Oliveira ◽  
João Vitor Lira de Carvalho Firmino ◽  
Marcelo Cavalcanti Rodrigues ◽  
Antônio Almeida Silva ◽  
...  
Keyword(s):  
Neural Network ◽  
Fundamental Frequency ◽  
Vibration Analysis ◽  
Vibration Amplitude ◽  
Operating Conditions ◽  
The Other ◽  
Smart System ◽  
Wind Speeds ◽  
Hover Flight ◽  
Artificial Neural Network Ann

In the forward flight, wind loads affect the helicopters and cause vibration. This paper analyzes the behavior of a helicopter prototype composed by two blades when subjected to a front wind load, similar to the forwarding flight condition. An Artificial Neural Network (ANN) processes the experimental data in order to identify the pattern of its dynamic behavior. The tests led to Vibration analysis for different wind speeds. Also, the data indicates that vibration amplitude increases when the blades are subjected to the fundamental frequency and its first harmonic on tests conducted without rotor plane tilt (hover flight). On the other hand, the second test performs a 5-degree tilt on the rotor disc. In this test, the vibration amplitude decreased in the fundamental frequency, and the amplitude related to the first harmonic increased. The ANN achieved 100% efficiency in recognizing the flight conditions of the prototype.

scholarly journals Music Waveform Analysis Based on SOM Neural Network and Big Data

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Xinmei Zhang
Keyword(s):  
Neural Network ◽  
Big Data ◽  
Audio Signal ◽  
The Self ◽  
Waveform Analysis ◽  
Self Organizing Map ◽  
Matching Method ◽  
Emotion Model ◽  
Som Neural Network ◽  
First Time

Music is an indispensable part of our life and study and is one of the most important forms of multimedia applications. With the development of deep learning and neural network in recent years, how to use cutting-edge technology to study and apply music has become a research hotspot. Music waveform is not only the main form of music frequency but also the basis of music feature extraction. This paper first designs a method of note extraction based on the fast Fourier transform principle of the audio signal packet route under the self-organizing map (SOM neural network) which can accurately extract the musical features of the note, such as amplitude, loudness, period, and so on. Secondly, the audio segments are divided into summary by adding window moving matching method, and the music features such as amplitude, loudness, and period of each bar are obtained according to the performance of audio signal in each bar. Finally, according to the similarity of the audio music theory of the adjacent summary of each bar, the audio segments are divided, and the music features of each segment are obtained. The traditional recurrent neural network (RNN) is improved, and the SOM neural network is used to recognize the audio emotion features. The final experimental results show that the proposed method based on SOM neural network and big data can effectively extract and analyze music waveform features. Compared with previous studies, this paper creatively proposed a new algorithm, which can more accurately and quickly extract and analyze the data sound waveform, and used SOM neural network to analyze the emotion model contained in music for the first time.

Sign in / Sign up

Export Citation Format

Share Document