A Hardware Accelerator for Convolutional Neural Network Using Fast Fourier Transform

2019 ◽  
pp. 28-36
Author(s):  
S. Kala ◽  
Babita R. Jose ◽  
Debdeep Paul ◽  
Jimson Mathew
Keyword(s):  
Neural Network ◽  
Fourier Transform ◽  
Fast Fourier Transform ◽  
Convolutional Neural Network ◽  
Hardware Accelerator

scholarly journals Development of Deep Convolutional Neural Network with Adaptive Batch Normalization Algorithm for Bearing Fault Diagnosis

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Chao Fu ◽  
Qing Lv ◽  
Hsiung-Cheng Lin
Keyword(s):  
Neural Network ◽  
Fourier Transform ◽  
Fault Diagnosis ◽  
Fast Fourier Transform ◽  
Convolutional Neural Network ◽  
Deep Convolutional Neural Network ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Batch Normalization ◽  
Fault Information

It is crucial to carry out the fault diagnosis of rotating machinery by extracting the features that contain fault information. Many previous works using a deep convolutional neural network (CNN) have achieved excellent performance in finding fault information from feature extraction of detected signals. They, however, may suffer from time-consuming and low versatility. In this paper, a CNN integrated with the adaptive batch normalization (ABN) algorithm (ABN-CNN) is developed to avoid high computing resource requirements of such complex networks. It uses a large-scale convolution kernel at the grassroots level and a multidimensional 3 × 1 small convolution nuclear. Therefore, a fast convergence and high recognition accuracy under noise and load variation environment can be achieved for bearing fault diagnosis. The performance results verify that the proposed model is superior to Support Vector Machine with Fast Fourier Transform (FFT-SVM) and Multilayer Perceptron with Fast Fourier Transform (FFT-MLP) models and Deep Neural Network with Fast Fourier Transform (FFT-DNN).

scholarly journals A Frequency Pattern Mining Model Based on Deep Neural Network for Real-Time Classification of Heart Conditions

Healthcare ◽  
2020 ◽  
Vol 8 (3) ◽  
pp. 234 ◽  
Author(s):  
Hyun Yoo ◽  
Soyoung Han ◽  
Kyungyong Chung
Keyword(s):  
Neural Network ◽  
Big Data ◽  
Fourier Transform ◽  
Fast Fourier Transform ◽  
Real Time ◽  
Normal Control ◽  
Input Data ◽  
Deep Neural Network ◽  
Pattern Mining ◽  
F Measure

Recently, a massive amount of big data of bioinformation is collected by sensor-based IoT devices. The collected data are also classified into different types of health big data in various techniques. A personalized analysis technique is a basis for judging the risk factors of personal cardiovascular disorders in real-time. The objective of this paper is to provide the model for the personalized heart condition classification in combination with the fast and effective preprocessing technique and deep neural network in order to process the real-time accumulated biosensor input data. The model can be useful to learn input data and develop an approximation function, and it can help users recognize risk situations. For the analysis of the pulse frequency, a fast Fourier transform is applied in preprocessing work. With the use of the frequency-by-frequency ratio data of the extracted power spectrum, data reduction is performed. To analyze the meanings of preprocessed data, a neural network algorithm is applied. In particular, a deep neural network is used to analyze and evaluate linear data. A deep neural network can make multiple layers and can establish an operation model of nodes with the use of gradient descent. The completed model was trained by classifying the ECG signals collected in advance into normal, control, and noise groups. Thereafter, the ECG signal input in real time through the trained deep neural network system was classified into normal, control, and noise. To evaluate the performance of the proposed model, this study utilized a ratio of data operation cost reduction and F-measure. As a result, with the use of fast Fourier transform and cumulative frequency percentage, the size of ECG reduced to 1:32. According to the analysis on the F-measure of the deep neural network, the model had 83.83% accuracy. Given the results, the modified deep neural network technique can reduce the size of big data in terms of computing work, and it is an effective system to reduce operation time.

scholarly journals Identifikasi Penyakit Diabetes Mellitus Melalui Nafas Berbasis Sensor Gas Dengan Metode Fast Fourier Transform dan Backpropagation

2018 ◽  
Vol 2 (02) ◽  
pp. 85-91
Author(s):  
Mohammad Hafiz Hersyah ◽  
Andrizal Andrizal ◽  
Revinessia Revinessia
Keyword(s):  
Neural Network ◽  
Diabetes Mellitus ◽  
Fourier Transform ◽  
Hydrogen Sulfide ◽  
Fast Fourier Transform ◽  
Success Rate ◽  
The Neural Network ◽  
Random Samples ◽  
Backpropagation Method ◽  
Bad Breath

The purpose of this research is to detect whether a person has diabetes mellitus or not. In people with diabetes mellitus uncontrolled will result in a decline in the rate of saliva that results in bad breath. The system uses the sensor TGS 2602 and MQ 4. It's function is to detect the levels of Hydrogen Sulfide and Methan in a person’s breath. The decision is made by using the neural network with a backpropagation method. The result for 5 (five) tests of diabetes mellitus samples can be detected with a success rate of 80%, whereas using random samples, the test detected with detected with a success rate of 80% samples that didn’t contain diabetes mellitus. This system could provide a solution for testing if a person is suffering from diabetes mellitus

scholarly journals Intelligent Automatic V6 and V8 Engine Sound Detection Based on Artificial Neural Network

2019 ◽  
Vol 130 ◽  
pp. 01035 ◽  
Author(s):  
Wenny Vincent ◽  
Astuti Winda ◽  
Mahmud Iwan Solihin
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fourier Transform ◽  
Fast Fourier Transform ◽  
Intelligent System ◽  
Recorded Sound ◽  
Sound Detection ◽  
Testing Accuracy ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

The sound of V6 or V8 engines has its own cultural appeal that cannot be replaced by the modern four-cylinder naturally aspirated or turbocharged engines. The identification of the type of engine by the sound is not an easy task, even for the professionals. An intelligent system that can identify V6 to V8 engines from various cars will give an insight of the features in the engine sounds that characterized the two different engines. In this work, an Artificial Neural Network (ANN) approach is applied for identifying cylinder of the engine based on the engine sound identification is proposed. The recorded sound of the engine is then processed in order to get some features which later be used in the proposed system. The Fast Fourir Transform (FFT) is adopted as a feature and later used as input to the Artificial Neural Network (ANN) based identifier. The Experimental results confirm the effectiveness of the proposed intelligent automatic six cylinder and eight cylinder engine based on Fast Fourier Transform (FFT) and Artificial Neural Network (ANN), since it resulting the training and testing accuracy of 100 % and 100 %, respectively.

Real Time Harmonic Load Identification Based on Fast Fourier Transform and Artificial Neural Network

2021 ◽  
Vol 16 (3) ◽  
pp. 220
Author(s):  
Dimas Okky Anggriawan ◽  
Aidin Amsyar ◽  
Aji Akbar Firdaus ◽  
Endro Wahjono ◽  
Indhana Sudiharto ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fourier Transform ◽  
Fast Fourier Transform ◽  
Real Time ◽  
Harmonic Load ◽  
Load Identification ◽  
Time Harmonic ◽  
Artificial Neural
Sign in / Sign up

Export Citation Format

Share Document