scholarly journals Determination of Chewing Count from Video Recordings Using Discrete Wavelet Decomposition and Low Pass Filtration

Sensors ◽  
2021 ◽  
Vol 21 (20) ◽  
pp. 6806
Author(s):  
Sana Alshboul ◽  
Mohammad Fraiwan
Keyword(s):  
Wavelet Decomposition ◽  
Smart Devices ◽  
Percentage Error ◽  
Discrete Wavelet ◽  
Pass Filter ◽  
Low Pass Filter ◽  
Video Recordings ◽  
Area Of Interest ◽  
Discrete Wavelet Decomposition ◽  
Low Pass

Several studies have shown the importance of proper chewing and the effect of chewing speed on the human health in terms of caloric intake and even cognitive functions. This study aims at designing algorithms for determining the chew count from video recordings of subjects consuming food items. A novel algorithm based on image and signal processing techniques has been developed to continuously capture the area of interest from the video clips, determine facial landmarks, generate the chewing signal, and process the signal with two methods: low pass filter, and discrete wavelet decomposition. Peak detection was used to determine the chew count from the output of the processed chewing signal. The system was tested using recordings from 100 subjects at three different chewing speeds (i.e., slow, normal, and fast) without any constraints on gender, skin color, facial hair, or ambience. The low pass filter algorithm achieved the best mean absolute percentage error of 6.48%, 7.76%, and 8.38% for the slow, normal, and fast chewing speeds, respectively. The performance was also evaluated using the Bland-Altman plot, which showed that most of the points lie within the lines of agreement. However, the algorithm needs improvement for faster chewing, but it surpasses the performance of the relevant literature. This research provides a reliable and accurate method for determining the chew count. The proposed methods facilitate the study of the chewing behavior in natural settings without any cumbersome hardware that may affect the results. This work can facilitate research into chewing behavior while using smart devices.

scholarly journals Klasterisasi Kerusakan Bearing Motor Induksi 3 Fasa Menggunakan Metode Transformasi Wavelet Diskrit dan K-Medoids

ELKHA ◽  
2020 ◽  
Vol 12 (2) ◽  
pp. 54
Author(s):  
Eska Rizqi Naufal ◽  
Gigih Priyandoko ◽  
Fachrudin Hunaini
Keyword(s):  
Induction Motor ◽  
Extraction Method ◽  
Data Extraction ◽  
Working Environment ◽  
Discrete Wavelet ◽  
Clustering Method ◽  
Pass Filter ◽  
Low Pass Filter ◽  
Group Data ◽  
Low Pass

The 3 phase induction motor is a reliable and strong motor also has cheap price. However induction motor are also vulnerable, from the result of survey conducted by Electric Power Research Institute (EPRI), there are 41% cases of damage occur in the bearing caused by working environment condition, bearing age, and several other factors. Bearing fault is not easily to identified, with applying the data extraction method using the Discrete Wavelet Transform (DWT) and the K-Medoids clustering method will facilitate the identification process. The extraction method will pass the data in the form of current signals into the digital filter (Low Pass Filter and High Pass Filter) to be mapped into the region of frequency and time simultaneously, and clustering method will group data based on certain characteristics. Based on the clustering tests that have been done on the 3 phase induction motor current signal data with 3 bearing conditions, the Discrete Wavelet Transformation with mother wavelet bior1.1 decomposition level 2 and K-Medoids produce an accuracy rate of 86.8%.

Treatment of Noise in Experimental Transport Measurements Plots With Discrete Wavelet Transforms

2009 ◽  
Author(s):  
Rube´n Panta Pazos
Keyword(s):  
Wavelet Transform ◽  
Wavelet Transforms ◽  
Transport Theory ◽  
Discrete Wavelet ◽  
Transform Method ◽  
Pass Filter ◽  
Low Pass Filter ◽  
Low Pass ◽  
Thresholding Algorithm ◽  
High Pass

In this work it is applied the wavelet transform method [2] in order to reduce diverse type of noises of experimental measurement plots in transport theory. First, suppose that a problem is governed by the transport equation for neutral particles, and an unknown perturbation occurs. In this case, the perturbation can be associated to the source, or even to the flux inside the domain X. How is the behavior of the perturbed flux in relation to the flux without the perturbation? For that, we employ the wavelet transform method in order to compress the angular flux considered as a 1D, or n-th dimensional signal ψ. The compression of this signal can be performed up to some a convenient order (that depends of the length of the signal). Now, the transport signal is decomposed as [9, 11]: ψ=〈am|dm|dm−1|dm−2|⋯|d2|d1〉 where ak represents the sub signal of k-th level generated by the low-pass filter associated to the discrete wavelet transform (DWT) chosen, and dk the sub signal of k-th level generated by the high-pass filter associated to the same DWT. It is applied basically the Haar, Daub4 and Coiflet wavelets transforms. Indeed, the sub signal am cumulates the energy, for this work of order 96% of the original signal ψ. A thresholding algorithm provides treatment for the noise, with significant reduction in the compressed signal. Then, it is established a comparison with a base of data in order to identify the perturbed signal. After the identification, it is recomposed the signal applying the inverse DWT. Many assumptions can be established: the rate signal-to-noise is properly high, the base of data must contain so many perturbed signals all with the same level of compression. The problem considered is for perturbations in the signal. For measurements the problem is similar, but in this case the unknown perturbations are generated by the apparatus of measurements, problems in experimental techniques, or simply by random noises. With the same above assumptions, the DWT is applied. For the identification, it is used a method evolving statistical and metric techniques. It is given some results obtained with an algebraic computer system.

scholarly journals Personnel Identification System Using the Wireless Channel Characteristics and Machine Learning

CONVERTER ◽  
2021 ◽  
pp. 70-89
Author(s):  
Yong Li, Jie Zhao,
Keyword(s):  
Short Term Memory ◽  
Wireless Channel ◽  
Human Gait ◽  
Identification System ◽  
Discrete Wavelet ◽  
Pass Filter ◽  
Low Pass Filter ◽  
Identity Recognition ◽  
Walking Gait ◽  
Low Pass

In the presence of a Wi-Fi network, movements of individuals lead to changes in the channel state information (CSI) of the Wi-Fi network. Thus, it is possible to use CSI to identify specific individuals based on walking gait and under movements. We have built a hardware system to collect CSI and developed CSI real-time acquisition and visualization software. We further improve results by preprocessing the CSI to remove noise by outlier removal, a low-pass filter, and a discrete wavelet transform. For identity recognition, we propose a parallel learning structure using a convolutional neural network (CNN) and bidirectional long-term and short-term memory network to extract amplitude and time sequence features of human gait at the same time. We then classify the two gait features using Softmax function to identify individuals. Our identity recognition experiment with 30 people yielded a maximum accuracy of 98.7% with our device and software. The system has a value of application in the field of smart home and intrusion detection.

Design of Programmable Wideband Low Pass Filter with Continuous-Time/Discrete-Time Hybrid Architecture

2017 ◽  
Vol E100.C (10) ◽  
pp. 858-865 ◽  
Author(s):  
Yohei MORISHITA ◽  
Koichi MIZUNO ◽  
Junji SATO ◽  
Koji TAKINAMI ◽  
Kazuaki TAKAHASHI
Keyword(s):  
Discrete Time ◽  
Continuous Time ◽  
Hybrid Architecture ◽  
Pass Filter ◽  
Low Pass Filter ◽  
Low Pass

ANALYSIS AND IMPROVEMENT TECHNIQUES FOR THE TRANSFER FUNCTION OF A PLANAR LOW - PASS FILTER

2016 ◽  
Vol 15 (12) ◽  
pp. 2579-2586
Author(s):  
Adina Racasan ◽  
Calin Munteanu ◽  
Vasile Topa ◽  
Claudia Pacurar ◽  
Claudia Hebedean
Keyword(s):  
Transfer Function ◽  
Pass Filter ◽  
Low Pass Filter ◽  
Low Pass

scholarly journals Simulating Elliptic Low-pass Filter based on MOCCCII

2020 ◽  
Vol 965 ◽  
pp. 012037
Author(s):  
Nanan Chomnak ◽  
Siradanai Srisamranrungrueang ◽  
Natapong Wongprommoon
Keyword(s):  
Pass Filter ◽  
Low Pass Filter ◽  
Low Pass
Sign in / Sign up

Export Citation Format

Share Document