Classification of materials by acoustic signal processing in real time for NAO robots

López-Caudana, Edgar; Quiroz, Omar; Rodríguez, Adriana Morales; Yépez, Luis; Ibarra, David

doi:10.1177/1729881417714996

Cited by 15 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The spectrogram script implemented in the python program uses Fast Fourier Transform. This was chosen since many studies proved its robustness for classification and segmentation even when the environment is noisy (Lopez-Caudana et al, 2017;Rahmawati et al, 2019). Moreover, the use of spectrogram in classifying harmonic signals has been found out to be accurate, fast, and cost-efficient (Jopri et al, 2017).…”

Section: Methodsmentioning

confidence: 99%

Coconut Maturity Detector Using Spectrogram and Convolutional Neural Network

Abadies,

Romulo,

Arboleda

et al. 2024

Preprint

View full text Add to dashboard Cite

Coconut is an important multipurpose crop wherein different stages of its maturity are used for different products. Traditional approach of its classification use sound formed by tapping the fruit, and the tapper will base its judgment through the sound he heard. The procedure was highly subjective and attempts had been made by other researchers to automate and classify the adulthood of the coconut objectively. Nowadays, deep learning techniques are being utilized to solve classification problems. One such method is Convolutional Neural Network (CNN) that takes raw pixel data, learns to extract features, and ultimately classifies the input. In this study, a portable device was developed that takes audio signals generated from tapping the fruit mechanically. This audio clip was converted to spectrogram and was used as input to a LeNet CNN architecture. We argue that CNN classifier has improved accuracy compared to the non-deep learning system. Our evaluation confirmed that the use of CNN had improved the accuracy of classifying coconut by about 15%.

show abstract

Section: Methodsmentioning

confidence: 99%

Coconut Maturity Detector Using Spectrogram and Convolutional Neural Network

Abadies,

Romulo,

Arboleda

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The variation in velocities with pressure is nonmonotonic. There have been ongoing attempts to classify materials by acoustic signals in developing humanoid robots' performances [109]. According to the sound velocity classification [109,110], our compound possesses low velocity.…”

Section: Acoustic Propertiesmentioning

confidence: 99%

“…There have been ongoing attempts to classify materials by acoustic signals in developing humanoid robots' performances [109]. According to the sound velocity classification [109,110], our compound possesses low velocity. Such low sound velocity solids are useful as low thermal conductivity materials.…”

Section: Acoustic Propertiesmentioning

confidence: 99%

Solid Waste Disposal Scenario of Three Ladies’ Halls in the University of Chittagong, Chattogram, Bangladesh

Naher

Ahsan

2023

Am. J. Agric. Sci. Eng. Technol.

View full text Add to dashboard Cite

University of Chittagong (CU) is well known for its beautiful green campus. It had 11 student halls (plus two were under construction), of which three were ladies’ halls named (Shamsun Nahar, Pritilata and Deshnetri Begum Khaleda Zia). But, due to lack of a proper waste management plan, wastes were found to be scattered in open areas of ladies’ halls premises. So, to protect the environmental quality of three ladies’ halls a research work has conducted during June 2012 to March 2013. Here researcher try to determine the waste generation rates, their physical composition and characterized them. At that time data about disposed wastes were collected weekly from kitchen, dining, canteen, bathroom, and halls premises at 8.00 to 11.00 am and wastes were measured by using weighing machine in kilogram (kg). Based on sources, wastes were categorized mainly on four types, such as: (1) kitchen waste, (2) dining and canteen wastes, (3) bathroom waste, and (4) others (veranda, corridor, and in and around the halls’ campus) wastes. Overall, 18,505.0 kg wastes were disposed from different sources and among them 10,406.0 kg (i.e., 56.24%) were from kitchen, 1,218.5 kg (i.e., 6.59 %) from dining and canteen, 1,570.5 kg (i.e., 8.49 %) from bathroom and 5,310.0 kg (i.e., 28.68 %) from others sources. On an average each student of 3 ladies’ halls disposed 0.029 kg waste per day that gave a total of 8.520 kg wastes during the 10 months of study period. The campus of The University of Chittagong is well known as a habitat of different types of wild animals. So, monthly waste dumping sites were visited and the wild animals those were seen eating foods from dumping wastes were identified with the help of field guides (Section e.g., Grimmett et al., 2009; Ahmed et al., 2009).

show abstract

“…Fourier Transform is transformation development to Discreet Fourier Transform (DFT) with a purpose to improve the speed in discreet data and turn it into fourier row. Fourier transformation is a mathematical method to transform discreet data signal, which is in discreet time domain, into discreet frequency domain [12]. In the event that the total of complex multiplication in DFT is in the amount of N 2 with N is the original point of fourier transformation sample and for DFT i (N/2), while for FFT, the total of complex multiplication is (N/2)log2(N).…”

Section: Fast Fourier Transform (Fft) Fastmentioning

confidence: 99%

The Design of Coconut Maturity Prediction Device With Acoustic Frequency Detection Using Naive Bayes Method Based Microcontroller

Rahmawati

Haryanto

Sakariya

2019

JEEMECS (Journal of Electrical Engineering, Mechatronic and Computer Science)

View full text Add to dashboard Cite

The level of coconut maturity can be determined by not only observing its shell color but also by applying audio recognition approach from knocking on coconut shell. This knocking sound distinguishes young, fairly mature, and mature coconut. Recognizing the sound characteristic of knocking on coconut is usually performed by the skilled ones who are having extensive experiences and sound sensitiveness of coconut knocking. In order to substitute the skilled ones, the design of coconut maturity prediction device with acoustic frequency detection is invented. The coconut sound signal is tapped by stethoscope which is connected to MAX9814 noise sensor. Arduino Due micro-controller is used to process the signal. The process in processing the signal consists of: conversing analog signal to digital, screening the signal, and finding the average value of sound signal frequency spectrum. The signal screening uses bandpass digital filter, type IIR (Infinite Impulse Response) Elliptic order 7. This filter is utilized in order that the signal that is being processed is not some noise but the signal of knocking sound on coconut. The calculation of average value of sound signal frequency spectrum uses FFT (Fast Fourier Transform) analysis. The maturity prediction is carried out using the classification method of Naive Bayes. The input is three average value of knocking sound frequency and coconut size, and the output is classification of coconut maturity. From this research, it is generated 80% of system success rate.

show abstract

Classification of materials by acoustic signal processing in real time for NAO robots

Cited by 15 publications

References 11 publications

Coconut Maturity Detector Using Spectrogram and Convolutional Neural Network

Coconut Maturity Detector Using Spectrogram and Convolutional Neural Network

Solid Waste Disposal Scenario of Three Ladies’ Halls in the University of Chittagong, Chattogram, Bangladesh

The Design of Coconut Maturity Prediction Device With Acoustic Frequency Detection Using Naive Bayes Method Based Microcontroller

Contact Info

Product

Resources

About