PH12017000082A1 - Apparatus for identifying and detecting microorganisms in plants and method therefor - Google Patents
Apparatus for identifying and detecting microorganisms in plants and method therefor Download PDFInfo
- Publication number
- PH12017000082A1 PH12017000082A1 PH12017000082A PH12017000082A PH12017000082A1 PH 12017000082 A1 PH12017000082 A1 PH 12017000082A1 PH 12017000082 A PH12017000082 A PH 12017000082A PH 12017000082 A PH12017000082 A PH 12017000082A PH 12017000082 A1 PH12017000082 A1 PH 12017000082A1
- Authority
- PH
- Philippines
- Prior art keywords
- identifying
- detecting microorganisms
- plants
- microorganisms
- audio
- Prior art date
Links
- 244000005700 microbiome Species 0.000 title claims description 18
- 238000000034 method Methods 0.000 title claims description 16
- 238000013528 artificial neural network Methods 0.000 claims description 25
- 238000011161 development Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 229910000859 α-Fe Inorganic materials 0.000 claims description 3
- 241000209094 Oryza Species 0.000 abstract description 24
- 235000007164 Oryza sativa Nutrition 0.000 abstract description 15
- 235000009566 rice Nutrition 0.000 abstract description 15
- 241001330975 Magnaporthe oryzae Species 0.000 abstract description 7
- 241001544321 Thanatephorus cucumeris Species 0.000 abstract description 7
- 241000589652 Xanthomonas oryzae Species 0.000 abstract description 6
- 230000001580 bacterial effect Effects 0.000 abstract description 6
- 244000000003 plant pathogen Species 0.000 abstract description 6
- 201000010099 disease Diseases 0.000 description 17
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 17
- 238000012549 training Methods 0.000 description 14
- 238000012545 processing Methods 0.000 description 8
- 238000012360 testing method Methods 0.000 description 8
- 230000005236 sound signal Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 235000013305 food Nutrition 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 240000007594 Oryza sativa Species 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 244000063299 Bacillus subtilis Species 0.000 description 1
- 235000014469 Bacillus subtilis Nutrition 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000011138 biotechnological process Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006260 foam Substances 0.000 description 1
- 230000037433 frameshift Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 244000052769 pathogen Species 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000013518 transcription Methods 0.000 description 1
- 230000035897 transcription Effects 0.000 description 1
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
This invention seeks to solve the problem of the prior art by using the sound waves produced by plant pathogens, more particularly rice plant pathogens bacterial leaf blight (Xanthomonas oryzae), rice blast (Thanatephorus cucumeris), and sheath blight (Magnaporthe oryzae). The frequency of microbes in the leaves of the rice plant will serve as the input of the system. The frequent movement of microbes will be collected using an electret microphone observed in an anechoic chamber. The audio recording will be processed using MATLAB? software and will undergo several stages to achieve accurate result. Based on the result, the program will generate a report in PDF.
Description
and the result will prompt with a suggestion of viewing the recommendation. The © recommendation is shown in PDF. -
After audio recording of the sample leaves had been gathered as depicted in Figure 3, y the system will then determine the microorganisms present in the samples. After > analysis, the recommendation based on the results will be presented in PDF. _
The flow of the program in identifying the disease of the rice plant using the preferred . embodiment is shown in Figure 4. First, recorded ambient noise and audio signal of ~ microbes undergo spectral subtraction in which the output is a clean sound that comes ® only from the microbes without any hint of sound from the environment or surroundings. ~
The process follows pre-emphasis to cepstral lifter computation. The signal is first pre- emphasized using a first order FIR filter with pre-emphasis coefficient ALPHA. The pre- emphasized speech signal is subjected to the short-time Fourier transform analysis with frame durations of TW (ms), frame shifts of TS (ms) and analysis window function given as a function handle in WINDOW. This is followed by magnitude spectrum computation and followed by filter bank design with M triangular filters uniformly spaced on the Mel scale between lower and upper frequency limits given in R (Hz). The filter bank is applied to the magnitude spectrum values to produce filter bank energies (FBEs) 310 (M per frame). Log-compressed FBEs are then decorrelated using the discrete cosine transform to produce cepstral co-efficients. Final step applies sinusoidal lifter to produce lifter MFCCs.
The data obtained are stored in the matrix and fed to the fuzzy neural network. The identified disease is presented in the user interface window. Thereupon, strategic options for proper management of the disease are generated in PDF format.
The steps undertaken in implementing the artificial neural network is depicted in Figure 5. First, the database for the network must be comprised of sufficient data examples. For disease identification, the system recommends using 450 audio recording samples, 150 samples for each of the three microbes. Training and performance parameters are a initialized after creating the neural network. Because the artificial neural network uses an = iterative learning algorithm, weights and biases are arbitrarily initialized and the images = are presented to the network one at a time. At least one of the training parameters must . be satisfied for the network to consider the data as correctly classified. From the sample, - 80 percent was used for training and 20 percent was used for testing. em
This process is repeated once the training number is reached. The learning algorithm = allows the network to improve its performance by adjusting the weights so as to predict = the next set of data correctly. The training stops once the mean square error of the o network is less that 1x10-10
The preferred embodiment makes use of MATLAB™ in creating functions for the audio processing due to its computing power and availability of toolboxes. The fuzzy neural network algorithm was also implemented using the MATLAB™,
In the preferred embodiment, to train a Fuzzy Interference System (FIS), a training data 15s was loaded containing the desired input/output data of the system to be modeled. Any data set loaded must be an array with the data arranged as column vectors, and the output data in the last column. The training data set is used to train a fuzzy system by adjusting the membership function parameters that best model this data and appears in the plot in the center of the GUI as a set of circles. The horizontal axis is the marked data set index. This index indicates the row from which that input data value was obtained (whether or not the input is a vector or a scalar).
To test the FIS against the testing data, select Testing data in the Test FIS portion of the
Artificial Neuro Fuzzy Inference System (ANFIS) Editor GUI, and click Test Now. The plot shows the checking error as 4 on the top. The training errors as *** are found on the bottom. The checking error decreases up to a certain point in the training, and then it increases. The increase represents the point of model over fitting. ANFIS chooses the
Co 10 mode! parameters associated with the minimum checking error (just prior to this jump . point). ~
The database of the preferred embodiment consists of the microorganisms namely X. Ny oryzae, M. oryzae and T. cucumeris from the laboratory of International Rice Research = s Institute. Using the anechoic chamber, the frequency of 9 different concentrations of - microorganisms (50 trials of first concentration of M. oryzae with 50000 spores per 50 @ milliliters, 50 trials of second concentration of M. oryzae with 100000 spores per 50 " milliliters, 50 trials of third concentration of M. oryzae with 150000 spores per 50 . milliliters, 50 trials of first concentration of T. cucumeris with 50000 spores per 50 o milliliters, 50 trials of second concentration of T. cucumeris 100000 spores per 50 - milliliters, 50 trials of third concentration of T. cucumeris 150000 spores per 50 milliliters 50 trials of first concentration of X. oryzae 10° series fold of cells by 10 milliliters, 50 trials of second concentration of X. oryzae 108 series fold of cells by 10 milliliters, 50 trials of third concentration of X. oryzae 107 series fold of cells by 10 milliliters) were recorded and fed to the program as input. Variability in numbers of the audio per trial is due to the availability of the microorganisms that is available on the laboratory. Each audio undergoes three audio processing techniques; audio enhancement and feature extraction. All the features of the processed images are saved as MATLAB™ Workspace (.mat) and as an excel document (.xlIsx) for backup.
It should be understood, however, that the foregoing description of the preferred embodiment is not intended to limit the invention to the particular form disclosed. The intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention as defined by the claims herein.
TECHNOLOGICAL UNIVERSITY OF THE PHILIPPINES ©
Applicant =
By: = bot
FORTUN NARVASA & SALAZAR =
A “od
BAYAI B. LOSTE ©
SPECIFICATION a
Apparatus for Identifying and Detecting -
Microorganisms in Plants and Method Therefor ~ ,
This invention pertains to an apparatus for detecting microorganisms in rice plant and - the method for implementing the same. -
Background of the Invention 5
Rice is the world's most important food crop; it is grown and consumed across the planet. Rice is one of Philippines’ major food products, taking up approximately 4 million hectares of land. It remains the main staple of more than 90 million Filipinos and consumes about 60-65 percent in the smallest household income for food.
The population of the Philippines is estimated to be at around 97 million and its annual growth rate at roughly 2 percent. Because of population growth, there is an expected increase in demand for rice. The challenge to increase rice production is not an easy task due to various agronomical factors which affect yield loss.
In a study conducted by the International Rice Research Institute (IRR), it was found that on average, rice farmers lose 37 percent of their rice yield due to pests and diseases and that these losses can range between 24 percent and 41 percent depending on the various factors such as type of disease. For instance, the three common rice plant diseases are bacterial leaf blight (Xanthomonas oryzae), rice blast (Thanatephorus cucumeris), and sheath blight (Magnaporthe oryzae), and these diseases cause different amounts of damage.
The traditional way of identifying rice plant diseases is through the detection of visible - structures produced by the pathogens. Kahar et al. (2015) in their paper entitled “Early ~
Detection and Classification of Paddy Diseases with Neural Networks and Fuzzy Logic” found optical detection of bacterial leaf blight, rice blast, and sheath blight with the use of 2
Matrix Laboratory™ (MATLAB) in combination with a neuro fuzzy architecture which consists of a back-propagation neural network together with fuzzy logic. The problem - with their study that that there is no indication that the researchers considered using = audio signal processing in their system, which is faster and more accurate. = >
The use of sound to identify plant pathogens had been the subject of the study entitled = ‘Production of sound waves by bacterial cells and the response of bacterial cells to sound” (Matsuhashi, 1998). According to the study, certain microbes such as Bacillus subtilis emit sounds with a distinct frequency. Through the identification of the distinct frequency of a certain microbe using a sensitive microphone system, it can be determine if a rice plant is infected by disease.
This can be done by creating a signal processing system that will be used to detect and identify the microorganisms that reside on a rice plant.
The automatic classification of sound sources using their acoustic signatures recorded at the microphone of a sound monitoring system is an active subject of researches.
Automatic sound recognition has many potential applications including command and control. Dictation, transcription of recorded speech, searching audio documents and interactive spoken dialogues are examples of the use of sound monitoring system.
A technique that has been widely successful in sound recognition is based on fuzzy neural network. The development and application of neuro-fuzzy systems integrating the learn ability of neural networks with the transparency and interpretability of the fuzzy systems currently grows (Nauck, 1997). The performance of fuzzy neural network is = experimentally compared with other neural networks trained to by back propagation ~ algorithms. It shows better convergence speed. This confirms its applicability in learning ~ large-sized neural networks of real-life applications like adaptive interactive systems, modeling of biotechnological processes, etc. They are object-oriented implemented in =
MATLAB™ (Brian, 1999). =
This invention seeks to solve the problem of the prior art by using the sound waves produced by plant pathogens, more particularly rice plant pathogens bacterial leaf blight (Xanthomonas oryzae), rice blast (Thanatephorus cucumeris), and sheath blight (Magnaporthe oryzae). The frequency of microbes in the leaves of the rice plant will serve as the input of the system. The frequent movement of microbes will be collected using an electret microphone observed in an anechoic chamber. The audio recording will be processed using MATLAB™ software and will undergo several stages to achieve accurate result. Based on the result, the program will generate a report in PDF.
The above and other features of the present invention will become more apparent to those of ordinary skill in the art by describing in detail the preferred embodiment thereof with reference to the attached drawings in which:
Figure 1 is a block diagram of the apparatus according to an embodiment of the invention;
Figure 2 is a Visual Basic™ graphic user interface flow chart of the invention o following Figure 1; .
Figure 3 is a Visual Basic™ recommendation flow chart of the invention following c
Figure 1; wd
Figure 4 is a disease identification flow chart of the invention following Figure 1; and Ea
Figure 5 is a neural network flowchart of the invention following Figure 1. -
As shown in Figure 1, the preferred embodiment of the apparatus comprises three (3) main sections namely audio recording 2; audio signal processing 3, which consists of audio enhancement 4, feature extraction 9, and training section 6 through fuzzy neural network; and presentation of recommendation 8. Audio recording section 2 is responsible for obtaining audio signal 1 using an anechoic chamber (not shown) with an electret condenser microphone (not shown) inside ranging 20 Hz up to 120 KHz of frequency response. In audio enhancement 4, spectral subtraction adjustment is performed. In feature extraction 5, Mel frequency cepstral coefficient is the algorithm used to extract the characteristics for each input.
For the training section 6, the recorded audio serves as the input and is processed in this section. The system is trained using the fuzzy neural network architecture to improve the accuracy of the software program.
Neural networks and fuzzy logic have some common features such as distributed = representation of knowledge, model-free estimation, ability to handle data with - uncertainty and imprecision. Fuzzy logic has tolerance for imprecision of data while ~ neural networks have tolerance for noise. In this embodiment, the database of the = network consists of the frequency of different concentrations of the three microorganisms = that cause the most common rice plant diseases in the Philippines. fe vf
The neural network increases the accuracy of the audio processing system. The = database 7 in this embodiment of the network involved 450 recordings for the diseases, ez 80% for training and 20% for testing. Fuzzy neural network 6 uses a multi-player © perception network and a modified Mel frequency cepstral coefficient training algorithm, b= which employs gradient information to be modified and decrease the error on the succeeding tests of inputs.
The recommendation section 8 will then generate a report in Portable Document Format (PDF) based on the analysis of the apparatus and will consist of the following:
For Disease Identification: o Disease Identified o Local names of the disease e Symptoms o When it occurs o Where it occurs o Cure of rice plant in different stages
The frequency of microbes in the leaves of the rice plant will serve as the input of the system. The frequent movement of microbes will be collected using an electret microphone and will be observed in an anechoic chamber. The audio recording 2 will be
Se ——— oo 6 Co processed using MATLAB™ software and will undergo several stages to achieve an : accurate result. Based on the result, the program will generate a report in PDF. o
In the preferred embodiment, MATLAB™ will serve as the integrated development ~ environment (IDE) for signal processing 3 although other IDEs can be used with minor = adjustments to the system. This process includes audio recording 2, audio enhancement 4, feature extraction 3, database creation 7 and fuzzy neural network timing 6. 3
Neural networks and fuzzy logic have some common features such as distributed = representation of knowledge, model-free estimation ability to handle data with © uncertainty and imprecision. Fuzzy logic has tolerance for imprecision of data, while © neural networks have tolerance for noise. re
In the preferred embodiment, the audio recording 2 responsible for obtaining signal uses an anechoic chamber with an electret condenser microphone inside, ranging 20 Hz up to 120 KHz of frequency response. Electret condenser microphones (ECM) are mainly used for measurement because of their frequency response, stability. The ECM used in the preferred embodiment has the following specifications: approximate input referred self-noise level of 23 dB SPL, power supply: 48 mm in length, 20mm in diameter and 40g in weight.
An interface 9 as shown in Figure 9 is also provided to allow interaction between the user and the apparatus. The user can choose his preferred language, for input or to initialize audio recording process.
For acquisition of samples of the rice plant pathogens, an anechoic chamber is used in the preferred embodiment to be the control in a non-reverberant environment when the audio signal is recorded. The anechoic chamber is a box installed with an electrets condenser microphone inside and acoustic foams on the walls.
The preferred dimensions of anechoic chamber are as follows: 15 inches in length, 15 = inches in width and 15 inches in height. For the materials of the chamber, plyboard was - used to achieve rigidity. The chamber is also lined on all sides with pyramid shaped - foamed ferrite as these help to make external audio waves minimal, and are a good x solution for sound absorption. The computation for Reverberation Time is as follows: -
RT= 0.049 x V 0 -sin (1-a) -
Where: @ ,
V = sidein® = [15in — 2(0.5in) — 2(3in)} = 512 in3 = 0.2963 ft3
S = 6 x siden? = 6 x [15in — 2(0.5in) — 2(3in)J2 = 384 in2 = 2.6667 ft2
A=0.80
RT = 0.049 x 0.2963 = 3.3828 milliseconds -(2.6667)in(1-0.8)
In developing the software, MATLAB™ was used as the IDE for the preferred embodiment for the processing of the audio signal produced by the microbes and for training the system using the fuzzy neural network algorithm. Visual Basic™ was used, on the other hand, as the IDE for developing a graphic user interface (GUI) that will allow the user to record the audio signal produced by the frequent movement of microbes and generate the report in PDF format. Once the program starts up, the user can choose a language he prefers to use. As shown in Figure 2, the user will have to record the ambient noise inside the anechoic chamber. Then, the microbe frequency will be recorded after the leaf sample is placed inside the chamber. Analysis can now be done
Claims (12)
1. An apparatus for identifying and detecting microorganisms in plants comprising ol of: = an input unit with audio recording means; - a combination of an integrated development environment consisting of an audio wo ~ enhancement means, a feature extraction means, a fuzzy neural network, and a processing software; - a database for storing collected information pertaining to microorganisms; and = a display means with a graphical user interface. o
2. The apparatus according to Claim 1 wherein the audio recording means consists of an electret condenser microphone configured inside an anechoic chamber.
3. The apparatus according to Claim 2 wherein the electret condenser microphone has a frequency response ranging from 20 Hz to 120 KHz.
4. The apparatus according to Claim 2 wherein the anechoic chamber is lined on all sides with pyramid-shaped foamed ferrite.
5. The apparatus according to Claim 1 wherein the integrated development environment uses a Matrix Laboratory ™,
6. The apparatus according to Claim 1 wherein the display means uses Visual Basic™ for developing the graphical user interface.
7. A method for identifying and detecting microorganisms in plants, the method comprising the steps of:
a. using an input unit with audio recording means; oO b. using a combination of an integrated development environment consisting - of an audio enhancement means, a feature extraction means, a fuzzy ” neural network, and a processing software; o
C. using a database for storing collected information pertaining to 2 microorganisms: and @
d. using a displaying means with a graphical user interface. -
8. A method for identifying and detecting microorganisms in plants according to = Claim 7 wherein the use of an audio recording means consists of using an = electret condenser microphone configured inside an anechoic chamber, o
9. A method for identifying and detecting microorganisms in plants according to Claim 8 wherein the use of an electret condenser microphone as a frequency response ranging from 20 Hz to 120 KHz.
10. A method for identifying and detecting microorganisms in plants according to Claim 8 wherein the use of an anechoic chamber has lining on all sides with pyramid-shaped foamed ferrite.
11.A method for identifying and detecting microorganisms in plants according to Claim 7 wherein the use of integrated development environment consists of using a Matrix Laboratory™,
12.A method for identifying and detecting microorganisms in plants according to Claim 7 wherein the use of displaying means consists of using Visual Basic™ for developing the graphical user interface,
TECHNOLOGICAL UNIVERSITY OF THE PHILIPPINES = Applicant - By: ” > ~ FORTUN NARYASA & SALAZAR = BAYANI B.
LOSTE 2 Fd
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PH12017000082A PH12017000082A1 (en) | 2017-03-17 | 2017-03-17 | Apparatus for identifying and detecting microorganisms in plants and method therefor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PH12017000082A PH12017000082A1 (en) | 2017-03-17 | 2017-03-17 | Apparatus for identifying and detecting microorganisms in plants and method therefor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| PH12017000082A1 true PH12017000082A1 (en) | 2019-01-21 |
Family
ID=65228655
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PH12017000082A PH12017000082A1 (en) | 2017-03-17 | 2017-03-17 | Apparatus for identifying and detecting microorganisms in plants and method therefor |
Country Status (1)
| Country | Link |
|---|---|
| PH (1) | PH12017000082A1 (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6873914B2 (en) * | 2001-11-21 | 2005-03-29 | Icoria, Inc. | Methods and systems for analyzing complex biological systems |
| US20070238092A1 (en) * | 2004-11-05 | 2007-10-11 | Rubesa Pier | Method and Device for the Detection, Measurement and Analysis of Biological, Bioactive, Bioenergetic and Bioharmonic Signals |
| US20100216225A1 (en) * | 2009-02-25 | 2010-08-26 | Ag-Defense Systems, Inc. | Portable microorganism detection unit |
-
2017
- 2017-03-17 PH PH12017000082A patent/PH12017000082A1/en unknown
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6873914B2 (en) * | 2001-11-21 | 2005-03-29 | Icoria, Inc. | Methods and systems for analyzing complex biological systems |
| US20070238092A1 (en) * | 2004-11-05 | 2007-10-11 | Rubesa Pier | Method and Device for the Detection, Measurement and Analysis of Biological, Bioactive, Bioenergetic and Bioharmonic Signals |
| US20100216225A1 (en) * | 2009-02-25 | 2010-08-26 | Ag-Defense Systems, Inc. | Portable microorganism detection unit |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Martínez Ramírez et al. | Deep learning for black-box modeling of audio effects | |
| Wright et al. | Real-time guitar amplifier emulation with deep learning | |
| Mielke et al. | A method for automated individual, species and call type recognition in free-ranging animals | |
| Larson et al. | Validation of an automated cough detection algorithm for tracking recovery of pulmonary tuberculosis patients | |
| Civera et al. | The Teager-Kaiser energy cepstral coefficients as an effective structural health monitoring tool | |
| Abdollahi et al. | Automated beehive acoustics monitoring: A comprehensive review of the literature and recommendations for future work | |
| Sanahuja et al. | Classification of puffed snacks freshness based on crispiness-related mechanical and acoustical properties | |
| Ciaburro et al. | Acoustic characterization of rooms using reverberation time estimation based on supervised learning algorithm | |
| Copiaco et al. | A study of features and deep neural network architectures and hyper-parameters for domestic audio classification | |
| Balantic et al. | Statistical learning mitigation of false positives from template-detected data in automated acoustic wildlife monitoring | |
| Effendy et al. | Forest quality assessment based on bird sound recognition using convolutional neural networks | |
| Mukherjee et al. | Lung health analysis: adventitious respiratory sound classification using filterbank energies | |
| Faiß et al. | Adaptive representations of sound for automatic insect recognition | |
| Ruvinga et al. | Identifying queenlessness in honeybee hives from audio signals using machine learning | |
| Faragó et al. | CNN-based identification of Parkinson’s disease from continuous speech in noisy environments | |
| Al-Jumaili et al. | Classification of spoken english accents using deep learning and speech analysis | |
| Mewada et al. | Gaussian-filtered high-frequency-feature trained optimized BiLSTM network for spoofed-speech classification | |
| PH12017000082A1 (en) | Apparatus for identifying and detecting microorganisms in plants and method therefor | |
| Chao et al. | Implementation of artificial intelligence for classification of frogs in bioacoustics | |
| Stattner et al. | Acoustic scheme to count bird songs with wireless sensor networks | |
| Benocci et al. | Toward the definition of a soundscape ranking index (SRI) in an Urban Park using machine learning techniques | |
| Godino-Llorente et al. | Discriminative methods for the detection of voice disorders | |
| Suaste-Rivas et al. | Implementation of a linguistic fuzzy relational neural network for detecting pathologies by infant cry recognition | |
| Simundsson et al. | A neural network to classify auditory signals for use in autonomous harvester control systems | |
| Duque-Montoya et al. | Automatic ecosystem identification using Psychoacoustical features |