Frog Identification System Based on Local Means K-Nearest Neighbors with Fuzzy Distance Weighting (original) (raw)
Related papers
scientists have discovered that most frog species produce skin secretions of an amino acid compound called peptides that can produce several avenues of research with application for human medicine. Instead of depending on physical observation procedure to identify the particular species, this study proposes an automated frog identification system based on bioacoustic signal analysis. Experimental studies of 1260 audio data from 28 species of frogs from the Internet and Intelligent Biometric Group, Universiti Sains Malaysia, IBG, USM databases are used in this study. These audio data are then corrupted by 10dB and 5dB noise. A syllable feature extraction method i.e. Mel-Frequency Cepstrum Coefficients (MFCC) employed to extract the segmented signal. Subsequently, three classifiers i.e. Support Vector Machine (SVM), Sparse Representation Classifier (SRC) and Local Mean k-Nearest Neighbor with Fuzzy Distance Weighting (LMkNN-FDW) are developed in order to evaluate the performance of th...
Frog Sound Identification System Based On Automatic Syllables Segmentation
Automatic recognition of frog sound according to particular species is considered a worthy tool for biological research and environmental monitoring. In addition, the synthesis of peptides with antimicrobial activity found in the skin of certain frog species is valuable for medical values. As a result, automatic recognition of frog sound offers many advantages rather than manual method that depending on physical observation procedure. This study evaluate the accuracy of frog sound identification from 10 species that recorded from Malaysia forest located at Sungai Sedim, Kulim and Lata Mengkuang, Baling. By applying frequency information technique, the frog sound samples are automatically segmented into syllables. Two types of syllable feature extraction method i.e, MFCC and LPC are the determined. Finally, nonparametric kNN classifier with Euclidean distance and Chebyshev distance has been employed to recognize the frog species. Results show that kNN classifier based on MFCC and LPC...
Effect of Natural Background Noise and Man-Made Noise on Automated Frog Calls Identification System
A b s t r a c t Frog identification based on their calls becomes important for biological research and environmental monitoring. However, identifying particular frog calls becomes challenging particularly when the frog calls are interrupted with noises either in natural background noise or man-made noise. Hence, an automatic identification frog call system that robust in noisy environment has been proposed in this paper. Experimental studies of 675 audio obtained from 15 species of frogs in the Malaysian forest and recorded in an outdoor environment are used in this study. These audio data are then corrupted by 10dB and 5dB noise. A syllable segmentation technique i.e. short time energy (STE) and Short Time Average Zero Crossing Rate (STAZCR) and feature extraction, Mel-Frequency Cepstrum Coefficients (MFCC) are employed to segment the desired syllables and extract the segmented signal. Subsequently, the Local Mean k-Nearest Neighbor with Fuzzy Distance Weighting (LMkNN-FDW) are employed as a classifier in order to evaluate the performance of the identification system. The experimental results show both of natural background noise and man-made noise outperform by 95.2% and 88.27% in clean SNR, respectively.
Automatic Syllables Segmentation for Frog Identification System
Automatic recognition of frog sound according to particular species is considered a worthy tool for biological research and environmental monitoring. As a result, automatic recognition of frog sound offers many advantages rather than manual method that depending on physical observation procedure. This study evaluates the accuracy of frog sound identification from 12 species that recorded from Malaysia forest. By applying short time energy and short time average zero crossing rate, the frog sound samples are automatically segmented into syllables. A syllable feature extraction method i.e, Mel-Frequency Cepstrum Coefficients is employed to extract the segmented signal. Finally, nonparametric k-nearest neighbor classifier with Euclidean distance has been employed to recognize the frog species. A comparison between automatic segmentation and manual segmentation is applied and results show that automatic segmentation outperforms to identify the frog species with an accuracy of 97% compar...
MFCC based frog identification system in noisy environment
2013 IEEE International Conference on Signal and Image Processing Applications, 2013
Identification of frog sound is useful tool and competent in biological research and environmental monitoring. In contrast with traditional methods that not practical due to the time consuming, expensive or detrimental to the animal's welfare, this study proposes an automatic frog call identification system. 750 data species that recorded from Malaysia forest is used as data signals and have been corrupted by lOdB and 20dB noise to determine the performance of accuracy in noisy environment. MFCC parameter is employed as feature extraction. An analysis of signals for different number of MFCCs (8, 12, 15, 20 and 25) is presented and the results are provided using MFCC, Delta Coefficients (�MFCC) and Delta Delta Coefficients (��MFCC). Subsequently, kNN classifier is applied to evaluate the performance in the frog identification system. The results show the accuracy range from 84.67% to 85.78%, 61.33% to 68.89% and 59.33% to 67.33% in clean environment, lOdB and 20dB, respectively.
A Comparative Study of Classification Algorithms: Statistical, Machine Learning and Neural Network
Machine Intelligence 13, 1994
The study of frog is important since the chemical compound in their skin extracts peptides with antimicrobial activity becomes a valuable tool for pharmacology and biochemistry research. Instead of depending on physically observation procedure to identify the particular species, this study proposes an automated frog sound identification system for recognizing frog species. 990 data species that collected from internet database and recorded from Malaysia forest are sampled. Two features i.e. Mel Frequency Cepstrum Coefficient (MFCC) and Linear Predictive Coding (LPC) have been used in the feature extraction techniques. Subsequently Support Vector Machine (SVM) and k Nearest Neighbor (kNN) are obtained to evaluate the performance in the identification system. The experimental results show that kNN gives better performance with accuracy up to 80.33% to 98.4%compare than SVM.
This paper presents the evaluation of Linear Prediction Coding (LPC) implemented on a Wireless Sensor Networks (WSN) platform, with particular interest in the application of these techniques on frog's phonemes classification. LPC gives the sound, as a discrete signal, an important role on species phonemes characterization and subsequent classification processes . Therefore, we studied the possibility of species classification and recognition, according to the structure of the phoneme, sound characteristic statistical variance and signal probability densities. To evaluate this option we should consider the WSN limitations and contrast them against the LPC's high temporal and spatial complexity. Autocorrelation and PCA are complementary techniques of LPC whose features will also be studied in this article. Besides these techniques, we propose Modified K-Means (MKM) as classifier which is a postprocessing stage outside of WSN platforms
Frog call classification: a survey
Artificial Intelligence Review, 2016
Over the past decade, frog biodiversity has rapidly declined due to many problems including habitat loss and degradation, introduced invasive species, and environmental pollution. Frogs are greatly important to improve the global ecosystem and it is ever more necessary to monitor frog biodiversity. One way to monitor frog biodiversity is to record audio of frog calls. Various methods have been developed to classify these calls. However, to the best of our knowledge, there is still no paper that reviews and summarizes currently developed methods. This survey gives a quantitative and detailed analysis of frog call classification. To be specific, a frog call classification system consists of signal pre-processing, feature extraction, and classification. Signal pre-processing is made up of signal processing, noise reduction, and syllable segmentation. Following signal preprocessing, the next step is feature extraction, which is the most crucial step for improving classification performance. Features used for frog call classification are categorized into four types: (1) time domain and frequency domain features (we classify time domain and frequency domain features into one type because they are often combined together to achieve higher classification accuracy), (2) time-frequency features, (3) cepstral features, and (4) other features. For the classification step, different classifiers and evaluation criteria used for frog call classification are investigated. In conclusion, we discuss future work for frog call classification.
Intelligent frog species identification on android operating system
In this paper an Intelligent Frog Species Identification System (IFSIS) which works as a sensor is developed. It is designed to assist the nonexperts to recognize frog species according to frog bioacoustics signals for environmental monitoring. IFSIS consists of Android devices and a server. Android device is used to record frog call signal and to display the details of the detected frog species once the identification is processed by the server. Meanwhile, feature extraction and identification process of the frog call signal are done on Intel atom board which works as server. The Mel Frequency Cepstrum Coefficient (MFCC) is used as feature extraction technique while the classifier employed is Support Vector Machine (SVM). Experimental results show that the performances of 95.33% has been achieved which proves that IFSIS can be a viable automated tool for recognizing frog species.
Automatic classification of frogs calls based on fusion of features and SVM
2015 Eighth International Conference on Contemporary Computing (IC3), 2015
This paper presents a new approach for the acoustic classification of frogs' calls using a novel fusion of features: Mel Frequency Cepstral Coefficients (MFCCs), Shannon entropy and syllable duration. First, the audio recordings of different frogs' species are segmented in syllables. For each syllable, each feature is extracted and the cepstral features (MFCC) are computed and evaluated separately as in previous works. Finally, the data fusion is used to train a multiclass Support Vector Machine (SVM) classifier. In our experiment, the results show that our novel feature fusion increase the classification accuracy; achieving an average of 94.21% ± 8,04 in 18 frog's species.