Table 4. Overview of sound-based techniques and algorithms for detecting and monitoring pig disease symptoms, focusing on sound patterns such as coughs and vocalizations associated with specific health conditions

Detection/Classification	Classification Technique	Feature Extraction Technique	Accuracy	Reference
Sound	ANOVA	Digitalized	-	[14]
	SVDD	MFCC	94.0	[13]
	DNN-HMM	MFCC	92.46	[18]
	Fine-tuned AlexNet	Spectrogram with STFT	95.4	[39]
	SVM	MFCC, TFR, CQT, STFT, CNN	97.35	[47]
	SVM, Softmax	MFCC–CNN	96.68	[57]
	DNN-HMM	Kalman filtering, EMD-TEO, MFCC	83.0	[73]
	CMCC-CNN	MFCC	96	[70]

MFCC, mel-frequency cepstral coefficient; SVDD, support vector data description; DNN-HMM, deep neural network–hidden Markov model; STFT, short-time Fourier transform; SVM, support vector machine; STFT, short-time Fourier transform; TFR, time-frequency representation; CQT, constant-Q transform; CNN, convolutional neural network; EMD, empirical mode decomposition; CMCC, Chirplet mel-frequency cepstral coefficient.