Since pig vocalization is an important indicator of monitoring pig conditions, pig vocalization detection and recognition using deep learning play a crucial role in the management and welfare of modern pig livestock farming. However, collecting pig sound data for deep learning model training takes time and effort. Acknowledging the challenges of collecting pig sound data for model training, this study introduces a deep convolutional neural network (DCNN) architecture for pig vocalization and non-vocalization classification with a real pig farm dataset. Various audio feature extraction methods were evaluated individually to compare the performance differences, including Mel-frequency cepstral coefficients (MFCC), Mel-spectrogram, Chroma, and Tonnetz. This study proposes a novel feature extraction method called Mixed-MMCT to improve the classification accuracy by integrating MFCC, Mel-spectrogram, Chroma, and Tonnetz features. These feature extraction methods were applied to extract relevant features from the pig sound dataset for input into a deep learning network. For the experiment, three datasets were collected from three actual pig farms: Nias, Gimje, and Jeongeup. Each dataset consists of 4000 WAV files (2000 pig vocalization and 2000 pig non-vocalization) with a duration of three seconds. Various audio data augmentation techniques are utilized in the training set to improve the model performance and generalization, including pitch-shifting, time-shifting, time-stretching, and background-noising. In this study, the performance of the predictive deep learning model was assessed using the k-fold cross-validation (k = 5) technique on each dataset. By conducting rigorous experiments, Mixed-MMCT showed superior accuracy on Nias, Gimje, and Jeongeup, with rates of 99.50%, 99.56%, and 99.67%, respectively. Robustness experiments were performed to prove the effectiveness of the model by using two farm datasets as a training set and a farm as a testing set. The average performance of the Mixed-MMCT in terms of accuracy, precision, recall, and F1-score reached rates of 95.67%, 96.25%, 95.68%, and 95.96%, respectively. All results demonstrate that the proposed Mixed-MMCT feature extraction method outperforms other methods regarding pig vocalization and non-vocalization classification in real pig livestock farming.

Currently, invasive and external radio frequency identification (RFID) devices and pet tags are widely used for dog identification. However, social problems such as abandoning and losing dogs are constantly increasing. A more effective alternative to the existing identification method is required and the biometrics can be the alternative. This paper proposes an effective dog muzzle recognition method to identify individual dogs. The proposed method consists of preprocessing, feature extraction, matching, and postprocessing. For preprocessing, proposed resize and histogram equalization are used. For feature extraction algorithm, Scale Invariant Feature Transform (SIFT), Speeded Up Robust Features (SURF), Binary Robust Invariant Scaling Keypoints (BRISK) and Oriented FAST, and Rotated BRIEF (ORB) are applied and compared. For matching, Fast Library for Approximate Nearest Neighbors (FLANN) is used for SIFT and SURF, and hamming distance are used for BRISK and ORB. For postprocessing, two techniques to reduce incorrect matches are proposed. The proposed method was evaluated with 55 dog muzzle pattern images acquired from 11 dogs and 990 images augmented by the image deformation (i.e., angle, illumination, noise, affine transform). The best Equal Error Rate (EER) of the proposed method was 0.35%, and ORB was the most appropriate for the dog muzzle pattern recognition.

서 론 기존 젖소 농가의 경우 착유 샘플링을 통한 검정시에만 유성분 함량에 대한 파악이 가능했으나 낙농 스마트팜 모 델 보급에 따라 로봇착유기 혹은 개체별 착유 시스템인 radio frequency identification (RFID)

In this study, water intake estimation models using reticulorumen bolus transponders were developed to estimate the water intake of cows that are difficult to measure by individual. Reticulorumen temperature was collected using reticulorumen bolus transponders, and the water intake index was defined to estimate the water intake through reticulorumen temperature. The water intake index is the sum of reticulorumen temperatures below baseline temperature, a proposed model was developed using the water intake index and daily mean ambient temperature. As the result of comparing the predicted water intake from proposed model and the predicted water intake from Jang et al. (2021), the coefficient of determination, MAPE, and RMSE were 0.67, 7.86%, 7.88 kg/d, respectively. The results showed that the possibility of estimating water intake through temperature of reticulorumen.

The increasing frequency of heatwaves and high-temperature events due to climate change intensifies heat stress and mortality risk in broiler production and necessitates reassessment of facility design and energy management. This study developed a machine learning surrogate model trained on BES-simulated heating and cooling loads to estimate future energy load changes in broiler houses under SSP climate scenarios. Training data were constructed using simulated energy load results under different insulation conditions combined with historical meteorological data (2011–2020). Four machine learning models, namely Linear Regression, Random Forest, Gradient Boosting, and XGBoost, were applied to compare their predictive performance for heating and cooling loads. Model performance was evaluated using five-fold cross-validation (K-fold cross-validation, K = 5). XGBoost and Random Forest showed the best performance for heating and cooling load prediction, respectively (R² > 0.99, MAPE < 10%). These models were applied to SSP1-2.6 and SSP5-8.5 climate scenarios. Results showed decreasing heating loads and increasing cooling loads across all scenarios, with cooling demand projected to increase by more than 150% relative to baseline levels under SSP5-8.5 by the late 21st century. This study demonstrates that simulation-trained machine learning can efficiently estimate long-term energy-demand changes, supporting climate-responsive facility design and energy management in livestock housing.

서 론 우리나라는 육류 소비량의 증가와 이로 인해 돼지 사육 두수가 증가하는 추세이다. 육류 소비량의 경우, 2000년부 터 2019년까지 1인당 31.9 kg에서 54.6 kg으로 연간 약 2.9%가량 증가하였다(KMTA, 2019). 또한 2022년 기준 육류 소비량은 58 kg으로 쌀 소비량인 56 kg을 넘어선 것 으로 보고되었다(Statistics Korea