Impact ground pressure events occur frequently in coal mining processes,significantly affecting the personal safety of construction workers.Real-time microseismic monitoring of coal rock body rupture information can p...Impact ground pressure events occur frequently in coal mining processes,significantly affecting the personal safety of construction workers.Real-time microseismic monitoring of coal rock body rupture information can provide early warnings,and the seismic source location method is an essential indicator for evaluating a microseismic monitoring system.This paper proposes a nonlinear hybrid optimal particle swarm optimisation(PSO)microseismic positioning method based on this technique.The method first improves the PSO algorithm by using the global search performance of this method to quickly find a feasible solution and provide a better initial solution for the subsequent solution of the nonlinear optimal microseismic positioning method.This approach effectively prevents the problem of the microseismic positioning method falling into a local optimum because of an over-reliance on the initial value.In addition,the nonlinear optimal microseismic positioning method further narrows the localisation error based on the PSO algorithm.A simulation test demonstrates that the new method has a good positioning effect,and engineering application examples also show that the proposed method has high accuracy and strong positioning stability.The new method is better than the separate positioning method,both overall and in three directions,making it more suitable for solving the microseismic positioning problem.展开更多
Nursing behaviour and the calling-to-nurse sound are crucial indicators for assessing sow maternal behaviour and nursing status.However,accurately identifying these behaviours for individual sows in complex indoor pig...Nursing behaviour and the calling-to-nurse sound are crucial indicators for assessing sow maternal behaviour and nursing status.However,accurately identifying these behaviours for individual sows in complex indoor pig housing is challenging due to factors such as variable lighting,rail obstructions,and interference from other sows'calls.Multimodal fusion,which integrates audio and visual data,has proven to be an effective approach for improving accuracy and robustness in complex scenarios.In this study,we designed an audio-visual data acquisition system that includes a camera for synchronised audio and video capture,along with a custom-developed sound source localisation system that leverages a sound sensor to track sound direction.Specifically,we proposed a novel transformer-based audio-visual multimodal fusion(TMF)framework for recognising fine-grained sow nursing behaviour with or without the calling-to-nurse sound.Initially,a unimodal self-attention enhancement(USE)module was employed to augment video and audio features with global contextual information.Subsequently,we developed an audio-visual interaction enhancement(AVIE)module to compress relevant information and reduce noise using the information bottleneck principle.Moreover,we presented an adaptive dynamic decision fusion strategy to optimise the model's performance by focusing on the most relevant features in each modality.Finally,we comprehensively identified fine-grained nursing behaviours by integrating audio and fused information,while incorporating angle information from the real-time sound source localisation system to accurately determine whether the sound cues originate from the target sow.Our results demonstrate that the proposed method achieves an accuracy of 98.42%for general sow nursing behaviour and 94.37%for fine-grained nursing behaviour,including nursing with and without the calling-to-nurse sound,and non-nursing behaviours.This fine-grained nursing information can provide a more nuanced understanding of the sow's health and lactation willingness,thereby enhancing management practices in pig farming.展开更多
基金supported by the Natural Science Foundation of Henan Province,China.(No,222300420596).
文摘Impact ground pressure events occur frequently in coal mining processes,significantly affecting the personal safety of construction workers.Real-time microseismic monitoring of coal rock body rupture information can provide early warnings,and the seismic source location method is an essential indicator for evaluating a microseismic monitoring system.This paper proposes a nonlinear hybrid optimal particle swarm optimisation(PSO)microseismic positioning method based on this technique.The method first improves the PSO algorithm by using the global search performance of this method to quickly find a feasible solution and provide a better initial solution for the subsequent solution of the nonlinear optimal microseismic positioning method.This approach effectively prevents the problem of the microseismic positioning method falling into a local optimum because of an over-reliance on the initial value.In addition,the nonlinear optimal microseismic positioning method further narrows the localisation error based on the PSO algorithm.A simulation test demonstrates that the new method has a good positioning effect,and engineering application examples also show that the proposed method has high accuracy and strong positioning stability.The new method is better than the separate positioning method,both overall and in three directions,making it more suitable for solving the microseismic positioning problem.
基金supported by the“National Natural Science Foundation of China”(grant numbers:32302801 and 32202733)the“Guangdong International Technology Cooperation Project”(grant numbers:2021A0505030058).
文摘Nursing behaviour and the calling-to-nurse sound are crucial indicators for assessing sow maternal behaviour and nursing status.However,accurately identifying these behaviours for individual sows in complex indoor pig housing is challenging due to factors such as variable lighting,rail obstructions,and interference from other sows'calls.Multimodal fusion,which integrates audio and visual data,has proven to be an effective approach for improving accuracy and robustness in complex scenarios.In this study,we designed an audio-visual data acquisition system that includes a camera for synchronised audio and video capture,along with a custom-developed sound source localisation system that leverages a sound sensor to track sound direction.Specifically,we proposed a novel transformer-based audio-visual multimodal fusion(TMF)framework for recognising fine-grained sow nursing behaviour with or without the calling-to-nurse sound.Initially,a unimodal self-attention enhancement(USE)module was employed to augment video and audio features with global contextual information.Subsequently,we developed an audio-visual interaction enhancement(AVIE)module to compress relevant information and reduce noise using the information bottleneck principle.Moreover,we presented an adaptive dynamic decision fusion strategy to optimise the model's performance by focusing on the most relevant features in each modality.Finally,we comprehensively identified fine-grained nursing behaviours by integrating audio and fused information,while incorporating angle information from the real-time sound source localisation system to accurately determine whether the sound cues originate from the target sow.Our results demonstrate that the proposed method achieves an accuracy of 98.42%for general sow nursing behaviour and 94.37%for fine-grained nursing behaviour,including nursing with and without the calling-to-nurse sound,and non-nursing behaviours.This fine-grained nursing information can provide a more nuanced understanding of the sow's health and lactation willingness,thereby enhancing management practices in pig farming.
