Pose-invariant facial expression recognition(FER)is an active but challenging research topic in computer vision.Especially with the involvement of diverse observation angles,FER makes the training parameter models inc...Pose-invariant facial expression recognition(FER)is an active but challenging research topic in computer vision.Especially with the involvement of diverse observation angles,FER makes the training parameter models inconsistent from one view to another.This study develops a deep global multiple-scale and local patches attention(GMS-LPA)dual-branch network for pose-invariant FER to weaken the influence of pose variation and selfocclusion on recognition accuracy.In this research,the designed GMS-LPA network contains four main parts,i.e.,the feature extraction module,the global multiple-scale(GMS)module,the local patches attention(LPA)module,and the model-level fusion model.The feature extraction module is designed to extract and normalize texture information to the same size.The GMS model can extract deep global features with different receptive fields,releasing the sensitivity of deeper convolution layers to pose-variant and self-occlusion.The LPA module is built to force the network to focus on local salient features,which can lower the effect of pose variation and self-occlusion on recognition results.Subsequently,the extracted features are fused with a model-level strategy to improve recognition accuracy.Extensive experimentswere conducted on four public databases,and the recognition results demonstrated the feasibility and validity of the proposed methods.展开更多
Long-term and widespread use of plastic mulching has led to the accumulation of residual plastic film(RPF)in farmland soils of Xinjiang,China.However,there is no specific quantitative basis for RPF pollution or a clea...Long-term and widespread use of plastic mulching has led to the accumulation of residual plastic film(RPF)in farmland soils of Xinjiang,China.However,there is no specific quantitative basis for RPF pollution or a clear understanding of the influence of residual film on crop growth.The aim of this study was to investigate the effect of RPF on the growth of cotton,an important cash crop of Xinjiang.Based on the field conditions and previous reports,various amount of residual film was applied in 0-30 cm soil layer.The growth index including emergence rate,dry matter,and yield of cotton was examined at different growth stages under different soil residual film levels.Results demonstrated a significant effect of RPF on soil moisture distribution and movement.Plastic residues had a significant effect on cotton growth at levels above 200 kg/hm2,and the yield decreased as the RPF amount increased.Based on these findings,200 kg/hm2 was suggested as a threshold level to determine the effects of RPF on cotton.This study provided a basis to rate RPF pollution in farmland soils and help understand the impact of pollution on crop productivity.展开更多
Since there are many interacting influence factors of the comfortable degree of lactating sows,a method that combines improved analytic hierarchy process(IAHP)and fuzzy comprehensive evaluation(FCE)was introduced to c...Since there are many interacting influence factors of the comfortable degree of lactating sows,a method that combines improved analytic hierarchy process(IAHP)and fuzzy comprehensive evaluation(FCE)was introduced to conduct a quantitative evaluation of the comfortable degree.Besides,an evaluation index system was established,and the weights of different indicators were determined by using IAHP method,including temperature,relative humidity,concentrations of carbon dioxide(CO_(2)),ammonia(NH_(3)),hydrogen sulfide(H_(2)S),and air speed.The construction method of fuzzy membership function and the calculation method of the parameters were proposed following the principle that the summation of membership degrees is equal to 1.Three basic types of membership functions(MFs),i.e.,ridgemf,gaussmf,and trimf were used to build an evaluation model which fitted IAHP-FCE well.The proposed method was verified and applied based on the environmental data in different seasons obtained from a pig farm in Zhenjiang City,Jiangsu Province,China.It is demonstrated that the proposed IAHP-FCE model with various types of MFs has drawn a unique and consistent conclusion.Moreover,the IAHP-FCE model has a higher correlation coefficient of 0.874 compared with the single-factor evaluation(SFE)model.The IAHP-FCE model could be served as a beneficial strategy for the precise regulation and early warning of environmental conditions to improve sow welfare.展开更多
To precisely meet the nutritional requirements of sows during the stages of pregnancy and lactation,a precision feeding system was developed by using the intelligent sow feeder combined with a rule-based expert system...To precisely meet the nutritional requirements of sows during the stages of pregnancy and lactation,a precision feeding system was developed by using the intelligent sow feeder combined with a rule-based expert system and the Internet of Things(IoTs).The model of uncertain knowledge representation was established for inference by using the certainty factor.The daily feeding amount of each sow was calculated by the expert system.An improved pattern matching algorithm Reused Degree Model-RETE(RDM-RETE)was proposed for the decision of daily feeding amount,which sped up inference by optimizing the RETE network topology.A prediction model of daily feeding amount was established by a rule-based expert system and the precision feeding was achieved by an accurate control technology of variable volume.The experimental results demonstrated that the HASH-RDM-RETE algorithm could effectively reduce the network complexity and improve the inference efficiency.The feeding amount decided by the expert system was a logarithmic model,which was consistent with the feeding law of lactating sows.The inferential feeding amount was adopted as the predicted feed intake and the coefficient of correlation between predicted feed intake and actual feed intake was greater than or equal to 0.99.Each sow was fed at different feeding intervals and different feed amounts for each meal in a day.The feed intake was 26.84% higher than that of artificial feeding during lactation days(p<0.05).The piglets weaned per sow per year(PSY)can be increased by 1.51 compared with that of relatively high levels in domestic pig farms.This system is stable in feeding and lowers the breeding cost that can be applied in precision feeding in swine production.展开更多
基金supported by the National Natural Science Foundation of China (No.31872399)Advantage Discipline Construction Project (PAPD,No.6-2018)of Jiangsu University。
文摘Pose-invariant facial expression recognition(FER)is an active but challenging research topic in computer vision.Especially with the involvement of diverse observation angles,FER makes the training parameter models inconsistent from one view to another.This study develops a deep global multiple-scale and local patches attention(GMS-LPA)dual-branch network for pose-invariant FER to weaken the influence of pose variation and selfocclusion on recognition accuracy.In this research,the designed GMS-LPA network contains four main parts,i.e.,the feature extraction module,the global multiple-scale(GMS)module,the local patches attention(LPA)module,and the model-level fusion model.The feature extraction module is designed to extract and normalize texture information to the same size.The GMS model can extract deep global features with different receptive fields,releasing the sensitivity of deeper convolution layers to pose-variant and self-occlusion.The LPA module is built to force the network to focus on local salient features,which can lower the effect of pose variation and self-occlusion on recognition results.Subsequently,the extracted features are fused with a model-level strategy to improve recognition accuracy.Extensive experimentswere conducted on four public databases,and the recognition results demonstrated the feasibility and validity of the proposed methods.
基金This work was financially supported by National key R&D plan of China(No.2017YFD0701102)the Corps key R&D projects(No.2019AB007)+2 种基金the Special Fund for Agroscientific Research in the Public Interest(No.201503105)and the National Natural Science Foundation of China(Grant No.11562019)The authors are grateful to the farmers of the trial area for their cooperation.
文摘Long-term and widespread use of plastic mulching has led to the accumulation of residual plastic film(RPF)in farmland soils of Xinjiang,China.However,there is no specific quantitative basis for RPF pollution or a clear understanding of the influence of residual film on crop growth.The aim of this study was to investigate the effect of RPF on the growth of cotton,an important cash crop of Xinjiang.Based on the field conditions and previous reports,various amount of residual film was applied in 0-30 cm soil layer.The growth index including emergence rate,dry matter,and yield of cotton was examined at different growth stages under different soil residual film levels.Results demonstrated a significant effect of RPF on soil moisture distribution and movement.Plastic residues had a significant effect on cotton growth at levels above 200 kg/hm2,and the yield decreased as the RPF amount increased.Based on these findings,200 kg/hm2 was suggested as a threshold level to determine the effects of RPF on cotton.This study provided a basis to rate RPF pollution in farmland soils and help understand the impact of pollution on crop productivity.
基金The study is financially supported by the National Natural Science Foundation of China(Grant No.31172243)Agricultural Science and Technology Independent Innovation Fund Project(Grant No.CX(16)1006)of Jiangsu Province,Advantage Discipline Construction Project(PAPD,No.87-2018)of Jiangsu UniversityPostgraduate Research&Practice Innovation Program of Jiangsu Province(Grant No.KYCX18-2262).
文摘Since there are many interacting influence factors of the comfortable degree of lactating sows,a method that combines improved analytic hierarchy process(IAHP)and fuzzy comprehensive evaluation(FCE)was introduced to conduct a quantitative evaluation of the comfortable degree.Besides,an evaluation index system was established,and the weights of different indicators were determined by using IAHP method,including temperature,relative humidity,concentrations of carbon dioxide(CO_(2)),ammonia(NH_(3)),hydrogen sulfide(H_(2)S),and air speed.The construction method of fuzzy membership function and the calculation method of the parameters were proposed following the principle that the summation of membership degrees is equal to 1.Three basic types of membership functions(MFs),i.e.,ridgemf,gaussmf,and trimf were used to build an evaluation model which fitted IAHP-FCE well.The proposed method was verified and applied based on the environmental data in different seasons obtained from a pig farm in Zhenjiang City,Jiangsu Province,China.It is demonstrated that the proposed IAHP-FCE model with various types of MFs has drawn a unique and consistent conclusion.Moreover,the IAHP-FCE model has a higher correlation coefficient of 0.874 compared with the single-factor evaluation(SFE)model.The IAHP-FCE model could be served as a beneficial strategy for the precise regulation and early warning of environmental conditions to improve sow welfare.
基金financially supported by the National Natural Science Foundation of China(Grant No.31172243)Agricultural Science and Technology Independent Innovation Fund Project[CX(16)1006]of Jiangsu Province,China.
文摘To precisely meet the nutritional requirements of sows during the stages of pregnancy and lactation,a precision feeding system was developed by using the intelligent sow feeder combined with a rule-based expert system and the Internet of Things(IoTs).The model of uncertain knowledge representation was established for inference by using the certainty factor.The daily feeding amount of each sow was calculated by the expert system.An improved pattern matching algorithm Reused Degree Model-RETE(RDM-RETE)was proposed for the decision of daily feeding amount,which sped up inference by optimizing the RETE network topology.A prediction model of daily feeding amount was established by a rule-based expert system and the precision feeding was achieved by an accurate control technology of variable volume.The experimental results demonstrated that the HASH-RDM-RETE algorithm could effectively reduce the network complexity and improve the inference efficiency.The feeding amount decided by the expert system was a logarithmic model,which was consistent with the feeding law of lactating sows.The inferential feeding amount was adopted as the predicted feed intake and the coefficient of correlation between predicted feed intake and actual feed intake was greater than or equal to 0.99.Each sow was fed at different feeding intervals and different feed amounts for each meal in a day.The feed intake was 26.84% higher than that of artificial feeding during lactation days(p<0.05).The piglets weaned per sow per year(PSY)can be increased by 1.51 compared with that of relatively high levels in domestic pig farms.This system is stable in feeding and lowers the breeding cost that can be applied in precision feeding in swine production.
