Defect detection is vital in the nonwoven material industry,ensuring surface quality before producing finished products.Recently,deep learning and computer vision advancements have revolutionized defect detection,maki...Defect detection is vital in the nonwoven material industry,ensuring surface quality before producing finished products.Recently,deep learning and computer vision advancements have revolutionized defect detection,making it a widely adopted approach in various industrial fields.This paper mainly studied the defect detection method for nonwoven materials based on the improved Nano Det-Plus model.Using the constructed samples of defects in nonwoven materials as the research objects,transfer learning experiments were conducted based on the Nano DetPlus object detection framework.Within this framework,the Backbone,path aggregation feature pyramid network(PAFPN)and Head network models were compared and trained through a process of freezing,with the ultimate aim of bolstering the model's feature extraction abilities and elevating detection accuracy.The half-precision quantization method was used to optimize the model after transfer learning experiments,reducing model weights and computational complexity to improve the detection speed.Performance comparisons were conducted between the improved model and the original Nano Det-Plus model,YOLO,SSD and other common industrial defect detection algorithms,validating that the improved methods based on transfer learning and semi-precision quantization enabled the model to meet the practical requirements of industrial production.展开更多
Earthquake precursor data have been used as an important basis for earthquake prediction.In this study,a recurrent neural network(RNN)architecture with long short-term memory(LSTM)units is utilized to develop a predic...Earthquake precursor data have been used as an important basis for earthquake prediction.In this study,a recurrent neural network(RNN)architecture with long short-term memory(LSTM)units is utilized to develop a predictive model for normal data.Furthermore,the prediction errors from the predictive models are used to indicate normal or abnormal behavior.An additional advantage of using the LSTM networks is that the earthquake precursor data can be directly fed into the network without any elaborate preprocessing as required by other approaches.Furthermore,no prior information on abnormal data is needed by these networks as they are trained only using normal data.Experiments using three groups of real data were conducted to compare the anomaly detection results of the proposed method with those of manual recognition.The comparison results indicated that the proposed LSTM network achieves promising results and is viable for detecting anomalies in earthquake precursor data.展开更多
This paper proposes a learning-based method for text detection and text segmentation in natural scene images. First, the input image is decomposed into multiple connected-components (CCs) by Niblack clustering algorit...This paper proposes a learning-based method for text detection and text segmentation in natural scene images. First, the input image is decomposed into multiple connected-components (CCs) by Niblack clustering algorithm. Then all the CCs including text CCs and non-text CCs are verified on their text features by a 2-stage classification module, where most non-text CCs are discarded by an attentional cascade classifier and remaining CCs are further verified by an SVM. All the accepted CCs are output to result in text only binary image. Experiments with many images in different scenes showed satisfactory performance of our proposed method.展开更多
Due to the influence of terrain structure,meteorological conditions and various factors,there are anomalous data in automatic dependent surveillance-broadcast(ADS-B)message.The ADS-B equipment can be used for position...Due to the influence of terrain structure,meteorological conditions and various factors,there are anomalous data in automatic dependent surveillance-broadcast(ADS-B)message.The ADS-B equipment can be used for positioning of general aviation aircraft.Aim to acquire the accurate position information of aircraft and detect anomaly data,the ADS-B anomaly data detection model based on deep learning and difference of Gaussian(DoG)approach is proposed.First,according to the characteristic of ADS-B data,the ADS-B position data are transformed into the coordinate system.And the origin of the coordinate system is set up as the take-off point.Then,based on the kinematic principle,the ADS-B anomaly data can be removed.Moreover,the details of the ADS-B position data can be got by the DoG approach.Finally,the long short-term memory(LSTM)neural network is used to optimize the recurrent neural network(RNN)with severe gradient reduction for processing ADS-B data.The position data of ADS-B are reconstructed by the sequence to sequence(seq2seq)model which is composed of LSTM neural network,and the reconstruction error is used to detect the anomalous data.Based on the real flight data of general aviation aircraft,the simulation results show that the anomaly data can be detected effectively by the proposed method of reconstructing ADS-B data with the seq2seq model,and its running time is reduced.Compared with the RNN,the accuracy of anomaly detection is increased by 2.7%.The performance of the proposed model is better than that of the traditional anomaly detection models.展开更多
In order to improve the accuracy of threaded hole object detection,combining a dual camera vision system with the Hough transform circle detection,we propose an object detection method of artifact threaded hole based ...In order to improve the accuracy of threaded hole object detection,combining a dual camera vision system with the Hough transform circle detection,we propose an object detection method of artifact threaded hole based on Faster region-ased convolutional neural network(Faster R-CNN).First,a dual camera image acquisition system is established.One industrial camera placed at a high position is responsible for collecting the whole image of the workpiece,and the suspected screw hole position on the workpiece can be preliminarily selected by Hough transform detection algorithm.Then,the other industrial camera is responsible for collecting the local images of the suspected screw holes that have been detected by Hough transform one by one.After that,ResNet50-based Faster R-CNN object detection model is trained on the self-built screw hole data set.Finally,the local image of the threaded hole is input into the trained Faster R-CNN object detection model for further identification and location.The experimental results show that the proposed method can effectively avoid small object detection of threaded holes,and compared with the method that only uses Hough transform or Faster RCNN object detection alone,it has high recognition and positioning accuracy.展开更多
The purpose of this research was to study learning retention in undergraduate biology students on the topic of enzyme properties by using simple enzyme activity from vegetables and fruits. A hands-on practical was dev...The purpose of this research was to study learning retention in undergraduate biology students on the topic of enzyme properties by using simple enzyme activity from vegetables and fruits. A hands-on practical was developed to simplify detection of enzyme activity of amylase, protease and lipase on starch agar, dry whole milk agar, and trihutyrin agar, respectively. The subjects of the study were 24 senior undergraduates who studied in the Program of General Science, Faculty of Science, Srinakharinwirot University, Bangkok, in three semesters during 2007 - 2008. The basic concepts of enzymes, e.g., substrate specificity, how to detect enzymes and optimal enzyme conditions, were taught before the practical. The first enzyme, protease, was used in the second semester of 2007, and then changed to be lipase and protease in the first and second semesters of 2008, respectively. Ten open-ended questions were used to assess students in all semesters. In agreement with the constructivist learning model, it was demonstrated that students had learning retention and applied their prior knowledge to other enzyme experiments.展开更多
This paper presents a novel system for violent scenes detection, which is based on machine learning to handle visual and audio features. MKL （Multiple Kernel Learning） is applied so that multimodality of videos can ...This paper presents a novel system for violent scenes detection, which is based on machine learning to handle visual and audio features. MKL （Multiple Kernel Learning） is applied so that multimodality of videos can be maximized. The largest features of our system is that mid-level concepts clustering is proposed and implemented in order to learn mid-level concepts implicitly. By this algorithm, our system does not need manually tagged annotations. The whole system is trained on the dataset from MediaEval 2013 Affect Task and evaluated by its official metric. The obtained results outperformed its best score.展开更多
Psychological studies on human subjects show that contrast detection learning promote learner＇s sensitivity to visual stimulus contrast. The underlying neural mechanisms remain unknown. In this study, three cats （Fe...Psychological studies on human subjects show that contrast detection learning promote learner＇s sensitivity to visual stimulus contrast. The underlying neural mechanisms remain unknown. In this study, three cats （Felis catus） were trained to perform monocularly a contrast detection task by two-altemative forced choice method. The perceptual ability of each cat improved remarkably with learning as indicated by a significantly increased contrast sensitivity to visual stimuli. The learning effect displayed an evident specificity to the eye employed for learning but could partially transfer to the naive eye, prompting the possibility that contrast detection learning might cause neural plasticity before and after the information from both eyes are merged in the visual pathway. Further, the contrast sensitivity improvement was evident basically around the spatial frequency （SF） used for learning, which suggested that contrast detection learning effect showed, to some extent, a SF specificity. This study indicates that cat exhibits a property of contrast detection learning similar to human subjects and can be used as an animal model for subsequent investigations on the neural correlates that mediate learning-induced contrast sensitivity improvement in humans.展开更多
基金National Key Research and Development Program of China(Nos.2022YFB4700600 and 2022YFB4700605)National Natural Science Foundation of China(Nos.61771123 and 62171116)+1 种基金Fundamental Research Funds for the Central UniversitiesGraduate Student Innovation Fund of Donghua University,China(No.CUSF-DH-D-2022044)。
文摘Defect detection is vital in the nonwoven material industry,ensuring surface quality before producing finished products.Recently,deep learning and computer vision advancements have revolutionized defect detection,making it a widely adopted approach in various industrial fields.This paper mainly studied the defect detection method for nonwoven materials based on the improved Nano Det-Plus model.Using the constructed samples of defects in nonwoven materials as the research objects,transfer learning experiments were conducted based on the Nano DetPlus object detection framework.Within this framework,the Backbone,path aggregation feature pyramid network(PAFPN)and Head network models were compared and trained through a process of freezing,with the ultimate aim of bolstering the model's feature extraction abilities and elevating detection accuracy.The half-precision quantization method was used to optimize the model after transfer learning experiments,reducing model weights and computational complexity to improve the detection speed.Performance comparisons were conducted between the improved model and the original Nano Det-Plus model,YOLO,SSD and other common industrial defect detection algorithms,validating that the improved methods based on transfer learning and semi-precision quantization enabled the model to meet the practical requirements of industrial production.
基金supported by the Science for Earthquake Resilience of China(No.XH18027)Research and Development of Comprehensive Geophysical Field Observing Instrument in China's Mainland(No.Y201703)Research Fund Project of Shandong Earthquake Agency(Nos.JJ1505Y and JJ1602)
文摘Earthquake precursor data have been used as an important basis for earthquake prediction.In this study,a recurrent neural network(RNN)architecture with long short-term memory(LSTM)units is utilized to develop a predictive model for normal data.Furthermore,the prediction errors from the predictive models are used to indicate normal or abnormal behavior.An additional advantage of using the LSTM networks is that the earthquake precursor data can be directly fed into the network without any elaborate preprocessing as required by other approaches.Furthermore,no prior information on abnormal data is needed by these networks as they are trained only using normal data.Experiments using three groups of real data were conducted to compare the anomaly detection results of the proposed method with those of manual recognition.The comparison results indicated that the proposed LSTM network achieves promising results and is viable for detecting anomalies in earthquake precursor data.
基金Project supported by the OMRON and SJTU Collaborative Founda-tion under PVS project (2005.03~2005.10)
文摘This paper proposes a learning-based method for text detection and text segmentation in natural scene images. First, the input image is decomposed into multiple connected-components (CCs) by Niblack clustering algorithm. Then all the CCs including text CCs and non-text CCs are verified on their text features by a 2-stage classification module, where most non-text CCs are discarded by an attentional cascade classifier and remaining CCs are further verified by an SVM. All the accepted CCs are output to result in text only binary image. Experiments with many images in different scenes showed satisfactory performance of our proposed method.
基金supported by the National Key R&D Program of China(No.2018AAA0100804)the Talent Project of Revitalization Liaoning(No.XLYC1907022)+5 种基金the Key R&D Projects of Liaoning Province(No.2020JH2/10100045)the Capacity Building of Civil Aviation Safety(No.TMSA1614)the Natural Science Foundation of Liaoning Province(No.2019-MS-251)the Scientific Research Project of Liaoning Provincial Department of Education(Nos.L201705,L201716)the High-Level Innovation Talent Project of Shenyang(No.RC190030)the Second Young and Middle-Aged Talents Support Program of Shenyang Aerospace University.
文摘Due to the influence of terrain structure,meteorological conditions and various factors,there are anomalous data in automatic dependent surveillance-broadcast(ADS-B)message.The ADS-B equipment can be used for positioning of general aviation aircraft.Aim to acquire the accurate position information of aircraft and detect anomaly data,the ADS-B anomaly data detection model based on deep learning and difference of Gaussian(DoG)approach is proposed.First,according to the characteristic of ADS-B data,the ADS-B position data are transformed into the coordinate system.And the origin of the coordinate system is set up as the take-off point.Then,based on the kinematic principle,the ADS-B anomaly data can be removed.Moreover,the details of the ADS-B position data can be got by the DoG approach.Finally,the long short-term memory(LSTM)neural network is used to optimize the recurrent neural network(RNN)with severe gradient reduction for processing ADS-B data.The position data of ADS-B are reconstructed by the sequence to sequence(seq2seq)model which is composed of LSTM neural network,and the reconstruction error is used to detect the anomalous data.Based on the real flight data of general aviation aircraft,the simulation results show that the anomaly data can be detected effectively by the proposed method of reconstructing ADS-B data with the seq2seq model,and its running time is reduced.Compared with the RNN,the accuracy of anomaly detection is increased by 2.7%.The performance of the proposed model is better than that of the traditional anomaly detection models.
文摘In order to improve the accuracy of threaded hole object detection,combining a dual camera vision system with the Hough transform circle detection,we propose an object detection method of artifact threaded hole based on Faster region-ased convolutional neural network(Faster R-CNN).First,a dual camera image acquisition system is established.One industrial camera placed at a high position is responsible for collecting the whole image of the workpiece,and the suspected screw hole position on the workpiece can be preliminarily selected by Hough transform detection algorithm.Then,the other industrial camera is responsible for collecting the local images of the suspected screw holes that have been detected by Hough transform one by one.After that,ResNet50-based Faster R-CNN object detection model is trained on the self-built screw hole data set.Finally,the local image of the threaded hole is input into the trained Faster R-CNN object detection model for further identification and location.The experimental results show that the proposed method can effectively avoid small object detection of threaded holes,and compared with the method that only uses Hough transform or Faster RCNN object detection alone,it has high recognition and positioning accuracy.
文摘The purpose of this research was to study learning retention in undergraduate biology students on the topic of enzyme properties by using simple enzyme activity from vegetables and fruits. A hands-on practical was developed to simplify detection of enzyme activity of amylase, protease and lipase on starch agar, dry whole milk agar, and trihutyrin agar, respectively. The subjects of the study were 24 senior undergraduates who studied in the Program of General Science, Faculty of Science, Srinakharinwirot University, Bangkok, in three semesters during 2007 - 2008. The basic concepts of enzymes, e.g., substrate specificity, how to detect enzymes and optimal enzyme conditions, were taught before the practical. The first enzyme, protease, was used in the second semester of 2007, and then changed to be lipase and protease in the first and second semesters of 2008, respectively. Ten open-ended questions were used to assess students in all semesters. In agreement with the constructivist learning model, it was demonstrated that students had learning retention and applied their prior knowledge to other enzyme experiments.
文摘This paper presents a novel system for violent scenes detection, which is based on machine learning to handle visual and audio features. MKL （Multiple Kernel Learning） is applied so that multimodality of videos can be maximized. The largest features of our system is that mid-level concepts clustering is proposed and implemented in order to learn mid-level concepts implicitly. By this algorithm, our system does not need manually tagged annotations. The whole system is trained on the dataset from MediaEval 2013 Affect Task and evaluated by its official metric. The obtained results outperformed its best score.
基金Supported by Natural Science Foundation of Anhui Province(070413138)the foundation of Key Laboratory of Anhui Province and the Key Research Foundation from Education Department of Anhui Province(KJ2009A167)
文摘Psychological studies on human subjects show that contrast detection learning promote learner＇s sensitivity to visual stimulus contrast. The underlying neural mechanisms remain unknown. In this study, three cats （Felis catus） were trained to perform monocularly a contrast detection task by two-altemative forced choice method. The perceptual ability of each cat improved remarkably with learning as indicated by a significantly increased contrast sensitivity to visual stimuli. The learning effect displayed an evident specificity to the eye employed for learning but could partially transfer to the naive eye, prompting the possibility that contrast detection learning might cause neural plasticity before and after the information from both eyes are merged in the visual pathway. Further, the contrast sensitivity improvement was evident basically around the spatial frequency （SF） used for learning, which suggested that contrast detection learning effect showed, to some extent, a SF specificity. This study indicates that cat exhibits a property of contrast detection learning similar to human subjects and can be used as an animal model for subsequent investigations on the neural correlates that mediate learning-induced contrast sensitivity improvement in humans.
