Pub Date : 2023-11-14DOI: 10.1007/s44196-023-00365-9
Jian Huang, Guangpeng Zhang, Li juan Ren, Nina Wang
Abstract When manually polishing blades, skilled workers can quickly machine a blade by observing the characteristics of the polishing sparks. To help workers better recognize spark images, we used an industrial charge-coupled device (CCD) camera to capture the spark images. Firstly, the spark image region detected by yolo5, then segment from the background. Secondly, the target region was further segmented and refined in a fully connected conditional random field (CRF), from which the complete spark image obtained. Experimental results showed that this method could quickly and accurately segment whole spark image. The test results showed that this method was better than other image segmentation algorithms. Our method could better segment irregular image, improve recognition and segmentation efficiency of spark image, achieve automatic image segmentation, and replace human observation.
{"title":"A New Image Segmentation Method Based on the YOLO5 and Fully Connected CRF","authors":"Jian Huang, Guangpeng Zhang, Li juan Ren, Nina Wang","doi":"10.1007/s44196-023-00365-9","DOIUrl":"https://doi.org/10.1007/s44196-023-00365-9","url":null,"abstract":"Abstract When manually polishing blades, skilled workers can quickly machine a blade by observing the characteristics of the polishing sparks. To help workers better recognize spark images, we used an industrial charge-coupled device (CCD) camera to capture the spark images. Firstly, the spark image region detected by yolo5, then segment from the background. Secondly, the target region was further segmented and refined in a fully connected conditional random field (CRF), from which the complete spark image obtained. Experimental results showed that this method could quickly and accurately segment whole spark image. The test results showed that this method was better than other image segmentation algorithms. Our method could better segment irregular image, improve recognition and segmentation efficiency of spark image, achieve automatic image segmentation, and replace human observation.","PeriodicalId":54967,"journal":{"name":"International Journal of Computational Intelligence Systems","volume":"43 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134953419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-14DOI: 10.1007/s44196-023-00323-5
Di Wu, Yan Xiao
Abstract Redundant nodes in a kernel incremental extreme learning machine (KI-ELM) increase ineffective iterations and reduce learning efficiency. To address this problem, this study established a novel improved hybrid intelligent deep kernel incremental extreme learning machine (HI-DKIELM), which is based on a hybrid intelligent algorithm and a KI-ELM. First, a hybrid intelligent algorithm was established based on the artificial transgender longicorn algorithm and multiple population gray wolf optimization methods to reduce the parameters of hidden layer neurons and then to determine the effective number of hidden layer neurons. The learning efficiency of the algorithm was improved through the reduction of network complexity. Then, to improve the classification accuracy and generalization performance of the algorithm, a deep network structure was introduced to the KI-ELM to gradually extract the original input data layer by layer and realize high-dimensional mapping of data. The experimental results show that the number of network nodes of HI-DKIELM algorithm is obviously reduced, which reduces the network complexity of ELM and greatly improves the learning efficiency of the algorithm. From the regression and classification experiments, its CCPP can be seen that the training error and test error of the HI-DKIELM algorithm proposed in this paper are 0.0417 and 0.0435, which are 0.0103 and 0.0078 lower than the suboptimal algorithm, respectively. On the Boston Housing database, the average and standard deviation of this algorithm are 98.21 and 0.0038, which are 6.2 and 0.0003 higher than the suboptimal algorithm, respectively.
{"title":"A Novel Deep Kernel Incremental Extreme Learning Machine Based on Artificial Transgender Longicorn Algorithm and Multiple Population Gray Wolf Optimization Methods","authors":"Di Wu, Yan Xiao","doi":"10.1007/s44196-023-00323-5","DOIUrl":"https://doi.org/10.1007/s44196-023-00323-5","url":null,"abstract":"Abstract Redundant nodes in a kernel incremental extreme learning machine (KI-ELM) increase ineffective iterations and reduce learning efficiency. To address this problem, this study established a novel improved hybrid intelligent deep kernel incremental extreme learning machine (HI-DKIELM), which is based on a hybrid intelligent algorithm and a KI-ELM. First, a hybrid intelligent algorithm was established based on the artificial transgender longicorn algorithm and multiple population gray wolf optimization methods to reduce the parameters of hidden layer neurons and then to determine the effective number of hidden layer neurons. The learning efficiency of the algorithm was improved through the reduction of network complexity. Then, to improve the classification accuracy and generalization performance of the algorithm, a deep network structure was introduced to the KI-ELM to gradually extract the original input data layer by layer and realize high-dimensional mapping of data. The experimental results show that the number of network nodes of HI-DKIELM algorithm is obviously reduced, which reduces the network complexity of ELM and greatly improves the learning efficiency of the algorithm. From the regression and classification experiments, its CCPP can be seen that the training error and test error of the HI-DKIELM algorithm proposed in this paper are 0.0417 and 0.0435, which are 0.0103 and 0.0078 lower than the suboptimal algorithm, respectively. On the Boston Housing database, the average and standard deviation of this algorithm are 98.21 and 0.0038, which are 6.2 and 0.0003 higher than the suboptimal algorithm, respectively.","PeriodicalId":54967,"journal":{"name":"International Journal of Computational Intelligence Systems","volume":"43 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134953416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-14DOI: 10.1007/s44196-023-00364-w
Hua Zhang, Zhengang Jiang, Guoxun Zheng, Xuekun Yao
Abstract Semantic segmentation of high-resolution remote sensing images has emerged as one of the foci of research in the remote sensing field, which can accurately identify objects on the ground and determine their localization. In contrast, the traditional deep learning-based semantic segmentation, on the other hand, requires a large amount of annotated data, which is unsuitable for high-resolution remote sensing tasks with limited resources. It is therefore important to build a semantic segmentation method for high-resolution remote sensing images. In this paper, it is proposed an improved U-Net model based on transfer learning to solve the semantic segmentation problem of high-resolution remote sensing images. The model is based on the symmetric encoder–decoder structure of U-Net. For the encoder, transfer learning is applied and VGG16 is used as the backbone of the feature extraction network, and in the decoder, after upsampling using bilinear interpolation, it is performed multiscale fusion with the feature maps of the corresponding layers of the encoder in turn and is finally obtained the predicted value of each pixel to achieve precise localization. To verify the efficacy of the proposed network, experiments are performed on the ISPRS Vaihingen dataset. The experiments show that the applied method has achieved high-quality semantic segmentation results on the high-resolution remote sensing dataset, and the MIoU is 1.70%, 2.20%, and 2.33% higher on the training, validation, and test sets, respectively, and the IoU is 4.26%, 6.89%, and 5.44% higher for the automotive category compared to the traditional U-Net.
{"title":"Semantic Segmentation of High-Resolution Remote Sensing Images with Improved U-Net Based on Transfer Learning","authors":"Hua Zhang, Zhengang Jiang, Guoxun Zheng, Xuekun Yao","doi":"10.1007/s44196-023-00364-w","DOIUrl":"https://doi.org/10.1007/s44196-023-00364-w","url":null,"abstract":"Abstract Semantic segmentation of high-resolution remote sensing images has emerged as one of the foci of research in the remote sensing field, which can accurately identify objects on the ground and determine their localization. In contrast, the traditional deep learning-based semantic segmentation, on the other hand, requires a large amount of annotated data, which is unsuitable for high-resolution remote sensing tasks with limited resources. It is therefore important to build a semantic segmentation method for high-resolution remote sensing images. In this paper, it is proposed an improved U-Net model based on transfer learning to solve the semantic segmentation problem of high-resolution remote sensing images. The model is based on the symmetric encoder–decoder structure of U-Net. For the encoder, transfer learning is applied and VGG16 is used as the backbone of the feature extraction network, and in the decoder, after upsampling using bilinear interpolation, it is performed multiscale fusion with the feature maps of the corresponding layers of the encoder in turn and is finally obtained the predicted value of each pixel to achieve precise localization. To verify the efficacy of the proposed network, experiments are performed on the ISPRS Vaihingen dataset. The experiments show that the applied method has achieved high-quality semantic segmentation results on the high-resolution remote sensing dataset, and the MIoU is 1.70%, 2.20%, and 2.33% higher on the training, validation, and test sets, respectively, and the IoU is 4.26%, 6.89%, and 5.44% higher for the automotive category compared to the traditional U-Net.","PeriodicalId":54967,"journal":{"name":"International Journal of Computational Intelligence Systems","volume":"42 19","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134953443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Hand sketch psychological data are mysterious and can be used to detect mental disorders early and prevent them from getting worse and with irreversible consequences. The Original Bender Gestalt Test is a psychology test based on hand-sketched patterns. Mental disorders require an automated scoring system. Unfortunately, there is no automatic scoring system for the Original Bender Gestalt test for adults and children with high accuracy. Automating the Original Bender Gestalt test requires 3 phases: Phase 1, collecting a comprehensive Original Bender Gestalt dataset called OBGET. Phase 2, classifying patterns by a proposed method called MYOLO V5; and Phase 3, scoring classified patterns according to associated rules of psychological standard criteria. This research reviews a comprehensive OBGET dataset that includes 817 samples, labeling samples for mental disorders by a psychologist, statistical analysis, the proposed semi-automatic labeling of patterns, patterns classification applied the proposed modified YOLO V5 called MYOLO V5, and automatic scoring of drawing patterns. MYOLO V5 accuracy is 95% and the accuracy of the proposed method called OBGESS as a mental disorder detection is 90%. In this research, a new automatic computer-aided psychological hand sketch drawing test has been proposed.
{"title":"OBGESS: Automating Original Bender Gestalt Test Based on One Stage Deep Learning","authors":"Maryam Fathi Ahmadsaraei, Azam Bastanfard, Amineh Amini","doi":"10.1007/s44196-023-00353-z","DOIUrl":"https://doi.org/10.1007/s44196-023-00353-z","url":null,"abstract":"Abstract Hand sketch psychological data are mysterious and can be used to detect mental disorders early and prevent them from getting worse and with irreversible consequences. The Original Bender Gestalt Test is a psychology test based on hand-sketched patterns. Mental disorders require an automated scoring system. Unfortunately, there is no automatic scoring system for the Original Bender Gestalt test for adults and children with high accuracy. Automating the Original Bender Gestalt test requires 3 phases: Phase 1, collecting a comprehensive Original Bender Gestalt dataset called OBGET. Phase 2, classifying patterns by a proposed method called MYOLO V5; and Phase 3, scoring classified patterns according to associated rules of psychological standard criteria. This research reviews a comprehensive OBGET dataset that includes 817 samples, labeling samples for mental disorders by a psychologist, statistical analysis, the proposed semi-automatic labeling of patterns, patterns classification applied the proposed modified YOLO V5 called MYOLO V5, and automatic scoring of drawing patterns. MYOLO V5 accuracy is 95% and the accuracy of the proposed method called OBGESS as a mental disorder detection is 90%. In this research, a new automatic computer-aided psychological hand sketch drawing test has been proposed.","PeriodicalId":54967,"journal":{"name":"International Journal of Computational Intelligence Systems","volume":"44 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136347160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-13DOI: 10.1007/s44196-023-00361-z
Xiaoliang Xu
Abstract The integration of educational technology in the modern classroom has transformed the way students learn yet challenges in providing high-quality materials persist. To address this, we propose a novel support vector-based long short-term memory (LSTM) recommendation model. Our model combines support vector machines (SVM) and LSTM networks to enhance accuracy. The SVM analyzes material content, identifying key features for topic relevance. Meanwhile, the LSTM assesses word sequences to predict material relevance to the topic. We conducted experiments on a diverse instructional dataset, demonstrating superior performance in accuracy and relevance compared to existing models. Our model adapts to new data and continuously improves based on user feedback. Therefore, our Support Vector-based LSTM recommendation model can revolutionize instructional material recommendations. Its accuracy and relevance enhance student engagement and learning outcomes, optimizing the educational experience.
{"title":"Revolutionizing Education: Advanced Machine Learning Techniques for Precision Recommendation of Top-Quality Instructional Materials","authors":"Xiaoliang Xu","doi":"10.1007/s44196-023-00361-z","DOIUrl":"https://doi.org/10.1007/s44196-023-00361-z","url":null,"abstract":"Abstract The integration of educational technology in the modern classroom has transformed the way students learn yet challenges in providing high-quality materials persist. To address this, we propose a novel support vector-based long short-term memory (LSTM) recommendation model. Our model combines support vector machines (SVM) and LSTM networks to enhance accuracy. The SVM analyzes material content, identifying key features for topic relevance. Meanwhile, the LSTM assesses word sequences to predict material relevance to the topic. We conducted experiments on a diverse instructional dataset, demonstrating superior performance in accuracy and relevance compared to existing models. Our model adapts to new data and continuously improves based on user feedback. Therefore, our Support Vector-based LSTM recommendation model can revolutionize instructional material recommendations. Its accuracy and relevance enhance student engagement and learning outcomes, optimizing the educational experience.","PeriodicalId":54967,"journal":{"name":"International Journal of Computational Intelligence Systems","volume":"48 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136347521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-09DOI: 10.1007/s44196-023-00355-x
Mohamed Saied, Shawkat Guirguis, Magda Madbouly
Abstract The Internet-of-Things (IoT) environment has revolutionized the quality of living standards by enabling seamless connectivity and automation. However, the widespread adoption of IoT has also brought forth significant security challenges for manufacturers and consumers alike. Detecting network intrusions in IoT networks using machine learning techniques shows promising potential. However, selecting an appropriate machine learning algorithm for intrusion detection poses a considerable challenge. Improper algorithm selection can lead to reduced detection accuracy, increased risk of network infection, and compromised network security. This article provides a comparative evaluation to six state-of-the-art boosting-based algorithms for detecting intrusions in IoT. The methodology overview involves benchmarking the performance of the selected boosting-based algorithms in multi-class classification. The evaluation includes a comprehensive classification performance analysis includes accuracy, precision, detection rate, F1 score, as well as a temporal performance analysis includes training and testing times.
{"title":"A Comparative Study of Using Boosting-Based Machine Learning Algorithms for IoT Network Intrusion Detection","authors":"Mohamed Saied, Shawkat Guirguis, Magda Madbouly","doi":"10.1007/s44196-023-00355-x","DOIUrl":"https://doi.org/10.1007/s44196-023-00355-x","url":null,"abstract":"Abstract The Internet-of-Things (IoT) environment has revolutionized the quality of living standards by enabling seamless connectivity and automation. However, the widespread adoption of IoT has also brought forth significant security challenges for manufacturers and consumers alike. Detecting network intrusions in IoT networks using machine learning techniques shows promising potential. However, selecting an appropriate machine learning algorithm for intrusion detection poses a considerable challenge. Improper algorithm selection can lead to reduced detection accuracy, increased risk of network infection, and compromised network security. This article provides a comparative evaluation to six state-of-the-art boosting-based algorithms for detecting intrusions in IoT. The methodology overview involves benchmarking the performance of the selected boosting-based algorithms in multi-class classification. The evaluation includes a comprehensive classification performance analysis includes accuracy, precision, detection rate, F1 score, as well as a temporal performance analysis includes training and testing times.","PeriodicalId":54967,"journal":{"name":"International Journal of Computational Intelligence Systems","volume":" 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135241440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-07DOI: 10.1007/s44196-023-00359-7
Yu Zhang, Chunling Wang, Jia Wang
Abstract Zero-shot stance detection is both crucial and challenging because it demands detecting the stances of previously unseen targets in the inference stage. Learning transferable target invariant features effectively from training data is crucial for zero-shot stance detection. This paper proposes an adversarial adaptation approach for zero-shot stance detection, which applies an adversarial discriminative domain adaptation network to transfer knowledge efficiently. Specifically, the proposed model applies knowledge distillation to prevent overfitting the destination data and forgetting the learned source knowledge. Moreover, stance contrastive learning is applied to enhance the quality of feature representation for superior generalization, and sentiment information is extracted to assist with stance detection. The experimental results indicate that our model performs competitively on two benchmark datasets.
{"title":"Adversarial Distillation Adaptation Model with Sentiment Contrastive Learning for Zero-Shot Stance Detection","authors":"Yu Zhang, Chunling Wang, Jia Wang","doi":"10.1007/s44196-023-00359-7","DOIUrl":"https://doi.org/10.1007/s44196-023-00359-7","url":null,"abstract":"Abstract Zero-shot stance detection is both crucial and challenging because it demands detecting the stances of previously unseen targets in the inference stage. Learning transferable target invariant features effectively from training data is crucial for zero-shot stance detection. This paper proposes an adversarial adaptation approach for zero-shot stance detection, which applies an adversarial discriminative domain adaptation network to transfer knowledge efficiently. Specifically, the proposed model applies knowledge distillation to prevent overfitting the destination data and forgetting the learned source knowledge. Moreover, stance contrastive learning is applied to enhance the quality of feature representation for superior generalization, and sentiment information is extracted to assist with stance detection. The experimental results indicate that our model performs competitively on two benchmark datasets.","PeriodicalId":54967,"journal":{"name":"International Journal of Computational Intelligence Systems","volume":"40 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135432246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-07DOI: 10.1007/s44196-023-00348-w
Zhengjiang Wu, Xuyang Wu, Junwei Luo
Abstract It is a challenge to assemble an enormous amount of metagenome data in metagenomics. Usually, metagenome cluster sequence before assembly accelerates the whole process. In SpaRC, sequences are defined as nodes and clustered by a parallel label propagation algorithm (LPA). To address the randomness of label selection from the parallel LPA during clustering and improve the completeness of metagenome sequence clustering, Spark-based parallel label diffusion and label selection community detection algorithm is proposed in the paper to obtain more accurate clustering results. In this paper, the importance of sequence is defined based on the Jaccard similarity coefficient and its degree. The core sequence is defined as the one with the largest importance in its located community. Three strategies are formulated to reduce the randomness of label selection. Firstly, the core sequence label diffuses over its located cluster and becomes the initial label of other sequences. Those sequences that do not receive an initial label will select the sequence label with the highest importance in the neighbor sequences. Secondly, we perform improved label propagation in order of label frequency and sequence importance to reduce the randomness of label selection. Finally, a merge small communities step is added to increase the completeness of clustered clusters. The experimental results show that our proposed algorithm can effectively reduce the randomness of label selection, improve the purity, completeness, and F-Measure and reduce the runtime of metagenome sequence clustering.
{"title":"Spark-Based Label Diffusion and Label Selection Community Detection Algorithm for Metagenome Sequence Clustering","authors":"Zhengjiang Wu, Xuyang Wu, Junwei Luo","doi":"10.1007/s44196-023-00348-w","DOIUrl":"https://doi.org/10.1007/s44196-023-00348-w","url":null,"abstract":"Abstract It is a challenge to assemble an enormous amount of metagenome data in metagenomics. Usually, metagenome cluster sequence before assembly accelerates the whole process. In SpaRC, sequences are defined as nodes and clustered by a parallel label propagation algorithm (LPA). To address the randomness of label selection from the parallel LPA during clustering and improve the completeness of metagenome sequence clustering, Spark-based parallel label diffusion and label selection community detection algorithm is proposed in the paper to obtain more accurate clustering results. In this paper, the importance of sequence is defined based on the Jaccard similarity coefficient and its degree. The core sequence is defined as the one with the largest importance in its located community. Three strategies are formulated to reduce the randomness of label selection. Firstly, the core sequence label diffuses over its located cluster and becomes the initial label of other sequences. Those sequences that do not receive an initial label will select the sequence label with the highest importance in the neighbor sequences. Secondly, we perform improved label propagation in order of label frequency and sequence importance to reduce the randomness of label selection. Finally, a merge small communities step is added to increase the completeness of clustered clusters. The experimental results show that our proposed algorithm can effectively reduce the randomness of label selection, improve the purity, completeness, and F-Measure and reduce the runtime of metagenome sequence clustering.","PeriodicalId":54967,"journal":{"name":"International Journal of Computational Intelligence Systems","volume":"233 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135476084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-06DOI: 10.1007/s44196-023-00352-0
Siyong Fu, Qinghua Zhao, Zhen Fan, Qiuxiang Tao, Hesheng Liu
Abstract Unmanned vehicles need to know their location and direction information accurately to plan and navigate their paths. However, the positioning system is susceptible to interference from a variety of factors, which leads to increased positioning errors, thereby affecting the accuracy of unmanned vehicle positioning. An unmanned vehicle fusion positioning technology based on the "5G + Beidou" integrated positioning system was proposed. While using the "5G + Beidou" base station for positioning, the 3D point cloud image was fused, and the high-precision real-time positioning was carried out through the vehicle's autonomous navigation algorithm. This paper first analyzed the current situation and characteristics of GNSS technology and studied the key technologies and principles of the "5G + Beidou" integrated positioning system. Then, aiming at the difficulty of 5G base station deployment, the GNSS system parameter optimization scheme based on a multidimensional fusion structure was designed. Finally, in the experiment, it was verified that the fusion system could achieve higher precision positioning results compared with traditional single-dimensional GNSS and multi-dimensional GNSS. The technical advantages of "5G + Beidou" were used for data fusion processing of unmanned vehicles, and a positioning method based on the combination of 3D point cloud image and high-precision map was proposed. Through some experiments, it was concluded that the fusion location method could control the error below 0.1, which showed the accuracy of the fusion location.
{"title":"Unmanned Vehicle Fusion Positioning Technology Based on “5G + Beidou” and 3D Point Cloud Image","authors":"Siyong Fu, Qinghua Zhao, Zhen Fan, Qiuxiang Tao, Hesheng Liu","doi":"10.1007/s44196-023-00352-0","DOIUrl":"https://doi.org/10.1007/s44196-023-00352-0","url":null,"abstract":"Abstract Unmanned vehicles need to know their location and direction information accurately to plan and navigate their paths. However, the positioning system is susceptible to interference from a variety of factors, which leads to increased positioning errors, thereby affecting the accuracy of unmanned vehicle positioning. An unmanned vehicle fusion positioning technology based on the \"5G + Beidou\" integrated positioning system was proposed. While using the \"5G + Beidou\" base station for positioning, the 3D point cloud image was fused, and the high-precision real-time positioning was carried out through the vehicle's autonomous navigation algorithm. This paper first analyzed the current situation and characteristics of GNSS technology and studied the key technologies and principles of the \"5G + Beidou\" integrated positioning system. Then, aiming at the difficulty of 5G base station deployment, the GNSS system parameter optimization scheme based on a multidimensional fusion structure was designed. Finally, in the experiment, it was verified that the fusion system could achieve higher precision positioning results compared with traditional single-dimensional GNSS and multi-dimensional GNSS. The technical advantages of \"5G + Beidou\" were used for data fusion processing of unmanned vehicles, and a positioning method based on the combination of 3D point cloud image and high-precision map was proposed. Through some experiments, it was concluded that the fusion location method could control the error below 0.1, which showed the accuracy of the fusion location.","PeriodicalId":54967,"journal":{"name":"International Journal of Computational Intelligence Systems","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135636933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-31DOI: 10.1007/s44196-023-00351-1
Datian Liu, Haitao Yang, Zhang Lei
Abstract Three-dimensional (3D) human pose recognition techniques based on spatial data have gained attention. However, existing models and algorithms fail to achieve desired precision. We propose a 3D human motion pose recognition method using deep contrastive learning and an improved Transformer. The improved Transformer removes noise between human motion RGB and depth images, addressing orientation correlation in 3D models. Two-dimensional (2D) pose features are extracted from de-noised RGB images using a kernel generation module in a graph convolutional network (GCN). Depth features are extracted from de-noised depth images. The 2D pose features and depth features are fused using a regression module in the GCN to obtain 3D pose recognition results. The results demonstrate that the proposed method captures RGB and depth images, achieving high recognition accuracy and fast speed. The proposed method demonstrates good accuracy in 3D human motion pose recognition.
{"title":"Recognition Method with Deep Contrastive Learning and Improved Transformer for 3D Human Motion Pose","authors":"Datian Liu, Haitao Yang, Zhang Lei","doi":"10.1007/s44196-023-00351-1","DOIUrl":"https://doi.org/10.1007/s44196-023-00351-1","url":null,"abstract":"Abstract Three-dimensional (3D) human pose recognition techniques based on spatial data have gained attention. However, existing models and algorithms fail to achieve desired precision. We propose a 3D human motion pose recognition method using deep contrastive learning and an improved Transformer. The improved Transformer removes noise between human motion RGB and depth images, addressing orientation correlation in 3D models. Two-dimensional (2D) pose features are extracted from de-noised RGB images using a kernel generation module in a graph convolutional network (GCN). Depth features are extracted from de-noised depth images. The 2D pose features and depth features are fused using a regression module in the GCN to obtain 3D pose recognition results. The results demonstrate that the proposed method captures RGB and depth images, achieving high recognition accuracy and fast speed. The proposed method demonstrates good accuracy in 3D human motion pose recognition.","PeriodicalId":54967,"journal":{"name":"International Journal of Computational Intelligence Systems","volume":"2011 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135814150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：