Visual Question Answering (VQA) is a challenging problem that needs to combine concepts from computer vision and natural language processing. In recent years, researchers have proposed many methods for this typical multimodal problem. Most existing methods use a two-stream strategy, i.e., compute image and question features separately and fuse them using various techniques, rarely relying on higher-level image representations, to capture semantic and spatial relationships. Based on the above problems, a visual question answering model (CAM-GCN) based on Cooperative Attention Mechanism (CAM) and Graph Convolutional Network (GCN) is proposed. First, the graph learning module and the concept of graph convolution are combined to learn the problem-specific graph representation of the input image and capture the interactive image representation of the specific problem. Image region dependence, and finally, continue to optimize the fused features through feature enhancement. The test results on the VQA v2 dataset show that the CAM-GCN model achieves better classification results than the current representative models.
{"title":"Visual Question Answering Model Based on CAM and GCN","authors":"Ping Wen, Matthew Li, Zhang Zhen, Wang Ze","doi":"10.1145/3573942.3574090","DOIUrl":"https://doi.org/10.1145/3573942.3574090","url":null,"abstract":"Visual Question Answering (VQA) is a challenging problem that needs to combine concepts from computer vision and natural language processing. In recent years, researchers have proposed many methods for this typical multimodal problem. Most existing methods use a two-stream strategy, i.e., compute image and question features separately and fuse them using various techniques, rarely relying on higher-level image representations, to capture semantic and spatial relationships. Based on the above problems, a visual question answering model (CAM-GCN) based on Cooperative Attention Mechanism (CAM) and Graph Convolutional Network (GCN) is proposed. First, the graph learning module and the concept of graph convolution are combined to learn the problem-specific graph representation of the input image and capture the interactive image representation of the specific problem. Image region dependence, and finally, continue to optimize the fused features through feature enhancement. The test results on the VQA v2 dataset show that the CAM-GCN model achieves better classification results than the current representative models.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125790500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Exposure time is one of the important reasons that affect the accuracy of 3D vision measurement. Different exposure times need to be set to ensure the measurement accuracy for parcel volume measurement in different lighting environments. The existing exposure time setting is mainly based on manual experience and lacks scientific basis. For this reason, this paper proposes an algorithm for automatic camera exposure adjustment based on fuzzy rules. The exposure time is coarsely adjusted first and then finely adjusted to obtain a more accurate exposure time. Experiments show that the proposed camera automatic exposure algorithm using fuzzy rules is fast and reliable.
{"title":"Automatic Exposure Control of Line Structured Light Sensor Based on Fuzzy Logic","authors":"Y. Liu, Wangqian Sun","doi":"10.1145/3573942.3574008","DOIUrl":"https://doi.org/10.1145/3573942.3574008","url":null,"abstract":"Exposure time is one of the important reasons that affect the accuracy of 3D vision measurement. Different exposure times need to be set to ensure the measurement accuracy for parcel volume measurement in different lighting environments. The existing exposure time setting is mainly based on manual experience and lacks scientific basis. For this reason, this paper proposes an algorithm for automatic camera exposure adjustment based on fuzzy rules. The exposure time is coarsely adjusted first and then finely adjusted to obtain a more accurate exposure time. Experiments show that the proposed camera automatic exposure algorithm using fuzzy rules is fast and reliable.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129513370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Quasi-cyclic low-density parity-check (QC-LDPC) codes are linear block codes with performance close to the Shannon limit. The layered minimum sum (LMS) decoding algorithm speeds up the decoding convergence by layering the check matrix and updating the nodes according to the layers. However, the MS algorithm has the problem of over estimation and affects the decoding performance due to its simplified strategy of MS algorithm updating the message of check nodes. Therefore, this paper proposes a layered minimum sum decoding algorithm based on overestimation. By setting the correction threshold and updating the check nodes by the conditions, the decoding performance is improved. When the code length is 2048 and the bit error rate is , the proposed algorithm can improve the decoding convergence speed by about 25% and obtain a coding gain of about 0.1 dB.
{"title":"Improved Layered Minimum Sum Decoding Algorithm Based on Overestimation","authors":"Liu Yu, Lin Bai, Yaohui Hao","doi":"10.1145/3573942.3573996","DOIUrl":"https://doi.org/10.1145/3573942.3573996","url":null,"abstract":"Quasi-cyclic low-density parity-check (QC-LDPC) codes are linear block codes with performance close to the Shannon limit. The layered minimum sum (LMS) decoding algorithm speeds up the decoding convergence by layering the check matrix and updating the nodes according to the layers. However, the MS algorithm has the problem of over estimation and affects the decoding performance due to its simplified strategy of MS algorithm updating the message of check nodes. Therefore, this paper proposes a layered minimum sum decoding algorithm based on overestimation. By setting the correction threshold and updating the check nodes by the conditions, the decoding performance is improved. When the code length is 2048 and the bit error rate is , the proposed algorithm can improve the decoding convergence speed by about 25% and obtain a coding gain of about 0.1 dB.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130957270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Suya Chao, Guang Yang, Min Nie, Yuan-hua Liu, Meiling Zhang
Intrusion detection system (IDS) is a significant mechanism to improve network security. As a promising technique, machine learning (ML) methods has been applied in IDS to obtain high classification accuracy. However, classical ML based IDS methods hit a bottleneck in computing performance in case of huge network traffic and complex high-dimensional data. Due to the parallelism, superposition, entanglement of quantum computing, quantum computing provides a new solution to speed up the classical ML algorithms. This paper proposes a novel IDS scheme based on full-rotation quantum convolutional neural network (FR-QCNN). The key component of the FR-QCNN is the quantum convolution filter, which is composed of coding layer, variational layer and measurement layer. Different from the traditional quantum convolutional neural network, a full-rotation quantum circuit is used in the variational layer of the FR-QCNN, realizing a complete parameter update in the model training. Experiment on dataset from KDD Cup shows that the IDS classification accuracy of FR-QCNN is higher than classical ML models such as convolutional neural network (CNN), decision tree (DT) and support vector machine (SVM), as well as higher than traditional quantum convolutional neural network(QCNN). Meanwhile, FR-QCNN and QCNN have lower space complexity and time complexity than classical ML methods.
{"title":"Full-Rotation Quantum Convolutional Neural Network for Abnormal Intrusion Detection System","authors":"Suya Chao, Guang Yang, Min Nie, Yuan-hua Liu, Meiling Zhang","doi":"10.1145/3573942.3574105","DOIUrl":"https://doi.org/10.1145/3573942.3574105","url":null,"abstract":"Intrusion detection system (IDS) is a significant mechanism to improve network security. As a promising technique, machine learning (ML) methods has been applied in IDS to obtain high classification accuracy. However, classical ML based IDS methods hit a bottleneck in computing performance in case of huge network traffic and complex high-dimensional data. Due to the parallelism, superposition, entanglement of quantum computing, quantum computing provides a new solution to speed up the classical ML algorithms. This paper proposes a novel IDS scheme based on full-rotation quantum convolutional neural network (FR-QCNN). The key component of the FR-QCNN is the quantum convolution filter, which is composed of coding layer, variational layer and measurement layer. Different from the traditional quantum convolutional neural network, a full-rotation quantum circuit is used in the variational layer of the FR-QCNN, realizing a complete parameter update in the model training. Experiment on dataset from KDD Cup shows that the IDS classification accuracy of FR-QCNN is higher than classical ML models such as convolutional neural network (CNN), decision tree (DT) and support vector machine (SVM), as well as higher than traditional quantum convolutional neural network(QCNN). Meanwhile, FR-QCNN and QCNN have lower space complexity and time complexity than classical ML methods.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130996369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The rapid development of deep learning has contributed to the increasing number of open-source deep learning frameworks, and in practice, benchmarking deep learning frameworks to effectively understand the performance characteristics of these frameworks and make choices becomes a challenge. Based on this, this paper uses three types of neural networks (convolutional neural networks, recurrent neural networks, and vision transformer models) to conduct extensive experimental evaluation and analysis of three popular deep learning frameworks, TensorFlow, PyTorch, and PaddlePaddle. Experiments are mainly conducted in CPU and GPU environments using different datasets, and performance parameters such as accuracy, training time, inference time, hardware utilization and other non-performance factors are considered. Finally, the performance characteristics, advantages and disadvantages of different frameworks are analyzed based on the above indexes, which provides theoretical guidance for users to choose.
{"title":"Performance Evaluation and Analysis of Deep Learning Frameworks","authors":"Xiaoyan Xie, Wanqi He, Yun Zhu, Hao Xu","doi":"10.1145/3573942.3573948","DOIUrl":"https://doi.org/10.1145/3573942.3573948","url":null,"abstract":"The rapid development of deep learning has contributed to the increasing number of open-source deep learning frameworks, and in practice, benchmarking deep learning frameworks to effectively understand the performance characteristics of these frameworks and make choices becomes a challenge. Based on this, this paper uses three types of neural networks (convolutional neural networks, recurrent neural networks, and vision transformer models) to conduct extensive experimental evaluation and analysis of three popular deep learning frameworks, TensorFlow, PyTorch, and PaddlePaddle. Experiments are mainly conducted in CPU and GPU environments using different datasets, and performance parameters such as accuracy, training time, inference time, hardware utilization and other non-performance factors are considered. Finally, the performance characteristics, advantages and disadvantages of different frameworks are analyzed based on the above indexes, which provides theoretical guidance for users to choose.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130266430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
According to the heavy computation and high cost of two-dimensional (2D) multiple signal classification (MUSIC) to achieve 2D direction of arrival (DOA) estimation in various complex arrays, this paper proposes a reduced-dimensional (RD) estimation algorithm based on L-shaped uniform array without the need of 2D spectral peak search and secondary optimization. This algorithm makes full use of the structural characteristics of L-shaped array, decomposes the L-shaped uniform array into two uniform linear arrays, and estimates the angle between the source and the X-axis and Y-axis by one-dimensional (1D) search respectively, then obtains the 2D-DOA estimation according to the geometric relationship and uses the maximum likelihood method for angle matching. In this algorithm, the time-consuming 2D search is transformed into 1D search, which greatly reduces the computational complexity. In order to further reduce the complexity and improve the estimation accuracy, the root-finding method can be used instead of one-dimensional search. The simulation results show that the proposed algorithm has higher DOA estimation performance as well as faster operation speed.
{"title":"Reduced-Dimension DOA Estimation Based on MUSIC Algorithm in L-Shaped Array","authors":"Junliang Yang, Hu He, Shumin Wang","doi":"10.1145/3573942.3574113","DOIUrl":"https://doi.org/10.1145/3573942.3574113","url":null,"abstract":"According to the heavy computation and high cost of two-dimensional (2D) multiple signal classification (MUSIC) to achieve 2D direction of arrival (DOA) estimation in various complex arrays, this paper proposes a reduced-dimensional (RD) estimation algorithm based on L-shaped uniform array without the need of 2D spectral peak search and secondary optimization. This algorithm makes full use of the structural characteristics of L-shaped array, decomposes the L-shaped uniform array into two uniform linear arrays, and estimates the angle between the source and the X-axis and Y-axis by one-dimensional (1D) search respectively, then obtains the 2D-DOA estimation according to the geometric relationship and uses the maximum likelihood method for angle matching. In this algorithm, the time-consuming 2D search is transformed into 1D search, which greatly reduces the computational complexity. In order to further reduce the complexity and improve the estimation accuracy, the root-finding method can be used instead of one-dimensional search. The simulation results show that the proposed algorithm has higher DOA estimation performance as well as faster operation speed.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130409590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we consider the two algorithms of generating artwork covers based on texts or audio file features. The resulting image is combined from existing images labelled with keywords after applying filter-based image harmonization. To achieve realistic composition, we train GAN to predict an appropriate filter or apply emotion-based Neural Style Transfer. The quality of generated book covers and music album covers was evaluated by assessors. According to their assessment, the suggested algorithms appeared to produce a better result compared to the existing solutions. The suggested methods also achieve printing quality and require less time for computations, moreover, generated images can be used without copyright infringement.
{"title":"First Describe, Then Depict: Generating Covers for Music and Books via Extracting Keywords: This paper presents two methods to generate high resolution uncopyrighted book covers or music album covers.","authors":"V. Efimova, V. Shalamov, A. Filchenkov","doi":"10.1145/3573942.3574088","DOIUrl":"https://doi.org/10.1145/3573942.3574088","url":null,"abstract":"In this paper, we consider the two algorithms of generating artwork covers based on texts or audio file features. The resulting image is combined from existing images labelled with keywords after applying filter-based image harmonization. To achieve realistic composition, we train GAN to predict an appropriate filter or apply emotion-based Neural Style Transfer. The quality of generated book covers and music album covers was evaluated by assessors. According to their assessment, the suggested algorithms appeared to produce a better result compared to the existing solutions. The suggested methods also achieve printing quality and require less time for computations, moreover, generated images can be used without copyright infringement.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125421973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract: Container has become an important part of cloud-native architecture. More and more enterprises are deploying their core business on containers. The running status of containers is very important for the stability of their business. This paper proposes a container anomaly detection system based on the improved isolation forest algorithm and eBPF. The data is directly extracted from the kernel through eBPF, and the data fluctuating with time is corrected by the method of polynomial regression, and then the iTrees are constructed by the improved isolation forest algorithm, and the abnormal score is calculated to locate the abnormal container. Experiments show that the system improves the precision and recall rate compared with the classical isolation forest algorithm, and the resource overhead is very small.
{"title":"Container Anomaly Detection System Based on Improved-iForest and eBPF","authors":"Yuxuan Bai, Lijun Chen, Fan Zhang","doi":"10.1145/3573942.3574110","DOIUrl":"https://doi.org/10.1145/3573942.3574110","url":null,"abstract":"Abstract: Container has become an important part of cloud-native architecture. More and more enterprises are deploying their core business on containers. The running status of containers is very important for the stability of their business. This paper proposes a container anomaly detection system based on the improved isolation forest algorithm and eBPF. The data is directly extracted from the kernel through eBPF, and the data fluctuating with time is corrected by the method of polynomial regression, and then the iTrees are constructed by the improved isolation forest algorithm, and the abnormal score is calculated to locate the abnormal container. Experiments show that the system improves the precision and recall rate compared with the classical isolation forest algorithm, and the resource overhead is very small.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126855272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To overcome the intensive of manual labeling tasks at the pixel level required for semantic segmentation under traditional supervised learning, an Unsupervised Domain Adaptive for Semantic Segmentation (UDASS) method based on DAFormer improved model is proposed. This model adapted the Max Mean Discrepancy (MMD) method in the regenerated Hilbert space to help the alignment of the feature distribution, the soft paste strategy to retain the partially covered image blocks to help the model to accelerate convergence, the non-convex consistency regularization at the output level to enhance the robustness of the network, and the spatial pyramid pooling framework and the decoder with large window attention collaboration to improve its consistency. The proposed method was evaluated on the public dataset, and obtained the of 2.4% mIoU improvement in GTA5-to-Cityscapes and 1.1% mIoU in SYSTHIA-to-Cityscapes, respectively, which proved that this method was effective for DAFormer improvement.
{"title":"Unsupervised Domain Adaptive Semantic Segmentation Based on Improved DAFormer","authors":"Hao Liu, Jingchun Piao","doi":"10.1145/3573942.3574046","DOIUrl":"https://doi.org/10.1145/3573942.3574046","url":null,"abstract":"To overcome the intensive of manual labeling tasks at the pixel level required for semantic segmentation under traditional supervised learning, an Unsupervised Domain Adaptive for Semantic Segmentation (UDASS) method based on DAFormer improved model is proposed. This model adapted the Max Mean Discrepancy (MMD) method in the regenerated Hilbert space to help the alignment of the feature distribution, the soft paste strategy to retain the partially covered image blocks to help the model to accelerate convergence, the non-convex consistency regularization at the output level to enhance the robustness of the network, and the spatial pyramid pooling framework and the decoder with large window attention collaboration to improve its consistency. The proposed method was evaluated on the public dataset, and obtained the of 2.4% mIoU improvement in GTA5-to-Cityscapes and 1.1% mIoU in SYSTHIA-to-Cityscapes, respectively, which proved that this method was effective for DAFormer improvement.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126881994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In response to the problem that software testing cannot satisfy the verification of multi-threaded programs, a visual modeling language (Extending UML for Model Checking, xUML4MC) oriented concurrent program verification method is proposed. The concurrent program to be verified is visually modeled by xUML4MC; firstly, the visual concurrent system model is analyzed using program analysis techniques, and the concurrent system model is sequenced, and then the sequenced system model is transformed into a Lightweight Concurrent Transition System(LCTS);Then, we construct an impoverished system automaton corresponding to the LCTS, simplify its state space using a partial-order statute algorithm, extract the nature non-automaton to be verified, and verify the simplified impoverished system automaton and the nature non-automaton using a model checking technique. Experiments show that the developed model checking tool can successfully detect errors in concurrent programs and give counterexample paths.
针对软件测试不能满足多线程程序验证的问题，提出了一种面向可视化建模语言(extended UML for Model Checking, xUML4MC)的并发程序验证方法。用xUML4MC对待验证并发程序进行可视化建模;首先利用程序分析技术对可视化并发系统模型进行分析，并对并发系统模型进行排序，然后将排序后的系统模型转化为轻量级并发转换系统(LCTS);然后构造与LCTS对应的穷化系统自动机，利用分序规约算法简化其状态空间，提取待验证的本质非自动机;并利用模型检验技术对简化贫困系统的自动机和自然非自动机进行了验证。实验表明，所开发的模型检测工具能够成功地检测并发程序中的错误，并给出反例路径。
{"title":"A Bounded Model Checking Method for Concurrent Systems in xUML4MC","authors":"Xinfeng Shu, Zewei Yang","doi":"10.1145/3573942.3574016","DOIUrl":"https://doi.org/10.1145/3573942.3574016","url":null,"abstract":"In response to the problem that software testing cannot satisfy the verification of multi-threaded programs, a visual modeling language (Extending UML for Model Checking, xUML4MC) oriented concurrent program verification method is proposed. The concurrent program to be verified is visually modeled by xUML4MC; firstly, the visual concurrent system model is analyzed using program analysis techniques, and the concurrent system model is sequenced, and then the sequenced system model is transformed into a Lightweight Concurrent Transition System(LCTS);Then, we construct an impoverished system automaton corresponding to the LCTS, simplify its state space using a partial-order statute algorithm, extract the nature non-automaton to be verified, and verify the simplified impoverished system automaton and the nature non-automaton using a model checking technique. Experiments show that the developed model checking tool can successfully detect errors in concurrent programs and give counterexample paths.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121258757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：