Network traffic features change with time and network environment, creating a concept drift problem that leads to a decrease in the accuracy of machine learning-based network traffic classification methods. This is because the traditional network traffic classifiers are static models that cannot adapt to the changes in data distribution. Therefore, we proposed a concept drift detection approach based on Jensen–Shannon divergence, named CDJD. The method uses a double-layer window mechanism to detect changes in data distribution based on the Jensen-Shannon divergence, and thus detects concept drift. After detecting concept drift, the Jensen-Shannon divergence is used to check whether the current concept is a recurrence of the past concept and thus decide whether to reuse the old classifier. The method is experimentally compared with common concept drift detection methods, and the experimental results show that the method can effectively detect concept drift and showing better classification performance.
{"title":"A Concept Drift Detection Approach Based on Jensen-Shannon Divergence for Network Traffic Classification","authors":"Wujun Yang, Rui Su, Yuanzheng Cheng, Juan Guo","doi":"10.1145/3573942.3573979","DOIUrl":"https://doi.org/10.1145/3573942.3573979","url":null,"abstract":"Network traffic features change with time and network environment, creating a concept drift problem that leads to a decrease in the accuracy of machine learning-based network traffic classification methods. This is because the traditional network traffic classifiers are static models that cannot adapt to the changes in data distribution. Therefore, we proposed a concept drift detection approach based on Jensen–Shannon divergence, named CDJD. The method uses a double-layer window mechanism to detect changes in data distribution based on the Jensen-Shannon divergence, and thus detects concept drift. After detecting concept drift, the Jensen-Shannon divergence is used to check whether the current concept is a recurrence of the past concept and thus decide whether to reuse the old classifier. The method is experimentally compared with common concept drift detection methods, and the experimental results show that the method can effectively detect concept drift and showing better classification performance.","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":"129914075","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 the environment of the 5G era, with the advancement of communication technology and the continuous improvement of people's living and work needs, users' demand for network access bandwidth is increasing. Orthogonal Frequency Division Multiplexing-Radio Frequency over Optical (OFDM-RoF) system is an Internet solution with high spectrum utilization, large bandwidth and fast transmission data rate. The chromatic dispersion (CD) and polarization mode dispersion (PMD) existing in the system will affect the transmission performance of the OFDM-RoF system. In this paper, the artificial neural network algorithm is applied to the field of channel estimation. Reduce the effect of dispersion on the system by estimating the activation function of the channel. Simulation results show that compared with the frequency domain least squares (FDLS) method, this algorithm can improve the system performance and improve the bit error rate optimization ability by an order of magnitude.
{"title":"Channel Estimation Algorithm of OFDM-RoF System in 5G Mobile Front-end Network Based on Artificial Neural Network","authors":"Yun Zhang, Siyuan Liang, Chunting Wang, Feng Zhao","doi":"10.1145/3573942.3574000","DOIUrl":"https://doi.org/10.1145/3573942.3574000","url":null,"abstract":"In the environment of the 5G era, with the advancement of communication technology and the continuous improvement of people's living and work needs, users' demand for network access bandwidth is increasing. Orthogonal Frequency Division Multiplexing-Radio Frequency over Optical (OFDM-RoF) system is an Internet solution with high spectrum utilization, large bandwidth and fast transmission data rate. The chromatic dispersion (CD) and polarization mode dispersion (PMD) existing in the system will affect the transmission performance of the OFDM-RoF system. In this paper, the artificial neural network algorithm is applied to the field of channel estimation. Reduce the effect of dispersion on the system by estimating the activation function of the channel. Simulation results show that compared with the frequency domain least squares (FDLS) method, this algorithm can improve the system performance and improve the bit error rate optimization ability by an order of magnitude.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"29 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":"120985769","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}
Multimodal sentiment analysis refers to the use of computers to analyze and identify the emotions that people want to express through the extracted multimodal sentiment features, and it plays a significant role in human-computer interaction and financial market prediction. Most existing approaches to multimodal sentiment analysis use contextual information for modeling, and while this modeling approach can effectively capture the contextual connections within modalities, the correlations between modalities are often overlooked, and the correlations between modalities are also critical to the final recognition results in multimodal sentiment analysis. Therefore, this paper proposes a multimodal sentiment analysis approach based on the universal transformer, a framework that uses the universal transformer to model the connections between multiple modalities while employing effective feature extraction methods to capture the contextual connections of individual modalities. We evaluated our proposed method on two benchmark datasets for multimodal sentiment analysis, CMU-MOSI and CMU-MOSEI, and the results outperformed other methods of the same type.
{"title":"A Method with Universal Transformer for Multimodal Sentiment Analysis","authors":"Hao Ai, Ying Liu, Jie Fang, Sheikh Faisal Rashid","doi":"10.1145/3573942.3573968","DOIUrl":"https://doi.org/10.1145/3573942.3573968","url":null,"abstract":"Multimodal sentiment analysis refers to the use of computers to analyze and identify the emotions that people want to express through the extracted multimodal sentiment features, and it plays a significant role in human-computer interaction and financial market prediction. Most existing approaches to multimodal sentiment analysis use contextual information for modeling, and while this modeling approach can effectively capture the contextual connections within modalities, the correlations between modalities are often overlooked, and the correlations between modalities are also critical to the final recognition results in multimodal sentiment analysis. Therefore, this paper proposes a multimodal sentiment analysis approach based on the universal transformer, a framework that uses the universal transformer to model the connections between multiple modalities while employing effective feature extraction methods to capture the contextual connections of individual modalities. We evaluated our proposed method on two benchmark datasets for multimodal sentiment analysis, CMU-MOSI and CMU-MOSEI, and the results outperformed other methods of the same type.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"4 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":"121151314","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}
Most of the image description generation methods in the attention-based encoder-decoder framework extract local features from images. Despite the relatively high semantic level of local features, it still has two problems to be solved, one is object loss, where some important objects may be lost when generating image descriptions, and the other is prediction error, as an object may be identified in the wrong class. In this paper, a G-AoANet model is proposed to solve the above problems. The model uses an attention mechanism to combine global features with local features. In this way, our model can selectively focus on both object and contextual information, improving the quality of the generated descriptions. Experimental results show that the model improves the initially reported best CIDEr-D and SPICE scores on the MS COCO dataset by 9.3% and 5.1% respectively.
{"title":"Research on Image Description Generation Method Based on G-AoANet","authors":"Pi Qiao, Ruixue Shen, Yuan Li","doi":"10.1145/3573942.3574072","DOIUrl":"https://doi.org/10.1145/3573942.3574072","url":null,"abstract":"Most of the image description generation methods in the attention-based encoder-decoder framework extract local features from images. Despite the relatively high semantic level of local features, it still has two problems to be solved, one is object loss, where some important objects may be lost when generating image descriptions, and the other is prediction error, as an object may be identified in the wrong class. In this paper, a G-AoANet model is proposed to solve the above problems. The model uses an attention mechanism to combine global features with local features. In this way, our model can selectively focus on both object and contextual information, improving the quality of the generated descriptions. Experimental results show that the model improves the initially reported best CIDEr-D and SPICE scores on the MS COCO dataset by 9.3% and 5.1% respectively.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"29 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":"127607955","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}
This paper proposes a chaotic encryption algorithm based on Latin squares and adaptive Z-diffusion. First, in order to improve the defects of the traditional Sine system, two-dimensional enhance Sine chaotic system (2D-ESCS) is designed. In terms of bifurcation diagram, Lyapunov exponent and NIST, we can observe that 2D-ESCS have continuous and large chaotic ranges. Second, the generation of Latin squares through pseudorandom sequences generated by 2D-ESCS and then perform scrambling operation with the image. Third, adaptive Z-diffusion depends on the location of the pixels. the cipher image is calculated by different combinations of pseudorandom numbers, plain images pixel values and intermediate cipher image pixel values. Finally, simulation experiments and security analysis show that the proposed algorithm has a high security level to resist various cryptanalytic attacks and a high execution efficiency.
{"title":"Image Encryption Algorithm Based on Latin Squares and Adaptive Z-Diffusion","authors":"Yangguang Lou, Shu-cui Xie, Jianzhong Zhang","doi":"10.1145/3573942.3574062","DOIUrl":"https://doi.org/10.1145/3573942.3574062","url":null,"abstract":"This paper proposes a chaotic encryption algorithm based on Latin squares and adaptive Z-diffusion. First, in order to improve the defects of the traditional Sine system, two-dimensional enhance Sine chaotic system (2D-ESCS) is designed. In terms of bifurcation diagram, Lyapunov exponent and NIST, we can observe that 2D-ESCS have continuous and large chaotic ranges. Second, the generation of Latin squares through pseudorandom sequences generated by 2D-ESCS and then perform scrambling operation with the image. Third, adaptive Z-diffusion depends on the location of the pixels. the cipher image is calculated by different combinations of pseudorandom numbers, plain images pixel values and intermediate cipher image pixel values. Finally, simulation experiments and security analysis show that the proposed algorithm has a high security level to resist various cryptanalytic attacks and a high execution efficiency.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"241 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":"133683634","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 view of the importance of Age of Information (AoI) in delay sensitive applications of Wireless Sensor Networks (WSNs), an improved gray wolf algorithm (POPAGA) based on the combination of particle swarm optimization possibility fuzzy C-mean clustering is proposed. POPAGA is optimized from the clustering stage and the path planning stage. In the clustering stage, the particle swarm optimization algorithm is first used to optimize the possibility fuzzy hybrid clustering algorithm, which not only overcomes the problem that the fuzzy C-means is sensitive to the initial clustering center, but also avoids the poor initialization effect of the possibility fuzzy c-means clustering, so as to determine the Hovering Collection Data points (HCD) and their associated Sensor Nodes (SNs). In the path planning stage, based on the hover collection data points obtained in the previous stage, the improved gray wolf optimization algorithm (GWO) is used to find the optimal path to minimize the maximum AoI and the average AoI. The simulation results show that POPAGA can obtain the global minimum AoI optimal value, whether compared with the traditional genetic algorithm (GA) and simulated annealing algorithm (SA) for solving TSP problem, or compared with the genetic algorithm (GA) and greedy algorithm based on AoI.
{"title":"An Age-Based Data Collection and Path Planning Algorithm in UAV-Assisted Wireless Sensor Networks","authors":"Chi Sun, De Wei","doi":"10.1145/3573942.3573981","DOIUrl":"https://doi.org/10.1145/3573942.3573981","url":null,"abstract":"In view of the importance of Age of Information (AoI) in delay sensitive applications of Wireless Sensor Networks (WSNs), an improved gray wolf algorithm (POPAGA) based on the combination of particle swarm optimization possibility fuzzy C-mean clustering is proposed. POPAGA is optimized from the clustering stage and the path planning stage. In the clustering stage, the particle swarm optimization algorithm is first used to optimize the possibility fuzzy hybrid clustering algorithm, which not only overcomes the problem that the fuzzy C-means is sensitive to the initial clustering center, but also avoids the poor initialization effect of the possibility fuzzy c-means clustering, so as to determine the Hovering Collection Data points (HCD) and their associated Sensor Nodes (SNs). In the path planning stage, based on the hover collection data points obtained in the previous stage, the improved gray wolf optimization algorithm (GWO) is used to find the optimal path to minimize the maximum AoI and the average AoI. The simulation results show that POPAGA can obtain the global minimum AoI optimal value, whether compared with the traditional genetic algorithm (GA) and simulated annealing algorithm (SA) for solving TSP problem, or compared with the genetic algorithm (GA) and greedy algorithm based on AoI.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"7 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":"128407001","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 order to solve the problem that the micro moving gesture features are not obvious and difficult to be identified, a micro moving gesture recognition method based on multi-scale fusion deep network for millimeter wave radar is proposed in this paper. The method is mainly composed of 2D convolution module, multi-scale fusion module and attention mechanism module. The multi-scale fusion module is composed of three residual blocks of different scales, which can obtain receptive fields of different sizes and obtain multi-scale features. Meanwhile, residual blocks of different scales are fused to increase the diversity of the network and better extract the deep features of the data. The Squeeze-and-congestion (SE) attention mechanism module is added to suppress the channel characteristics with little information. This improves the network identification accuracy and reduces the number of parameters and computation. The experimental results show that this method is simple to implement, doesn't need to do complex data preprocessing. The convergence speed of the network is fast, which can realize the effective recognition of the micro moving gesture.
{"title":"Radar micro moving gesture recognition method based on multi-scale fusion deep network","authors":"Zhiqiang Bao, Tiantian Liu","doi":"10.1145/3573942.3574076","DOIUrl":"https://doi.org/10.1145/3573942.3574076","url":null,"abstract":"In order to solve the problem that the micro moving gesture features are not obvious and difficult to be identified, a micro moving gesture recognition method based on multi-scale fusion deep network for millimeter wave radar is proposed in this paper. The method is mainly composed of 2D convolution module, multi-scale fusion module and attention mechanism module. The multi-scale fusion module is composed of three residual blocks of different scales, which can obtain receptive fields of different sizes and obtain multi-scale features. Meanwhile, residual blocks of different scales are fused to increase the diversity of the network and better extract the deep features of the data. The Squeeze-and-congestion (SE) attention mechanism module is added to suppress the channel characteristics with little information. This improves the network identification accuracy and reduces the number of parameters and computation. The experimental results show that this method is simple to implement, doesn't need to do complex data preprocessing. The convergence speed of the network is fast, which can realize the effective recognition of the micro moving gesture.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"105 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":"134167521","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}
Firstly, an improved ant colony algorithm (QCANT) is proposed to optimize quantum connectivity, and the entanglement example distribution node deployment in quantum wireless multi-hop networks is studied and analyzed. On this basis, this paper combined genetic algorithm with improved ant colony algorithm (GA-QCANT), which can effectively alleviate the problem of low efficiency of ant colony algorithm due to the lack of initial pheromone. Simulation results show that both QCANT and GA-QCANT improves quantum connectivity significantly, and GA-QCANT improves quantum connectivity by an average of 32.1% compared to QCANT.
{"title":"Research on Multi-hop Transmission in Quantum Wireless Communication Networks Based on Improved Ant Colony Algorithm","authors":"Xinyuan Mao, Min Nie, Guang Yang","doi":"10.1145/3573942.3573985","DOIUrl":"https://doi.org/10.1145/3573942.3573985","url":null,"abstract":"Firstly, an improved ant colony algorithm (QCANT) is proposed to optimize quantum connectivity, and the entanglement example distribution node deployment in quantum wireless multi-hop networks is studied and analyzed. On this basis, this paper combined genetic algorithm with improved ant colony algorithm (GA-QCANT), which can effectively alleviate the problem of low efficiency of ant colony algorithm due to the lack of initial pheromone. Simulation results show that both QCANT and GA-QCANT improves quantum connectivity significantly, and GA-QCANT improves quantum connectivity by an average of 32.1% compared to QCANT.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"22 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":"133104268","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 application of swarm optimization algorithm in WSNs has become a new research hotspot of scholars at home and abroad. Aiming at the problem that the spotted hyena optimization algorithm is easy to fall into local optimum, which leads to low optimization accuracy, an improved spotted hyena optimization algorithm is proposed. On the basis of the original algorithm, Sine chaotic map and elite reverse learning strategy are embedded to reduce the probability of falling into local optimum and improve the global search ability of spotted hyena optimization algorithm. In addition, the adaptive inertia weight is introduced to balance the global search and local development capabilities of the spotted hyena optimization algorithm. The experimental results show that compared with the original spotted hyena optimization algorithm, sine and cosine algorithm, multiverse optimization algorithm, differential evolution algorithm and particle swarm optimization algorithm, the improved algorithm has significant performance advantages in optimization ability and stability.
{"title":"Optimization Algorithm of Spotted Hyena Based on Chaotic Reverse Learning Strategy","authors":"Xu He, Hengzhi Lu, Zixing Ling","doi":"10.1145/3573942.3574018","DOIUrl":"https://doi.org/10.1145/3573942.3574018","url":null,"abstract":"The application of swarm optimization algorithm in WSNs has become a new research hotspot of scholars at home and abroad. Aiming at the problem that the spotted hyena optimization algorithm is easy to fall into local optimum, which leads to low optimization accuracy, an improved spotted hyena optimization algorithm is proposed. On the basis of the original algorithm, Sine chaotic map and elite reverse learning strategy are embedded to reduce the probability of falling into local optimum and improve the global search ability of spotted hyena optimization algorithm. In addition, the adaptive inertia weight is introduced to balance the global search and local development capabilities of the spotted hyena optimization algorithm. The experimental results show that compared with the original spotted hyena optimization algorithm, sine and cosine algorithm, multiverse optimization algorithm, differential evolution algorithm and particle swarm optimization algorithm, the improved algorithm has significant performance advantages in optimization ability and stability.","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":"133183649","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}
Most of the traditional detection methods for crop diseases and insect pests are manually operated in the field according to the experience and technology of the staff, which have the disadvantages of long time and low efficiency. With the development of deep learning technology, the application of complex deep neural network algorithm models in the field of crop diseases and insect pests can effectively solve the above problems, however, the current research on the identification method of crop diseases and insect pests only focuses on the identification and analysis of single crop diseases and insect pests, and does not analyze and improve the analysis and improvement of various crops. Therefore, this paper proposes a recognition model of crop pests and diseases based on convolutional neural network. First, on the bilinear network model, the ResNet50 network is used as the feature extractor, that is, the backbone network of the network, instead of the original VGG-D and VGG-M backbone networks. Secondly, a connect module is added to design the bilinear network model and the extractor to do mutual outer product with the previous features of different levels, so that it is connected with the outer product of the feature vector. Finally, the loss function is used to conduct experiments on the AI Challenger 2018 crop pest and disease dataset. The experimental results show that the average recognition rate of the improved B-CNN-ResNet50-connect network model reaches 89.62%.
{"title":"Research on Recognition Model of Crop Diseases and Insect Pests Based on Convolutional Neural Network","authors":"Pi Qiao, Zilu Wang","doi":"10.1145/3573942.3574087","DOIUrl":"https://doi.org/10.1145/3573942.3574087","url":null,"abstract":"Most of the traditional detection methods for crop diseases and insect pests are manually operated in the field according to the experience and technology of the staff, which have the disadvantages of long time and low efficiency. With the development of deep learning technology, the application of complex deep neural network algorithm models in the field of crop diseases and insect pests can effectively solve the above problems, however, the current research on the identification method of crop diseases and insect pests only focuses on the identification and analysis of single crop diseases and insect pests, and does not analyze and improve the analysis and improvement of various crops. Therefore, this paper proposes a recognition model of crop pests and diseases based on convolutional neural network. First, on the bilinear network model, the ResNet50 network is used as the feature extractor, that is, the backbone network of the network, instead of the original VGG-D and VGG-M backbone networks. Secondly, a connect module is added to design the bilinear network model and the extractor to do mutual outer product with the previous features of different levels, so that it is connected with the outer product of the feature vector. Finally, the loss function is used to conduct experiments on the AI Challenger 2018 crop pest and disease dataset. The experimental results show that the average recognition rate of the improved B-CNN-ResNet50-connect network model reaches 89.62%.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"44 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":"133422484","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：