To alleviate the problem of under-utilization features of sentence-level relation extraction,which leads to insufficient performance of the pre-trained language model and underutilization of the feature vector,a sente...To alleviate the problem of under-utilization features of sentence-level relation extraction,which leads to insufficient performance of the pre-trained language model and underutilization of the feature vector,a sentence-level relation extraction method based on adding prompt information and feature reuse is proposed.At first,in addition to the pair of nominals and sentence information,a piece of prompt information is added,and the overall feature information consists of sentence information,entity pair information,and prompt information,and then the features are encoded by the pre-trained language model ROBERTA.Moreover,in the pre-trained language model,BIGRU is also introduced in the composition of the neural network to extract information,and the feature information is passed through the neural network to form several sets of feature vectors.After that,these feature vectors are reused in different combinations to form multiple outputs,and the outputs are aggregated using ensemble-learning soft voting to perform relation classification.In addition to this,the sum of cross-entropy,KL divergence,and negative log-likelihood loss is used as the final loss function in this paper.In the comparison experiments,the model based on adding prompt information and feature reuse achieved higher results of the SemEval-2010 task 8 relational dataset.展开更多
Various diseases seriously affect the quality and yield of tomatoes. Fast and accurate identification of disease types is of great significance for the development of smart agriculture. Many Convolution Neural Network...Various diseases seriously affect the quality and yield of tomatoes. Fast and accurate identification of disease types is of great significance for the development of smart agriculture. Many Convolution Neural Network (CNN) models have been applied to the identification of tomato leaf diseases and achieved good results. However, some of these are executed at the cost of large calculation time and huge storage space. This study proposed a lightweight CNN model named MFRCNN, which is established by the multi-scale and feature reuse structure rather than simply stacking convolution layer by layer. To examine the model performances, two types of tomato leaf disease datasets were collected. One is the laboratory-based dataset, including one healthy and nine diseases, and the other is the field-based dataset, including five kinds of diseases. Afterward, the proposed MFRCNN and some popular CNN models (AlexNet, SqueezeNet, VGG16, ResNet18, and GoogLeNet) were tested on the two datasets. The results showed that compared to traditional models, the MFRCNN achieved the optimal performance, with an accuracy of 99.01% and 98.75% in laboratory and field datasets, respectively. The MFRCNN not only had the highest accuracy but also had relatively less computing time and few training parameters. Especially in terms of storage space, the MFRCNN model only needs 2.7 MB of space. Therefore, this work provides a novel solution for plant disease diagnosis, which is of great importance for the development of plant disease diagnosis systems on low-performance terminals.展开更多
Due to the diversity and unpredictability of changes in malicious code,studying the traceability of variant families remains challenging.In this paper,we propose a GAN-EfficientNetV2-based method for tracing families ...Due to the diversity and unpredictability of changes in malicious code,studying the traceability of variant families remains challenging.In this paper,we propose a GAN-EfficientNetV2-based method for tracing families of malicious code variants.This method leverages the similarity in layouts and textures between images of malicious code variants from the same source and their original family of malicious code images.The method includes a lightweight classifier and a simulator.The classifier utilizes the enhanced EfficientNetV2 to categorize malicious code images and can be easily deployed on mobile,embedded,and other devices.The simulator utilizes an enhanced generative adversarial network to simulate different variants of malicious code and generates datasets to validate the model’s performance.This process helps identify model vulnerabilities and security risks,facilitating model enhancement and development.The classifier achieves 98.61%and 97.59%accuracy on the MMCC dataset and Malevis dataset,respectively.The simulator’s generated image of malicious code variants has an FID value of 155.44 and an IS value of 1.72±0.42.The classifier’s accuracy for tracing the family of malicious code variants is as high as 90.29%,surpassing that of mainstream neural network models.This meets the current demand for high generalization and anti-obfuscation abilities in malicious code classification models due to the rapid evolution of malicious code.展开更多
Although deep neural networks(DNNs)have achieved great success in semantic segmentation tasks,it is still challenging for real-time applications.A large number of feature channels,parameters,and floating-point operati...Although deep neural networks(DNNs)have achieved great success in semantic segmentation tasks,it is still challenging for real-time applications.A large number of feature channels,parameters,and floating-point operations make the network sluggish and computationally heavy,which is not desirable for real-time tasks such as robotics and autonomous driving.Most approaches,however,usually sacrifice spatial resolution to achieve inference speed in real time,resulting in poor performance.In this paper,we propose a light-weight stage-pooling semantic segmentation network(SPSSN),which can efficiently reuse the paramount features from early layers at multiple stages,at different spatial resolutions.SPSSN takes input of full resolution 2048×1024 pixels,uses only 1.42×10~6 parameters,yields 69.4%m Io U accuracy without pre-training,and obtains an inference speed of 59 frames/s on the Cityscapes dataset.SPSSN can run directly on mobile devices in real time,due to its light-weight architecture.To demonstrate the effectiveness of the proposed network,we compare our results with those of state-of-the-art networks.展开更多
基金supported by the project of the Ministry of Education(research on the construction and application of quantum encryption cloud service system based on big data analysis of web content(2019JB328L06))the scientific research planning project of the jilin Provincial Education Department(construction and application of medical knowledge graph for chronic diseases of the elderly(JKH20210614KJ)).
文摘To alleviate the problem of under-utilization features of sentence-level relation extraction,which leads to insufficient performance of the pre-trained language model and underutilization of the feature vector,a sentence-level relation extraction method based on adding prompt information and feature reuse is proposed.At first,in addition to the pair of nominals and sentence information,a piece of prompt information is added,and the overall feature information consists of sentence information,entity pair information,and prompt information,and then the features are encoded by the pre-trained language model ROBERTA.Moreover,in the pre-trained language model,BIGRU is also introduced in the composition of the neural network to extract information,and the feature information is passed through the neural network to form several sets of feature vectors.After that,these feature vectors are reused in different combinations to form multiple outputs,and the outputs are aggregated using ensemble-learning soft voting to perform relation classification.In addition to this,the sum of cross-entropy,KL divergence,and negative log-likelihood loss is used as the final loss function in this paper.In the comparison experiments,the model based on adding prompt information and feature reuse achieved higher results of the SemEval-2010 task 8 relational dataset.
基金supported by the China Agriculture Research System (CARS-170404)Qingyuan Science and Technology Plan (Grant No.2022KJJH063)Guangzhou Science and Technology Plan (Grant No.201903010063).
文摘Various diseases seriously affect the quality and yield of tomatoes. Fast and accurate identification of disease types is of great significance for the development of smart agriculture. Many Convolution Neural Network (CNN) models have been applied to the identification of tomato leaf diseases and achieved good results. However, some of these are executed at the cost of large calculation time and huge storage space. This study proposed a lightweight CNN model named MFRCNN, which is established by the multi-scale and feature reuse structure rather than simply stacking convolution layer by layer. To examine the model performances, two types of tomato leaf disease datasets were collected. One is the laboratory-based dataset, including one healthy and nine diseases, and the other is the field-based dataset, including five kinds of diseases. Afterward, the proposed MFRCNN and some popular CNN models (AlexNet, SqueezeNet, VGG16, ResNet18, and GoogLeNet) were tested on the two datasets. The results showed that compared to traditional models, the MFRCNN achieved the optimal performance, with an accuracy of 99.01% and 98.75% in laboratory and field datasets, respectively. The MFRCNN not only had the highest accuracy but also had relatively less computing time and few training parameters. Especially in terms of storage space, the MFRCNN model only needs 2.7 MB of space. Therefore, this work provides a novel solution for plant disease diagnosis, which is of great importance for the development of plant disease diagnosis systems on low-performance terminals.
基金support this work is the Key Research and Development Program of Heilongjiang Province,specifically Grant Number 2023ZX02C10.
文摘Due to the diversity and unpredictability of changes in malicious code,studying the traceability of variant families remains challenging.In this paper,we propose a GAN-EfficientNetV2-based method for tracing families of malicious code variants.This method leverages the similarity in layouts and textures between images of malicious code variants from the same source and their original family of malicious code images.The method includes a lightweight classifier and a simulator.The classifier utilizes the enhanced EfficientNetV2 to categorize malicious code images and can be easily deployed on mobile,embedded,and other devices.The simulator utilizes an enhanced generative adversarial network to simulate different variants of malicious code and generates datasets to validate the model’s performance.This process helps identify model vulnerabilities and security risks,facilitating model enhancement and development.The classifier achieves 98.61%and 97.59%accuracy on the MMCC dataset and Malevis dataset,respectively.The simulator’s generated image of malicious code variants has an FID value of 155.44 and an IS value of 1.72±0.42.The classifier’s accuracy for tracing the family of malicious code variants is as high as 90.29%,surpassing that of mainstream neural network models.This meets the current demand for high generalization and anti-obfuscation abilities in malicious code classification models due to the rapid evolution of malicious code.
基金Project supported by the National Key R&D Program of China(No.2017YFB1300205)。
文摘Although deep neural networks(DNNs)have achieved great success in semantic segmentation tasks,it is still challenging for real-time applications.A large number of feature channels,parameters,and floating-point operations make the network sluggish and computationally heavy,which is not desirable for real-time tasks such as robotics and autonomous driving.Most approaches,however,usually sacrifice spatial resolution to achieve inference speed in real time,resulting in poor performance.In this paper,we propose a light-weight stage-pooling semantic segmentation network(SPSSN),which can efficiently reuse the paramount features from early layers at multiple stages,at different spatial resolutions.SPSSN takes input of full resolution 2048×1024 pixels,uses only 1.42×10~6 parameters,yields 69.4%m Io U accuracy without pre-training,and obtains an inference speed of 59 frames/s on the Cityscapes dataset.SPSSN can run directly on mobile devices in real time,due to its light-weight architecture.To demonstrate the effectiveness of the proposed network,we compare our results with those of state-of-the-art networks.
