A novel hashing method based on multiple heterogeneous features is proposed to improve the accuracy of the image retrieval system. First, it leverages the imbalanced distribution of the similar and dissimilar samples ...A novel hashing method based on multiple heterogeneous features is proposed to improve the accuracy of the image retrieval system. First, it leverages the imbalanced distribution of the similar and dissimilar samples in the feature space to boost the performance of each weak classifier in the asymmetric boosting framework. Then, the weak classifier based on a novel linear discriminate analysis （LDA） algorithm which is learned from the subspace of heterogeneous features is integrated into the framework. Finally, the proposed method deals with each bit of the code sequentially, which utilizes the samples misclassified in each round in order to learn compact and balanced code. The heterogeneous information from different modalities can be effectively complementary to each other, which leads to much higher performance. The experimental results based on the two public benchmarks demonstrate that this method is superior to many of the state- of-the-art methods. In conclusion, the performance of the retrieval system can be improved with the help of multiple heterogeneous features and the compact hash codes which can be learned by the imbalanced learning method.展开更多
Visible-infrared Cross-modality Person Re-identification(VI-ReID)is a critical technology in smart public facilities such as cities,campuses and libraries.It aims to match pedestrians in visible light and infrared ima...Visible-infrared Cross-modality Person Re-identification(VI-ReID)is a critical technology in smart public facilities such as cities,campuses and libraries.It aims to match pedestrians in visible light and infrared images for video surveillance,which poses a challenge in exploring cross-modal shared information accurately and efficiently.Therefore,multi-granularity feature learning methods have been applied in VI-ReID to extract potential multi-granularity semantic information related to pedestrian body structure attributes.However,existing research mainly uses traditional dual-stream fusion networks and overlooks the core of cross-modal learning networks,the fusion module.This paper introduces a novel network called the Augmented Deep Multi-Granularity Pose-Aware Feature Fusion Network(ADMPFF-Net),incorporating the Multi-Granularity Pose-Aware Feature Fusion(MPFF)module to generate discriminative representations.MPFF efficiently explores and learns global and local features with multi-level semantic information by inserting disentangling and duplicating blocks into the fusion module of the backbone network.ADMPFF-Net also provides a new perspective for designing multi-granularity learning networks.By incorporating the multi-granularity feature disentanglement(mGFD)and posture information segmentation(pIS)strategies,it extracts more representative features concerning body structure information.The Local Information Enhancement(LIE)module augments high-performance features in VI-ReID,and the multi-granularity joint loss supervises model training for objective feature learning.Experimental results on two public datasets show that ADMPFF-Net efficiently constructs pedestrian feature representations and enhances the accuracy of VI-ReID.展开更多
Multifunctional therapeutic peptides(MFTP)hold immense potential in diverse therapeutic contexts,yet their prediction and identification remain challenging due to the limitations of traditional methodologies,such as e...Multifunctional therapeutic peptides(MFTP)hold immense potential in diverse therapeutic contexts,yet their prediction and identification remain challenging due to the limitations of traditional methodologies,such as extensive training durations,limited sample sizes,and inadequate generalization capabilities.To address these issues,we present AMHF-TP,an advanced method for MFTP recognition that utilizes attention mechanisms and multi-granularity hierarchical features to enhance performance.The AMHF-TP is composed of four key components:a migration learning module that leverages pretrained models to extract atomic compositional features of MFTP sequences;a convolutional neural network and selfattention module that refine feature extraction from amino acid sequences and their secondary structures;a hypergraph module that constructs a hypergraph for complex similarity representation between MFTP sequences;and a hierarchical feature extraction module that integrates multimodal peptide sequence features.Compared with leading methods,the proposed AMHF-TP demonstrates superior precision,accuracy,and coverage,underscoring its effectiveness and robustness in MFTP recognition.The comparative analysis of separate hierarchical models and the combined model,as well as with five contemporary models,reveals AMHFTP’s exceptional performance and stability in recognition tasks.展开更多
In recent years, the accuracy of speech recognition (SR) has been one of the most active areas of research. Despite that SR systems are working reasonably well in quiet conditions, they still suffer severe performance...In recent years, the accuracy of speech recognition (SR) has been one of the most active areas of research. Despite that SR systems are working reasonably well in quiet conditions, they still suffer severe performance degradation in noisy conditions or distorted channels. It is necessary to search for more robust feature extraction methods to gain better performance in adverse conditions. This paper investigates the performance of conventional and new hybrid speech feature extraction algorithms of Mel Frequency Cepstrum Coefficient (MFCC), Linear Prediction Coding Coefficient (LPCC), perceptual linear production (PLP), and RASTA-PLP in noisy conditions through using multivariate Hidden Markov Model (HMM) classifier. The behavior of the proposal system is evaluated using TIDIGIT human voice dataset corpora, recorded from 208 different adult speakers in both training and testing process. The theoretical basis for speech processing and classifier procedures were presented, and the recognition results were obtained based on word recognition rate.展开更多
To solve the problems of the AMR-WB+(Extended Adaptive Multi-Rate-WideBand) semi-open-loop coding mode selection algorithm,features for ACELP(Algebraic Code Excited Linear Prediction) and TCX(Transform Coded eXcitatio...To solve the problems of the AMR-WB+(Extended Adaptive Multi-Rate-WideBand) semi-open-loop coding mode selection algorithm,features for ACELP(Algebraic Code Excited Linear Prediction) and TCX(Transform Coded eXcitation) classification are investigated.11 classifying features in the AMR-WB+ codec are selected and 2 novel classifying features,i.e.,EFM(Energy Flatness Measurement) and stdEFM(standard deviation of EFM),are proposed.Consequently,a novel semi-open-loop mode selection algorithm based on EFM and selected AMR-WB+ features is proposed.The results of classifying test and listening test show that the performance of the novel algorithm is much better than that of the AMR-WB+ semi-open-loop coding mode selection algorithm.展开更多
To solve the problem that using a single feature cannot play the role of multiple features of Android application in malicious code detection, an Android malicious code detection mechanism is proposed based on integra...To solve the problem that using a single feature cannot play the role of multiple features of Android application in malicious code detection, an Android malicious code detection mechanism is proposed based on integrated learning on the basis of dynamic and static detection. Considering three types of Android behavior characteristics, a three-layer hybrid algorithm was proposed. And it combined the malicious code detection based on digital signature to improve the detection efficiency. The digital signature of the known malicious code was extracted to form a malicious sample library. The authority that can reflect Android malicious behavior, API call and the running system call features were also extracted. An expandable hybrid discriminant algorithm was designed for the above three types of features. The algorithm was tested with machine learning method by constructing the optimal classifier suitable for the above features. Finally, the Android malicious code detection system was designed and implemented based on the multi-layer hybrid algorithm. The experimental results show that the system performs Android malicious code detection based on the combination of signature and dynamic and static features. Compared with other related work, the system has better performance in execution efficiency and detection rate.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
With the growth of the Internet,more and more business is being done online,for example,online offices,online education and so on.While this makes people’s lives more convenient,it also increases the risk of the netw...With the growth of the Internet,more and more business is being done online,for example,online offices,online education and so on.While this makes people’s lives more convenient,it also increases the risk of the network being attacked by malicious code.Therefore,it is important to identify malicious codes on computer systems efficiently.However,most of the existing malicious code detection methods have two problems:(1)The ability of the model to extract features is weak,resulting in poor model performance.(2)The large scale of model data leads to difficulties deploying on devices with limited resources.Therefore,this paper proposes a lightweight malicious code identification model Lightweight Malicious Code Classification Method Based on Improved SqueezeNet(LCMISNet).In this paper,the MFire lightweight feature extraction module is constructed by proposing a feature slicing module and a multi-size depthwise separable convolution module.The feature slicing module reduces the number of parameters by grouping features.The multi-size depthwise separable convolution module reduces the number of parameters and enhances the feature extraction capability by replacing the standard convolution with depthwise separable convolution with different convolution kernel sizes.In addition,this paper also proposes a feature splicing module to connect the MFire lightweight feature extraction module based on the feature reuse and constructs the lightweight model LCMISNet.The malicious code recognition accuracy of LCMISNet on the BIG 2015 dataset and the Malimg dataset reaches 98.90% and 99.58%,respectively.It proves that LCMISNet has a powerful malicious code recognition performance.In addition,compared with other network models,LCMISNet has better performance,and a lower number of parameters and computations.展开更多
为了解决多功能视频编码(versatile video coding,VVC)标准下具有相同编码参数的视频双压缩检测方法准确率不高的问题,提出了一种基于编码单元(coding unit,CU)尺寸、划分模式和预测模式的检测方法。对待检测的视频进行多次编解码,分析...为了解决多功能视频编码(versatile video coding,VVC)标准下具有相同编码参数的视频双压缩检测方法准确率不高的问题,提出了一种基于编码单元(coding unit,CU)尺寸、划分模式和预测模式的检测方法。对待检测的视频进行多次编解码,分析并确定VVC流中与压缩编码次数密切相关的基础码流特征;以CU尺寸、划分模式和预测模式构建高级码流特征输入支持向量机完成视频的双压缩检测。实验结果表明,与对比文献的方法相比,所提方法的视频双压缩检测准确率有较大提升,平均准确率达到了95.82%。展开更多
基金The National Natural Science Foundation of China(No.61305058)the Natural Science Foundation of Higher Education Institutions of Jiangsu Province(No.12KJB520003)+1 种基金the Natural Science Foundation of Jiangsu Province(No.BK20130471)the Scientific Research Foundation for Advanced Talents by Jiangsu University(No.13JDG093)
文摘A novel hashing method based on multiple heterogeneous features is proposed to improve the accuracy of the image retrieval system. First, it leverages the imbalanced distribution of the similar and dissimilar samples in the feature space to boost the performance of each weak classifier in the asymmetric boosting framework. Then, the weak classifier based on a novel linear discriminate analysis （LDA） algorithm which is learned from the subspace of heterogeneous features is integrated into the framework. Finally, the proposed method deals with each bit of the code sequentially, which utilizes the samples misclassified in each round in order to learn compact and balanced code. The heterogeneous information from different modalities can be effectively complementary to each other, which leads to much higher performance. The experimental results based on the two public benchmarks demonstrate that this method is superior to many of the state- of-the-art methods. In conclusion, the performance of the retrieval system can be improved with the help of multiple heterogeneous features and the compact hash codes which can be learned by the imbalanced learning method.
基金supported in part by the National Natural Science Foundation of China under Grant 62177029,62307025in part by the Startup Foundation for Introducing Talent of Nanjing University of Posts and Communications under Grant NY221041in part by the General Project of The Natural Science Foundation of Jiangsu Higher Education Institution of China 22KJB520025,23KJD580.
文摘Visible-infrared Cross-modality Person Re-identification(VI-ReID)is a critical technology in smart public facilities such as cities,campuses and libraries.It aims to match pedestrians in visible light and infrared images for video surveillance,which poses a challenge in exploring cross-modal shared information accurately and efficiently.Therefore,multi-granularity feature learning methods have been applied in VI-ReID to extract potential multi-granularity semantic information related to pedestrian body structure attributes.However,existing research mainly uses traditional dual-stream fusion networks and overlooks the core of cross-modal learning networks,the fusion module.This paper introduces a novel network called the Augmented Deep Multi-Granularity Pose-Aware Feature Fusion Network(ADMPFF-Net),incorporating the Multi-Granularity Pose-Aware Feature Fusion(MPFF)module to generate discriminative representations.MPFF efficiently explores and learns global and local features with multi-level semantic information by inserting disentangling and duplicating blocks into the fusion module of the backbone network.ADMPFF-Net also provides a new perspective for designing multi-granularity learning networks.By incorporating the multi-granularity feature disentanglement(mGFD)and posture information segmentation(pIS)strategies,it extracts more representative features concerning body structure information.The Local Information Enhancement(LIE)module augments high-performance features in VI-ReID,and the multi-granularity joint loss supervises model training for objective feature learning.Experimental results on two public datasets show that ADMPFF-Net efficiently constructs pedestrian feature representations and enhances the accuracy of VI-ReID.
基金National Natural Science Foundation of China,Grant/Award Number:62276210Natural Science Basic Research Program of Shaanxi,Grant/Award Number:2022JM-380。
文摘Multifunctional therapeutic peptides(MFTP)hold immense potential in diverse therapeutic contexts,yet their prediction and identification remain challenging due to the limitations of traditional methodologies,such as extensive training durations,limited sample sizes,and inadequate generalization capabilities.To address these issues,we present AMHF-TP,an advanced method for MFTP recognition that utilizes attention mechanisms and multi-granularity hierarchical features to enhance performance.The AMHF-TP is composed of four key components:a migration learning module that leverages pretrained models to extract atomic compositional features of MFTP sequences;a convolutional neural network and selfattention module that refine feature extraction from amino acid sequences and their secondary structures;a hypergraph module that constructs a hypergraph for complex similarity representation between MFTP sequences;and a hierarchical feature extraction module that integrates multimodal peptide sequence features.Compared with leading methods,the proposed AMHF-TP demonstrates superior precision,accuracy,and coverage,underscoring its effectiveness and robustness in MFTP recognition.The comparative analysis of separate hierarchical models and the combined model,as well as with five contemporary models,reveals AMHFTP’s exceptional performance and stability in recognition tasks.
文摘In recent years, the accuracy of speech recognition (SR) has been one of the most active areas of research. Despite that SR systems are working reasonably well in quiet conditions, they still suffer severe performance degradation in noisy conditions or distorted channels. It is necessary to search for more robust feature extraction methods to gain better performance in adverse conditions. This paper investigates the performance of conventional and new hybrid speech feature extraction algorithms of Mel Frequency Cepstrum Coefficient (MFCC), Linear Prediction Coding Coefficient (LPCC), perceptual linear production (PLP), and RASTA-PLP in noisy conditions through using multivariate Hidden Markov Model (HMM) classifier. The behavior of the proposal system is evaluated using TIDIGIT human voice dataset corpora, recorded from 208 different adult speakers in both training and testing process. The theoretical basis for speech processing and classifier procedures were presented, and the recognition results were obtained based on word recognition rate.
文摘To solve the problems of the AMR-WB+(Extended Adaptive Multi-Rate-WideBand) semi-open-loop coding mode selection algorithm,features for ACELP(Algebraic Code Excited Linear Prediction) and TCX(Transform Coded eXcitation) classification are investigated.11 classifying features in the AMR-WB+ codec are selected and 2 novel classifying features,i.e.,EFM(Energy Flatness Measurement) and stdEFM(standard deviation of EFM),are proposed.Consequently,a novel semi-open-loop mode selection algorithm based on EFM and selected AMR-WB+ features is proposed.The results of classifying test and listening test show that the performance of the novel algorithm is much better than that of the AMR-WB+ semi-open-loop coding mode selection algorithm.
文摘To solve the problem that using a single feature cannot play the role of multiple features of Android application in malicious code detection, an Android malicious code detection mechanism is proposed based on integrated learning on the basis of dynamic and static detection. Considering three types of Android behavior characteristics, a three-layer hybrid algorithm was proposed. And it combined the malicious code detection based on digital signature to improve the detection efficiency. The digital signature of the known malicious code was extracted to form a malicious sample library. The authority that can reflect Android malicious behavior, API call and the running system call features were also extracted. An expandable hybrid discriminant algorithm was designed for the above three types of features. The algorithm was tested with machine learning method by constructing the optimal classifier suitable for the above features. Finally, the Android malicious code detection system was designed and implemented based on the multi-layer hybrid algorithm. The experimental results show that the system performs Android malicious code detection based on the combination of signature and dynamic and static features. Compared with other related work, the system has better performance in execution efficiency and detection rate.
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.
文摘With the growth of the Internet,more and more business is being done online,for example,online offices,online education and so on.While this makes people’s lives more convenient,it also increases the risk of the network being attacked by malicious code.Therefore,it is important to identify malicious codes on computer systems efficiently.However,most of the existing malicious code detection methods have two problems:(1)The ability of the model to extract features is weak,resulting in poor model performance.(2)The large scale of model data leads to difficulties deploying on devices with limited resources.Therefore,this paper proposes a lightweight malicious code identification model Lightweight Malicious Code Classification Method Based on Improved SqueezeNet(LCMISNet).In this paper,the MFire lightweight feature extraction module is constructed by proposing a feature slicing module and a multi-size depthwise separable convolution module.The feature slicing module reduces the number of parameters by grouping features.The multi-size depthwise separable convolution module reduces the number of parameters and enhances the feature extraction capability by replacing the standard convolution with depthwise separable convolution with different convolution kernel sizes.In addition,this paper also proposes a feature splicing module to connect the MFire lightweight feature extraction module based on the feature reuse and constructs the lightweight model LCMISNet.The malicious code recognition accuracy of LCMISNet on the BIG 2015 dataset and the Malimg dataset reaches 98.90% and 99.58%,respectively.It proves that LCMISNet has a powerful malicious code recognition performance.In addition,compared with other network models,LCMISNet has better performance,and a lower number of parameters and computations.
文摘为了解决多功能视频编码(versatile video coding,VVC)标准下具有相同编码参数的视频双压缩检测方法准确率不高的问题,提出了一种基于编码单元(coding unit,CU)尺寸、划分模式和预测模式的检测方法。对待检测的视频进行多次编解码,分析并确定VVC流中与压缩编码次数密切相关的基础码流特征;以CU尺寸、划分模式和预测模式构建高级码流特征输入支持向量机完成视频的双压缩检测。实验结果表明,与对比文献的方法相比,所提方法的视频双压缩检测准确率有较大提升,平均准确率达到了95.82%。
