Video inter-frame tampering detection is the most common type of forensics in video forensics. The traditional detection method is to detect tampering by extracting digital image features of video frames, such as SIFT...
详细信息
ISBN:
(纸本)9781450397438
Video inter-frame tampering detection is the most common type of forensics in video forensics. The traditional detection method is to detect tampering by extracting digital image features of video frames, such as SIFT, HOG, and ORB. The accuracy of frame discrimination and localization is limited. This paper introduces deep learning into the problem of tampering detection, and proposes a composite network model structure using the Siamese network Siamese and the bidirectional long short-term memory network autoencoder BiLSTM autoencoder to detect tampered frames. Among them, Siamese calculates the inter-frame distance by calculating the depth features of the frames extracted by VGG-16, and inputs them into BiLSTM autoencoder for frame sequence anomaly detection and localization. The model is experimented on two different datasets with good results, validating the model generalization performance. Compared with the classical method, this model obtains higher precision(93.7%) of tamper points, which verifies the superiority of this deep learning model.
There is a crucial need to have an intelligent and effective intrusion detection system to overcome network intrusion and cyber security attacks. Through this paper, the author compares various data pre-processing met...
详细信息
ISBN:
(纸本)9781450387637
There is a crucial need to have an intelligent and effective intrusion detection system to overcome network intrusion and cyber security attacks. Through this paper, the author compares various data pre-processing methods categorized as Feature selection, Feature encoding, and Feature scaling. The pre-processed data and an autoencoder are used for further processing to get the best features and use them with a deep neural network for classification. Finally, the paper concludes a comparative analysis of pre-processing methods to determine the best for performing network intrusion detection.
The human visual system proves smart in extracting both global and local features. Can we design a similar way for unsupervised feature learning? In this paper, we propose a novel pooling method within an unsupervised...
详细信息
ISBN:
(纸本)9781467395052
The human visual system proves smart in extracting both global and local features. Can we design a similar way for unsupervised feature learning? In this paper, we propose a novel pooling method within an unsupervised feature learning framework, named Rich and Robust Feature Pooling (R~2FP), to better explore rich and robust representation from sparse feature maps of the input data. Both local and global pooling strategies are further considered to instantiate such a method and intensively studied. The former selects the most conductive features in the sub-region and summarizes the joint distribution of the selected features, while the latter is utilized to extract multiple resolutions of features and fuse the features with a feature balancing kernel for rich representation. Extensive experiments on several image recognition tasks demonstrate the superiority of the proposed techniques.
While the term artificial intelligence and the concept of deep learning are not new, recent advances in high-performance computing, the availability of large annotated data sets required for training, and novel framew...
详细信息
While the term artificial intelligence and the concept of deep learning are not new, recent advances in high-performance computing, the availability of large annotated data sets required for training, and novel frameworks for implementing deep neural networks have led to an unprecedented acceleration of the field of molecular (network) biology and pharmacogenomics. The need to align biological data to innovative machine learning has stimulated developments in both data integration (fusion) and knowledge representation, in the form of heterogeneous, multiplex, and biological networks or graphs. In this chapter we briefly introduce several popular neural network architectures used in deep learning, namely, the fully connected deep neural network, recurrent neural network, convolutional neural network, and the autoencoder. Deep learning predictors, classifiers, and generators utilized in modern feature extraction may well assist interpretability and thus imbue AI tools with increased explication, potentially adding insights and advancements in novel chemistry and biology discovery. The capability of learning representations from structures directly without using any predefined structure descriptor is an important feature distinguishing deep learning from other machine learning methods and makes the traditional feature selection and reduction procedures unnecessary. In this chapter we briefly show how these technologies are applied for data integration (fusion) and analysis in drug discovery research covering these areas: (1) application of convolutional neural networks to predict ligand–protein interactions; (2) application of deep learning in compound property and activity prediction; (3) de novo design through deep learning. We also: (1) discuss some aspects of future development of deep learning in drug discovery/chemistry; (2) provide references to published information; (3) provide recently advocated recommendations on using artificial intelligence and deep learni
Turbofan engines are known as the heart of the aircraft,as important equipment of the aircraft,the health state of the engine determines the aircraft’s operational ***,the equipment monitoring and maintenance of the ...
详细信息
Turbofan engines are known as the heart of the aircraft,as important equipment of the aircraft,the health state of the engine determines the aircraft’s operational ***,the equipment monitoring and maintenance of the engine is an important part of ensuring the healthy and stable operation of the aircraft,and the remaining useful life（RUL） prediction of the engine is an important part of *** monitoring data of turbofan engines have a high dimension and a long time span,which brings difficulties to predicting the remaining useful life of the *** paper proposes a residual life prediction model based on autoencoder and temporal convolutional network（TCN）.Among them,autoencoder is used to reduce the dimension of the data and extract features from the engine monitoring *** obtained low-dimensional data is trained in the TCN network to predict the remaining useful *** model mentioned in this article is verified on the NASA public dataset（C-MAPSS）and compared with common machine learning methods and other deep neural *** experimental results show that the model proposed in this paper performs best in the evaluation methods,and this conclusion has important implications for engine health.
Thanks to its hierarchical and generative nature,Deep Belief Network（DBN） is effective to feature representation and extraction in signal *** this paper,DBN is investigated and implemented to monaural speech ***,two...
详细信息
Thanks to its hierarchical and generative nature,Deep Belief Network（DBN） is effective to feature representation and extraction in signal *** this paper,DBN is investigated and implemented to monaural speech ***,two separate DBNs are trained to extract features from mixed noisy signals and target clean speech ***,the two types of extracted features are associated together by training a BP neural network to obtain a mapping from the features of mixed signals to the features of target ***,by performing DBN and the above mapping neural network,target speech can be estimated from the input mixed *** are conducted on different kinds of mixed signals including female/male speech mixtures,human-speech/Gaussian-noise audio mixtures,and human-speech/music audio *** PESQ scores of the extracted speech are 3.32,2.59,and 3.42 respectively,which illustrates that the model performs well on speech separation tasks,especially on the mixed signals where the inference signals have obvious spectral structures.
We propose to use a feature representation obtained by pairwise learning in a low-resource language for query-by-example spoken term detection (QbE-STD). We assume that word pairs identified by humans are available in...
详细信息
ISBN:
(纸本)9781509041183
We propose to use a feature representation obtained by pairwise learning in a low-resource language for query-by-example spoken term detection (QbE-STD). We assume that word pairs identified by humans are available in the low-resource target language. The word pairs are parameterized by a multi-lingual bottleneck feature (BNF) extractor that is trained using transcribed data in high-resource languages. The multi-lingual BNFs of the word pairs are used as an initial feature representation to train an autoencoder (AE). We extract features from an internal hidden layer of the pairwise trained AE to perform acoustic pattern matching for QbE-STD. Our experiments on the TIMIT and Switchboard corpora show that the pairwise learning brings 7.61% and 8.75% relative improvements in mean average precision (MAP) respectively over the initial feature representation.
Nowadays, due to the development of network technology, the Internet becomes the main resource for people to obtain information. The openness of the network makes the network abound of all kinds of information, so it ...
详细信息
ISBN:
(纸本)9781632660015
Nowadays, due to the development of network technology, the Internet becomes the main resource for people to obtain information. The openness of the network makes the network abound of all kinds of information, so it becomes more and more important that using network text classification techniques enable people to get the information they are interested in quickly from the mixed and disorderly network information. Since network text classification technology is the basis of information filtering, search engines, and other fields, it has gradually become a research focus. The traditional text classification technology can't effectively support the Chinese web page text classification because of the large scale of Chinese web page text. An important way to learn the data feature from massive data is to use deep learning neural network structure. Deep learning network has excellent feature learning ability. It can combine objects of low-level features to form advanced abstract representations of the object which will be more suitable for classification. This paper proposes a new deep learning based text classification model to solve the problem of Chinese web text categorization of dimension reduction. Moreover we verify the feasibility of this method through the experiment.
As one of the most rapidly developing artificial intelligence techniques, deep learning has been applied in various machine learning tasks and has received great attention in data science and statistics. Regardless of...
详细信息
As one of the most rapidly developing artificial intelligence techniques, deep learning has been applied in various machine learning tasks and has received great attention in data science and statistics. Regardless of the complex model structure, deep neural networks can be viewed as a nonlinear and nonparametric generalization of existing statistical models. In this review, we introduce several popular deep learning models including convolutional neural networks, generative adversarial networks, recurrent neural networks, and autoencoders, with their applications in image data, sequential data and recommender systems. We review the architecture of each model and highlight their connections and differences compared with conventional statistical models. In particular, we provide a brief survey of the recent works on the unique overparameterization phenomenon, which explains the strengths and advantages of using an extremely large number of parameters in deep learning. In addition, we provide a practical guidance on optimization algorithms, hyperparameter tuning, and computing resources.
暂无评论