Credit card fraud detection using a deep learning multistage model

The Journal of Supercomputing - The banking sector is on the eve of a serious transformation and the thrust behind it is artificial intelligence (AI). Novel AI applications have been already...     

基于深度学习的安卓恶意应用检测

针对传统安卓恶意程序检测技术检测准确率低,对采用了重打包和代码混淆等技术的安卓恶意程序无法成功识别等问题,设计并实现了DeepDroid算法。首先,提取安卓应用程序的静态特征和动态特征,结合静态特征和动态特征生成应用程序的特征向量;然后,使用深度学习算法中的深度置信网络（DBN）对收集到的训练集进行训练,生成深度学习网络;最后,利用生成的深度学习网络对待测安卓应用程序进行检测。实验结果表明,在使用相同测试集的情况下,DeepDroid算法的正确率比支持向量机（SVM）算法高出3.96个百分点,比朴素贝叶斯（Naive Bayes）算法高出12.16个百分点,比K最邻近（KNN）算法高出13.62个百分点。DeepDroid算法结合了安卓应用程序的静态特征和动态特征,采用了动态检测和静态检测相结合的检测方法,弥补了静态检测代码覆盖率不足和动态检测误报率高的缺点,在特征识别的部分采用DBN算法使得网络训练速度得到保证的同时还有很高的检测正确率。     

Image steganography using deep learning based edge detection

This paper introduces a deep learning-based Steganography method for hiding secret information within the cover image. For this, we use a convolutional neural network (CNN) with Deep Supervision based edge detector, which can retain more edge pixels over conventional edge detection algorithms. Initially, the cover image is pre-processed by masking the last 5-bits of each pixel. The said edge detector model is then applied to obtain a gray-scale edge map. To get the prominent edge information, the gray-scale edge map is converted into a binary version using both global and adaptive binarization schemes. The purpose of using different binarization techniques is to prove the less sensitive nature of the edge detection method to the thresholding approaches. Our rule for embedding secret bits within the cover image is as follows: more bits into the edge pixels while fewer bits into the non-edge pixels. Experimental outcomes on various standard images confirm that compared to state-of-the-art methods, the proposed method achieves a higher payload.

     

Screening of breast cancer from thermogram images by edge detection aided deep transfer learning model

Multimedia Tools and Applications - Breast cancer, the most common invasive cancer, causes deaths of thousands of women in the world every year. Early detection of the same is a remedy to lessen...     

AHW-BGOA-DNN: a novel deep learning model for epileptic seizure detection

Neural Computing and Applications - “Brain–Computer Interface” (BCI)—a real-life support system provides a way for epileptic patients to improve their quality of life. In...     

Cyberattack detection model using deep learning in a network log system with data visualization

The Journal of Supercomputing - Network log data is significant for network administrators, since it contains information on every event that occurs in a network, including system errors, alerts,...     

BLoCNet: a hybrid,dataset-independent intrusion detection system using deep learning

International Journal of Information Security - Intrusion detection systems (IDS) identify cyber attacks given a sample of network traffic collected from real-world computer networks. As a powerful...     

Early-stage atherosclerosis detection using deep learning over carotid ultrasound images

This paper proposes a computer-aided diagnosis tool for the early detection of atherosclerosis. This pathology is responsible for major cardiovascular diseases, which are the main cause of death worldwide. Among preventive measures, the intima-media thickness (IMT) of the common carotid artery stands out as early indicator of atherosclerosis and cardiovascular risk. In particular, IMT is evaluated by means of ultrasound scans. Usually, during the radiological examination, the specialist detects the optimal measurement area, identifies the layers of the arterial wall and manually marks pairs of points on the image to estimate the thickness of the artery. Therefore, this manual procedure entails subjectivity and variability in the IMT evaluation. Instead, this article suggests a fully automatic segmentation technique for ultrasound images of the common carotid artery. The proposed methodology is based on machine learning and artificial neural networks for the recognition of IMT intensity patterns in the images. For this purpose, a deep learning strategy has been developed to obtain abstract and efficient data representations by means of auto-encoders with multiple hidden layers. In particular, the considered deep architecture has been designed under the concept of extreme learning machine (ELM). The correct identification of the arterial layers is achieved in a totally user-independent and repeatable manner, which not only improves the IMT measurement in daily clinical practice but also facilitates the clinical research. A database consisting of 67 ultrasound images has been used in the validation of the suggested system, in which the resulting automatic contours for each image have been compared with the average of four manual segmentations performed by two different observers (ground-truth). Specifically, the IMT measured by the proposed algorithm is 0.625 ± 0.167 mm (mean ± standard deviation), whereas the corresponding ground-truth value is 0.619 ± 0.176 mm. Thus, our method shows a difference between automatic and manual measures of only 5.79 ± 34.42 μm. Furthermore, different quantitative evaluations reported in this paper indicate that this procedure outperforms other methods presented in the literature.     

TINYCD: a (not so) deep learning model for change detection

Neural Computing and Applications - In this paper, we present a lightweight and effective change detection model, called TinyCD. This model has been designed to be faster and smaller than current...     

DFD-Net: lung cancer detection from denoised CT scan image using deep learning

The availability of pulmonary nodules in CT scan image of lung does not completely specify cancer. The noise in an image and morphology of nodules, like shape and size has an implicit and complex association with cancer, and thus, a careful analysis should be mandatory on every suspected nodules and the combination of information of every nodule. In this paper, we introduce a “denoising first” two-path convolutional neural network (DFD-Net) to address this complexity. The introduced model is composed of denoising and detection part in an end to end manner. First, a residual learning denoising model (DR-Net) is employed to remove noise during the preprocessing stage. Then, a two-path convolutional neural network which takes the denoised image by DR-Net as an input to detect lung cancer is employed. The two paths focus on the joint integration of local and global features. To this end, each path employs different receptive field size which aids to model local and global dependencies. To further polish our model performance, in different way from the conventional feature concatenation approaches which directly concatenate two sets of features from different CNN layers, we introduce discriminant correlation analysis to concatenate more representative features. Finally, we also propose a retraining technique that allows us to overcome difficulties associated to the image labels imbalance. We found that this type of model easily first reduce noise in an image, balances the receptive field size effect, affords more representative features, and easily adaptable to the inconsistency among nodule shape and size. Our intensive experimental results achieved competitive results.     

TVD-MRDL: traffic violation detection system using MapReduce-based deep learning for large-scale data

Maintaining a fluid and safe traffic is a major challenge for human societies because of its social and economic impacts. Various technologies have considerably paved the way for the elimination of traffic problems and have been able to effectively detect drivers’ violations. However, the high volume of the real-time data collected from surveillance cameras and traffic sensors along with the data obtained from individuals have made the use of traditional methods ineffective. Therefore, using Hadoop for processing large-scale structured and unstructured data as well as multimedia data can be of great help. In this paper, the TVD-MRDL system based on the MapReduce techniques and deep learning was employed to discover effective solutions. The Distributed Deep Learning System was implemented to analyze traffic big data and to detect driver violations in Hadoop. The results indicated that more accurate monitoring automatically creates the power of deterrence and behavior change in drivers and it prevents drivers from committing unusual behaviors in society. So, if the offending driver is identified quickly after committing the violation and is punished with the appropriate punishment and dealt with decisively and without negligence, we will surely see a decrease in violations at the community level. Also, the efficiency of the TVD-MRDL performance increased by more than 75% as the number of data nodes increased.

     

Segmentation and classification of breast cancer using novel deep learning architecture

Neural Computing and Applications - Breast cancer is one of the most frequent cancers in women, and it has a higher mortality rate than other cancers. As a result, early detection is critical. In...     

Vehicle re-identification using multi-task deep learning network and spatio-temporal model

Multimedia Tools and Applications - Vehicle re-identification (re-ID) plays an important role in the automatic analysis of the increasing urban surveillance videos and has become a hot topic in...     

Pedestrian detection with unsupervised multispectral feature learning using deep neural networks

Multispectral pedestrian detection is an important functionality in various computer vision applications such as robot sensing, security surveillance, and autonomous driving. In this paper, our motivation is to automatically adapt a generic pedestrian detector trained in a visible source domain to a new multispectral target domain without any manual annotation efforts. For this purpose, we present an auto-annotation framework to iteratively label pedestrian instances in visible and thermal channels by leveraging the complementary information of multispectral data. A distinct target is temporally tracked through image sequences to generate more confident labels. The predicted pedestrians in two individual channels are merged through a label fusion scheme to generate multispectral pedestrian annotations. The obtained annotations are then fed to a two-stream region proposal network (TS-RPN) to learn the multispectral features on both visible and thermal images for robust pedestrian detection. Experimental results on KAIST multispectral dataset show that our proposed unsupervised approach using auto-annotated training data can achieve performance comparable to state-of-the-art deep neural networks (DNNs) based pedestrian detectors trained using manual labels.     

Satellite data cloud detection using deep learning supported by hyperspectral data

ABSTRACT

Deep learning methods can play an important role in satellite data cloud detection. The number and quality of training samples directly affect the accuracy of cloud detection based on deep learning. Therefore, selecting a large number of representative and high-quality training samples is a key step in cloud detection based on deep learning. For different satellite data sources, choosing sufficient and high-quality training samples has become an important factor limiting the application of deep learning in cloud detection. This paper presents a fast method for obtaining high-quality learning samples, which can be used for cloud detection of different satellite data with deep learning methods. AVIRIS (Airborne Visible Infrared Imaging Spectrometer) data, which have 224 continuous bands in the spectral range from 400–2500 nm, are used to provide cloud detection samples for different types of satellite data. Through visual interpretation, a sufficient number of cloud and clear sky pixels are selected from the AVIRIS data to construct a hyperspectral data sample library, which is used to simulate different satellite data (such as data from the Moderate Resolution Imaging Spectroradiometer (MODIS) and Landsat Operational Land Imager (OLI) satellites) as training samples. This approach avoids selecting training samples for different satellite sensors. Based on the Keras deep learning framework platform, a backpropagation (BP) neural network is employed for cloud detection from Landsat 8 OLI, National Polar-orbiting Partnership (NPP) Visible Infrared Imaging Radiometer Suite (VIIRS) and Terra MODIS data. The results are compared with cloud coverage results interpreted via artificial vision. The results demonstrate that the algorithm achieves good cloud detection results for the above data, and the overall accuracy is greater than 90%.     

基于深度学习的Webshell检测

以AWD攻防中Webshell检测为背景,在超空间利用模糊C均值聚类分析发现了攻击向量全局稀疏、局部紧密的特点,提出了2种深度学习模型。由于GitHub收集的攻击行为多为随机获取,没有很好的针对性,所以对训练数据的长度进行了限制,并保留了有限的相关样本数量。由于一次攻击与相邻的2～4次操作紧密相关,而且攻击向量垂直方向关联特征明显,水平方向相对稳定,考虑到特征向量在传递过程中规模会减小,增加了卷积层的补零选项。针对深度学习训练曲线中的锯齿振荡现象,证明了Adam优化算法的快速计算公式,并修正了学习参数,不断消除了训练的Loss曲线中的锯齿,使得训练曲线按照指数规律平滑下降,迅速得到需要的训练结果。将目前已有的类似工作与提出的2种深度学习模型进行对比。实验结果表明,提出的的深度学习模型能够很好地检测出AWD中的Webshell攻击。     

深度学习目标检测方法综述

目标检测的任务是从图像中精确且高效地识别、定位出大量预定义类别的物体实例。随着深度学习的广泛应用,目标检测的精确度和效率都得到了较大提升,但基于深度学习的目标检测仍面临改进与优化主流目标检测算法的性能、提高小目标物体检测精度、实现多类别物体检测、轻量化检测模型等关键技术的挑战。针对上述挑战,本文在广泛文献调研的基础上,从双阶段、单阶段目标检测算法的改进与结合的角度分析了改进与优化主流目标检测算法的方法,从骨干网络、增加视觉感受野、特征融合、级联卷积神经网络和模型的训练方式的角度分析了提升小目标检测精度的方法,从训练方式和网络结构的角度分析了用于多类别物体检测的方法,从网络结构的角度分析了用于轻量化检测模型的方法。此外,对目标检测的通用数据集进行了详细介绍,从4个方面对该领域代表性算法的性能表现进行了对比分析,对目标检测中待解决的问题与未来研究方向做出预测和展望。目标检测研究是计算机视觉和模式识别中备受青睐的热点,仍然有更多高精度和高效的算法相继提出,未来将朝着更多的研究方向发展。     

A hybrid CNN and LSTM-based deep learning model for abnormal behavior detection

Multimedia Tools and Applications - Traditional cameras can only record videos passively. If the camera can further automatically recognize human behavior and activity, it can immediately issue an...     

一种基于注意力机制的小目标检测深度学习模型

小目标检测用来识别图像中小像素尺寸目标.传统目标识别算法泛化性差,而通用的深度卷积神经网络算法容易丢失小目标的特征,对小目标识别的效果不甚理想.针对以上问题,提出了一种基于注意力机制的小目标检测深度学习模型AM-R-CNN,该模型在ResNet101主干网络和候选区域生成网络中使用了通道域注意力和空间域注意力,通道域注...