We demonstrate a novel method for the automatic modulation classification based on a deep learning autoencoder network, trained by a nonnegativity constraint algorithm. The learning algorithm aims to constrain the neg...
详细信息
We demonstrate a novel method for the automatic modulation classification based on a deep learning autoencoder network, trained by a nonnegativity constraint algorithm. The learning algorithm aims to constrain the negative weights, learns features that amount to a part-based representation of data, and disentangles a more meaningful hidden structure. The performance of this algorithm is tested on the fourth-order cumulants of the modulated signals. The results indicate that the autoencoder with nonnegativity constraint (ANC) improves the sparsity and minimizes the reconstruction error in comparison with the conventional sparse autoencoder. The classification accuracy of an ANC based deep network shows improved accuracy under limited signal length and fading channel.
Deep learning algorithms have recently been applied to solving challenging problems in medicine such as medical image classification and analysis. In some areas, those algorithms have outperformed the human medical ex...
详细信息
Deep learning algorithms have recently been applied to solving challenging problems in medicine such as medical image classification and analysis. In some areas, those algorithms have outperformed the human medical experts experience in diagnosis. Thus, in this paper we apply three different deep networks to solve the problem of brain hemorrhage identification in CT images. The motivation behind this work is the difficulty that radiologists encounter when diagnosing a hemorrhagic brain CT image, in particularly in the early stages of the brain bleeding. autoencoder (AE), stacked autoencoder (SAE), and convolutional neural network (CNN) are employed and trained to classify the CT images into hemorrhagic or non-hemorrhagic. Experimentally, it was found that all employed networks performed differently in terms of accuracy, error reached, and training time. However, stacked autoencoder has achieved a higher accuracy and lesser error compared to other used networks.
A vision-based obstacle detection system is a key enabler for the development of autonomous robots and vehicles and intelligent transportation systems. This paper addresses the problem of urban scene monitoring and tr...
详细信息
A vision-based obstacle detection system is a key enabler for the development of autonomous robots and vehicles and intelligent transportation systems. This paper addresses the problem of urban scene monitoring and tracking of obstacles based on unsupervised, deep-learning approaches. Here, we design an innovative hybrid encoder that integrates deep Boltzmann machines (DBM) and auto-encoders (AE). This hybrid auto-encode (HAE) model combines the greedy learning features of DBM with the dimensionality reduction capacity of AE to accurately and reliably detect the presence of obstacles. We combine the proposed hybrid model with the one-class support vector machines (OCSVM) to visually monitor an urban scene. We also propose an efficient approach to estimating obstacles location and track their positions via scene densities. Specifically, we address obstacle detection as an anomaly detection problem. If an obstacle is detected by the OCSVM algorithm, then localization and tracking algorithm is executed. We validated the effectiveness of our approach by using experimental data from two publicly available dataset, the Malaga stereovision urban dataset (MSVUD) and the Daimler urban segmentation dataset (DUSD). Results show the capacity of the proposed approach to reliably detect obstacles. (C) 2017 Elsevier B.V. All rights reserved.
Anomaly detection refers to finding observations which do not conform to expected behavior. It is widely applied in many domains such as image processing, fraud detection, intrusion detection, medical health, etc. How...
详细信息
Anomaly detection refers to finding observations which do not conform to expected behavior. It is widely applied in many domains such as image processing, fraud detection, intrusion detection, medical health, etc. However, most of the anomaly detection techniques focus on detecting a single anomalous instance. Such techniques fail when there is only a slight difference between the anomalous instance and a non-anomalous instance. Various collective anomaly detection techniques (based on clustering, deep learning, etc) have been developed that determine whether a group of records form an anomaly even though they are only slightly anomalous instances. However, they do not provide any information about the attributes that make the group anomalous. In other words, they are focused only on detecting records that are collectively anomalous and are not able to detect anomalous patterns in general. FGSS is a scalable anomalous pattern detection technique that searches over both records and attributes. However, FGSS has several limitations preventing it from functioning on continuous, unstructured and high dimensional data such as images, etc. We propose a general framework called DeepFGSS, which uses autoencoder, enabling it to operate on any kind of data. We evaluate its performance using four experiments on both structured and unstructured data to determine its accuracy of detecting anomalies and efficiency of distinguishing between datasets containing anomalies and ones that do not.
Most modern communication systems rely on separate source encoding and channel encoding schemes to transmit data. Despite the long-lasting success of separate schemes, joint source channel coding schemes have been pro...
详细信息
Most modern communication systems rely on separate source encoding and channel encoding schemes to transmit data. Despite the long-lasting success of separate schemes, joint source channel coding schemes have been proven to outperform separate schemes in applications such as video communications. The task of this research is to develop a joint source-channel coding scheme that mitigates some of the limitations of current separate coding schemes. My research will attempt to leverage recent advances in machine/deep learning techniques to develop resilient schemes that do not depend on explicit codes for compression and error correction but automatically learn end-to-end mapping schemes for source signals. The success of the developed scheme will depend on its ability to correctly approximate an input vector under inconsistent channel conditions.
Spinal clinicians still rely on laborious workloads to conduct comprehensive assessments of multiple spinal structures in MRIs, in order to detect abnormalities and discover possible pathological factors. The objectiv...
详细信息
Spinal clinicians still rely on laborious workloads to conduct comprehensive assessments of multiple spinal structures in MRIs, in order to detect abnormalities and discover possible pathological factors. The objective of this work is to perform automated segmentation and classification (i.e., normal and abnormal) of intervertebral discs, vertebrae, and neural foramen in MRIs in one shot, which is called semantic segmentation that is extremely urgent to assist spinal clinicians in diagnosing neural foraminal stenosis, disc degeneration, and vertebral deformity as well as discovering possible pathological factors. However, no work has simultaneously achieved the semantic segmentation of intervertebral discs, vertebrae, and neural foramen due to three-fold unusual challenges: I) Multiple tasks, i.e., simultaneous semantic segmentation of multiple spinal structures, are more difficult than individual tasks;2) Multiple targets: average 21 spinal structures per MRI require automated analysis yet have high variety and variability;3) Weak spatial correlations and subtle differences between normal and abnormal structures generate dynamic complexity and indeterminacy. In this paper, we propose a Recurrent Generative Adversarial Network called Spine-GAN for resolving above-aforementioned challenges. Firstly, Spine-GAN explicitly solves the high variety and variability of complex spinal structures through an atrous convolution (i.e., convolution with holes) autoencoder module that is capable of obtaining semantic task-aware representation and preserving fine-grained structural information. Secondly, Spine-GAN dynamically models the spatial pathological correlations between both normal and abnormal structures thanks to a specially designed long short-term memory module. Thirdly, Spine-GAN obtains reliable performance and efficient generalization by leveraging a discriminative network that is capable of correcting predicted errors and global-level contiguity. Extensive experimen
With the proliferation of micro-phasor measurement units (mu PMU) and PMUs in smart grids, time synchronized high-resolution measurements can be obtained and used for numerous applications such as state estimation and...
详细信息
With the proliferation of micro-phasor measurement units (mu PMU) and PMUs in smart grids, time synchronized high-resolution measurements can be obtained and used for numerous applications such as state estimation and event analysis. Disruptive events frequently occur in power grids and interrupt the normal operation of the system and may eventually cause the permanent failure of equipment. Therefore, establishing a data-driven event diagnostic framework to extract useful information such as the cause or location of events is of utmost importance. The disruptive events may not cause immediate and direct failure. However, they are a potential source for permanent equipment failure over time. Accurate disruptive event analysis is beneficial in terms of time, maintenance crew utilization, and future outages prevention. In this paper, a PMU data-driven framework is proposed to distinguish two disruptive events, i.e., malfunctioned capacitor bank switching and malfunctioned regulator on-load tap changer (OLTC) switching from two normal operating events i.e., the normal abrupt load change and the reconfiguration in distribution grids. The event classification is formulated using a neural network based algorithm, i.e., autoencoders along with softmax classifiers. The performance of the proposed framework is verified using the simulation of the events on the modified IEEE 123-bus distribution test system. The end results of this paper demonstrate the effectiveness of the proposed algorithm and satisfactory classification accuracies under several conditions such as different PMU reporting rates, different measurement noise levels, different number of PMUs, and boosting scenario. (C) 2017 Elsevier B.V. All rights reserved.
A scene image is typically composed of successive background contexts and objects with regular shapes. To acquire such spatial information, we propose a new type of spatial partitioning scheme and a modified pyramid m...
详细信息
A scene image is typically composed of successive background contexts and objects with regular shapes. To acquire such spatial information, we propose a new type of spatial partitioning scheme and a modified pyramid matching kernel based on spatial pyramid matching (SPM). A dense histogram of oriented gradients (HOG) is used as a low-level visual descriptor. Furthermore, inspired by the expressive coding ability of autoencoders, we also propose another approach that encodes local descriptors into mid-level features using various autoencoders. The learned mid-level features are encouraged to be sparse, robust and contractive. Then, modified spatial pyramid pooling and local normalization of the mid-level features facilitate the generation of high-level image signatures for scene classification. Comprehensive experimental results on publicly available scene datasets demonstrate the effectiveness of our methods. (C) 2018 Elsevier Ltd. All rights reserved.
Studies have implied that depth is one of the important cues guiding visual attention. However, depth information has not been well explored in existing saliency estimation models. In this paper, we propose a model in...
详细信息
Studies have implied that depth is one of the important cues guiding visual attention. However, depth information has not been well explored in existing saliency estimation models. In this paper, we propose a model inspired by the observations in three-dimensional environment to better present the influence of depth. Firstly, we use depth to estimate each region's probability of being background. Afterward, we sample pairs of surrounding and central patches from the possible background of each image to train an autoencoder-based network. As a network learned from background, it tends to describe the center-surround reconstruction pattern in background rather than foreground. Therefore, the detection of saliency can be formulated by measuring the reconstruction residual of the network. With emphasis on sampling from background, the proposed method can decrease the false positive rate in stereoscopic saliency estimation significantly. Experimental results demonstrate that the proposed method can outperform the state-of-the-art fixation prediction algorithms on several public data sets for stereoscopic saliency estimation. Additionally, it is efficiently used for proto-object extraction. (C) 2018 Elsevier B.V. All rights reserved.
暂无评论