scholarly journals Bidirectional Nonnegative Deep Model and Its Optimization in Learning

2016 ◽  
Vol 2016 ◽  
pp. 1-8 ◽  
Author(s):  
Xianhua Zeng ◽  
Zhengyi He ◽  
Hong Yu ◽  
Shengwei Qu
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Nonnegative Matrix ◽  
Feature Representation ◽  
Nonlinear Fitting ◽  
Feature Representations ◽  
Deep Model ◽  
Proposed Model ◽  
Out Of Sample ◽  
Narrow Signal

Nonnegative matrix factorization (NMF) has been successfully applied in signal processing as a simple two-layer nonnegative neural network. Projective NMF (PNMF) with fewer parameters was proposed, which projects a high-dimensional nonnegative data onto a lower-dimensional nonnegative subspace. Although PNMF overcomes the problem of out-of-sample of NMF, it does not consider the nonlinear characteristic of data and is only a kind of narrow signal decomposition method. In this paper, we combine the PNMF with deep learning and nonlinear fitting to propose a bidirectional nonnegative deep learning (BNDL) model and its optimization learning algorithm, which can obtain nonlinear multilayer deep nonnegative feature representation. Experiments show that the proposed model can not only solve the problem of out-of-sample of NMF but also learn hierarchical nonnegative feature representations with better clustering performance than classical NMF, PNMF, and Deep Semi-NMF algorithms.

scholarly journals An Investigation into the Application of Deep Learning in the Detection and Mitigation of DDOS Attack on SDN Controllers

Technologies ◽  
2021 ◽  
Vol 9 (1) ◽  
pp. 14
Author(s):  
James Dzisi Gadze ◽  
Akua Acheampomaa Bamfo-Asante ◽  
Justice Owusu Agyemang ◽  
Henry Nunoo-Mensah ◽  
Kwasi Adu-Boahen Opare
Keyword(s):  
Deep Learning ◽  
Network Architecture ◽  
Learning Algorithm ◽  
Single Point ◽  
Denial Of Service ◽  
Specific Work ◽  
Learning Models ◽  
Ddos Attack ◽  
Deep Learning Algorithm ◽  
Proposed Model

Software-Defined Networking (SDN) is a new paradigm that revolutionizes the idea of a software-driven network through the separation of control and data planes. It addresses the problems of traditional network architecture. Nevertheless, this brilliant architecture is exposed to several security threats, e.g., the distributed denial of service (DDoS) attack, which is hard to contain in such software-based networks. The concept of a centralized controller in SDN makes it a single point of attack as well as a single point of failure. In this paper, deep learning-based models, long-short term memory (LSTM) and convolutional neural network (CNN), are investigated. It illustrates their possibility and efficiency in being used in detecting and mitigating DDoS attack. The paper focuses on TCP, UDP, and ICMP flood attacks that target the controller. The performance of the models was evaluated based on the accuracy, recall, and true negative rate. We compared the performance of the deep learning models with classical machine learning models. We further provide details on the time taken to detect and mitigate the attack. Our results show that RNN LSTM is a viable deep learning algorithm that can be applied in the detection and mitigation of DDoS in the SDN controller. Our proposed model produced an accuracy of 89.63%, which outperformed linear-based models such as SVM (86.85%) and Naive Bayes (82.61%). Although KNN, which is a linear-based model, outperformed our proposed model (achieving an accuracy of 99.4%), our proposed model provides a good trade-off between precision and recall, which makes it suitable for DDoS classification. In addition, it was realized that the split ratio of the training and testing datasets can give different results in the performance of a deep learning algorithm used in a specific work. The model achieved the best performance when a split of 70/30 was used in comparison to 80/20 and 60/40 split ratios.

scholarly journals A Novel Point Cloud Encoding Method Based on Local Information for 3D Classification and Segmentation

Sensors ◽  
2020 ◽  
Vol 20 (9) ◽  
pp. 2501 ◽  
Author(s):  
Yanan Song ◽  
Liang Gao ◽  
Xinyu Li ◽  
Weiming Shen
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Semantic Segmentation ◽  
Local Information ◽  
Local Region ◽  
Feature Representation ◽  
Learning Network ◽  
Feature Representations ◽  
Encoding Method ◽  
Deep Learning Network

Deep learning is robust to the perturbation of a point cloud, which is an important data form in the Internet of Things. However, it cannot effectively capture the local information of the point cloud and recognize the fine-grained features of an object. Different levels of features in the deep learning network are integrated to obtain local information, but this strategy increases network complexity. This paper proposes an effective point cloud encoding method that facilitates the deep learning network to utilize the local information. An axis-aligned cube is used to search for a local region that represents the local information. All of the points in the local region are available to construct the feature representation of each point. These feature representations are then input to a deep learning network. Two well-known datasets, ModelNet40 shape classification benchmark and Stanford 3D Indoor Semantics Dataset, are used to test the performance of the proposed method. Compared with other methods with complicated structures, the proposed method with only a simple deep learning network, can achieve a higher accuracy in 3D object classification and semantic segmentation.

scholarly journals Deep Learning for Generic Object Detection: A Survey

2019 ◽  
Vol 128 (2) ◽  
pp. 261-318 ◽  
Author(s):  
Li Liu ◽  
Wanli Ouyang ◽  
Xiaogang Wang ◽  
Paul Fieguth ◽  
Jie Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Rapid Evolution ◽  
Feature Representation ◽  
Future Research ◽  
Context Modeling ◽  
Feature Representations ◽  
Learning Techniques ◽  
Comprehensive Survey ◽  
Object Feature

Abstract Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images. Deep learning techniques have emerged as a powerful strategy for learning feature representations directly from data and have led to remarkable breakthroughs in the field of generic object detection. Given this period of rapid evolution, the goal of this paper is to provide a comprehensive survey of the recent achievements in this field brought about by deep learning techniques. More than 300 research contributions are included in this survey, covering many aspects of generic object detection: detection frameworks, object feature representation, object proposal generation, context modeling, training strategies, and evaluation metrics. We finish the survey by identifying promising directions for future research.

scholarly journals Real-Time Vehicle Make and Model Recognition with the Residual SqueezeNet Architecture

Sensors ◽  
2019 ◽  
Vol 19 (5) ◽  
pp. 982 ◽  
Author(s):  
Hyo Lee ◽  
Ihsan Ullah ◽  
Weiguo Wan ◽  
Yongbin Gao ◽  
Zhijun Fang
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Large Scale ◽  
Recognition Rate ◽  
Experimental Results ◽  
Learning Approach ◽  
Deep Model ◽  
Proposed Model ◽  
Real Time Applications ◽  
Model Recognition

Make and model recognition (MMR) of vehicles plays an important role in automatic vision-based systems. This paper proposes a novel deep learning approach for MMR using the SqueezeNet architecture. The frontal views of vehicle images are first extracted and fed into a deep network for training and testing. The SqueezeNet architecture with bypass connections between the Fire modules, a variant of the vanilla SqueezeNet, is employed for this study, which makes our MMR system more efficient. The experimental results on our collected large-scale vehicle datasets indicate that the proposed model achieves 96.3% recognition rate at the rank-1 level with an economical time slice of 108.8 ms. For inference tasks, the deployed deep model requires less than 5 MB of space and thus has a great viability in real-time applications.

scholarly journals Learning to Combine Local and Global Image Information for Contactless Palmprint Recognition

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 73
Author(s):  
Marjan Stoimchev ◽  
Marija Ivanovska ◽  
Vitomir Štruc
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Input Image ◽  
Palmprint Recognition ◽  
Learning Approaches ◽  
Elastic Deformations ◽  
Feature Representations ◽  
Palmar Surface ◽  
Proposed Model ◽  
Visual Artifacts

In the past few years, there has been a leap from traditional palmprint recognition methodologies, which use handcrafted features, to deep-learning approaches that are able to automatically learn feature representations from the input data. However, the information that is extracted from such deep-learning models typically corresponds to the global image appearance, where only the most discriminative cues from the input image are considered. This characteristic is especially problematic when data is acquired in unconstrained settings, as in the case of contactless palmprint recognition systems, where visual artifacts caused by elastic deformations of the palmar surface are typically present in spatially local parts of the captured images. In this study we address the problem of elastic deformations by introducing a new approach to contactless palmprint recognition based on a novel CNN model, designed as a two-path architecture, where one path processes the input in a holistic manner, while the second path extracts local information from smaller image patches sampled from the input image. As elastic deformations can be assumed to most significantly affect the global appearance, while having a lesser impact on spatially local image areas, the local processing path addresses the issues related to elastic deformations thereby supplementing the information from the global processing path. The model is trained with a learning objective that combines the Additive Angular Margin (ArcFace) Loss and the well-known center loss. By using the proposed model design, the discriminative power of the learned image representation is significantly enhanced compared to standard holistic models, which, as we show in the experimental section, leads to state-of-the-art performance for contactless palmprint recognition. Our approach is tested on two publicly available contactless palmprint datasets—namely, IITD and CASIA—and is demonstrated to perform favorably against state-of-the-art methods from the literature. The source code for the proposed model is made publicly available.

scholarly journals A Novel Feature Representation for Prediction of Global Horizontal Irradiance Using a Bidirectional Model

2021 ◽  
Vol 3 (4) ◽  
pp. 946-965
Author(s):  
Sourav Malakar ◽  
Saptarsi Goswami ◽  
Bhaswati Ganguli ◽  
Amlan Chakrabarti ◽  
Sugata Sen Roy ◽  
...  
Keyword(s):  
Deep Learning ◽  
Solar Energy ◽  
Weather Conditions ◽  
Feature Representation ◽  
Energy Prediction ◽  
Pv Systems ◽  
Proposed Model ◽  
Energy Domain ◽  
Learning Architectures ◽  
Gated Recurrent Unit

Complex weather conditions—in particular clouds—leads to uncertainty in photovoltaic (PV) systems, which makes solar energy prediction very difficult. Currently, in the renewable energy domain, deep-learning-based sequence models have reported better results compared to state-of-the-art machine-learning models. There are quite a few choices of deep-learning architectures, among which Bidirectional Gated Recurrent Unit (BGRU) has apparently not been used earlier in the solar energy domain. In this paper, BGRU was used with a new augmented and bidirectional feature representation. The used BGRU network is more generalized as it can handle unequal lengths of forward and backward context. The proposed model produced 59.21%, 37.47%, and 76.80% better prediction accuracy compared to traditional sequence-based, bidirectional models, and some of the established states-of-the-art models. The testbed considered for evaluation of the model is far more comprehensive and reliable considering the variability in the climatic zones and seasons, as compared to some of the recent studies in India.

scholarly journals A New Hybrid Deep Learning Algorithm for Prediction of Wide Traffic Congestion in Smart Cities

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
G. Kothai ◽  
E. Poovammal ◽  
Gaurav Dhiman ◽  
Kadiyala Ramana ◽  
Ashutosh Sharma ◽  
...  
Keyword(s):  
Deep Learning ◽  
Dynamic Behavior ◽  
Traffic Congestion ◽  
Performance Metrics ◽  
Learning Algorithm ◽  
Smart Cities ◽  
Experimental Result ◽  
Learning Models ◽  
Essential Information ◽  
Proposed Model

The vehicular adhoc network (VANET) is an emerging research topic in the intelligent transportation system that furnishes essential information to the vehicles in the network. Nearly 150 thousand people are affected by the road accidents that must be minimized, and improving safety is required in VANET. The prediction of traffic congestions plays a momentous role in minimizing accidents in roads and improving traffic management for people. However, the dynamic behavior of the vehicles in the network degrades the rendition of deep learning models in predicting the traffic congestion on roads. To overcome the congestion problem, this paper proposes a new hybrid boosted long short-term memory ensemble (BLSTME) and convolutional neural network (CNN) model that ensemble the powerful features of CNN with BLSTME to negotiate the dynamic behavior of the vehicle and to predict the congestion in traffic effectively on roads. The CNN extracts the features from traffic images, and the proposed BLSTME trains and strengthens the weak classifiers for the prediction of congestion. The proposed model is developed using Tensor flow python libraries and are tested in real traffic scenario simulated using SUMO and OMNeT++. The extensive experimentations are carried out, and the model is measured with the performance metrics likely prediction accuracy, precision, and recall. Thus, the experimental result shows 98% of accuracy, 96% of precision, and 94% of recall. The results complies that the proposed model clobbers the other existing algorithms by furnishing 10% higher than deep learning models in terms of stability and performance.

scholarly journals Development of Deep Learning Algorithm for Brain Tumor Segmentation

2019 ◽  
Vol 9 (1) ◽  
pp. 2800-2803
Keyword(s):  
Deep Learning ◽  
Brain Tumor ◽  
Brain Tumors ◽  
Learning Algorithm ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation ◽  
Human Errors ◽  
Deep Learning Algorithm ◽  
Proposed Model ◽  
A New Technique

Medical imaging is an emerging field in engineering. As traditional way of brain tumor analysis, MRI scanning is the way to identify brain tumor. The core drawback of manual MRI studies conducted by surgeons is getting manual visual errorswhich can lead toofa false identification of tumor boundaries. To avoid such human errors, ultra age engineering adopted deep learning as a new technique for brain tumor segmentation. Deep learning convolution network can be further developed by means of various deep learning models for better performance. Hence, we proposed a new deep learning algorithm development which can more efficiently identifies the types of brain tumors in terms of level of tumor like T1, T2, and T1ce etc. The proposed system can identify tumors using convolution neural network(CNN) which works with the proposed algorithm “Sculptor DeepCNet”. The proposed model can be used by surgeons to identify post-surgical remains (if any) of brain tumors and thus proposed research can be useful for ultra-age neural surgical image assessments. This paper discusses newly developed algorithm and its testing results.

scholarly journals An Improved Deep Learning Model for Traffic Crash Prediction

2018 ◽  
Vol 2018 ◽  
pp. 1-13 ◽  
Author(s):  
Chunjiao Dong ◽  
Chunfu Shao ◽  
Juan Li ◽  
Zhihua Xiong
Keyword(s):  
Deep Learning ◽  
Feature Learning ◽  
Learning Model ◽  
Fine Tuning ◽  
Crash Prediction ◽  
Traffic Crash ◽  
Explanatory Variables ◽  
Feature Representations ◽  
Proposed Model ◽  
Deep Learning Model

Machine-learning technology powers many aspects of modern society. Compared to the conventional machine learning techniques that were limited in processing natural data in the raw form, deep learning allows computational models to learn representations of data with multiple levels of abstraction. In this study, an improved deep learning model is proposed to explore the complex interactions among roadways, traffic, environmental elements, and traffic crashes. The proposed model includes two modules, an unsupervised feature learning module to identify functional network between the explanatory variables and the feature representations and a supervised fine tuning module to perform traffic crash prediction. To address the unobserved heterogeneity issues in the traffic crash prediction, a multivariate negative binomial (MVNB) model is embedding into the supervised fine tuning module as a regression layer. The proposed model was applied to the dataset that was collected from Knox County in Tennessee to validate the performances. The results indicate that the feature learning module identifies relational information between the explanatory variables and the feature representations, which reduces the dimensionality of the input and preserves the original information. The proposed model that includes the MVNB regression layer in the supervised fine tuning module can better account for differential distribution patterns in traffic crashes across injury severities and provides superior traffic crash predictions. The findings suggest that the proposed model is a superior alternative for traffic crash predictions and the average accuracy of the prediction that was measured by RMSD can be improved by 84.58% and 158.27% compared to the deep learning model without the regression layer and the SVM model, respectively.

scholarly journals A New Semantic and Statistical Distance-Based Anomaly Detection in Crowd Video Surveillance

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Fariba Rezaei ◽  
Mehran Yazdi
Keyword(s):  
Anomaly Detection ◽  
Topic Model ◽  
Nonnegative Matrix ◽  
Feature Representation ◽  
Test Time ◽  
Model Learning ◽  
Deep Model ◽  
Level Information ◽  
The Difference ◽  
High Level

Recently, attention toward autonomous surveillance has been intensified and anomaly detection in crowded scenes is one of those significant surveillance tasks. Traditional approaches include the extraction of handcrafted features that need the subsequent task of model learning. They are mostly used to extract low-level spatiotemporal features of videos, neglecting the effect of semantic information. Recently, deep learning (DL) methods have been emerged in various domains, especially CNN for visual problems, with the ability to extract high-level information at higher layers of their architectures. On the other side, topic modeling-based approaches like NMF can extract more semantic representations. Here, we investigate a new hybrid visual embedding method based on deep features and a topic model for anomaly detection. Features per frame are computed hierarchically through a pretrained deep model, and in parallel, topic distributions are learned through multilayer nonnegative matrix factorization entangling information from extracted deep features. Training is accomplished through normal samples. Thereafter, K -means is applied to find typical normal clusters. At test time, after achieving feature representation through deep model and topic distribution for test frames, a statistical earth mover distance (EMD) metric is evaluated to measure the difference between normal cluster centroids and test topic distributions. High difference versus a threshold is detected as an anomaly. Experimental results on the benchmark Ped1 and Ped2 UCSD datasets demonstrate the effectiveness of our proposed method in anomaly detection.

Sign in / Sign up

Export Citation Format

Share Document