- Conference Article
- 10.5339/qfarc.2016.ictpp1469
Classification of Bisyllabic Lexical Stress Patterns Using Deep Neural Networks
- Jan 01, 2016
- Mostafa Shahin + 1 more +1
Classification of Bisyllabic Lexical Stress Patterns Using Deep Neural Networks
With the rapid development of big data and cloud computing, network security threats are also growing. More and more researchers pay attention to the study of intrusion detection algorithms. Traditional intrusion detection algorithms are often unable to detect attacks with high dimensional and imbalanced data as input training data. In order to solve the problem above, this paper proposes an integrated intrusion detection model based on deep neural network. Furthermore, model integration solves the problem of sample imbalance and improves the generalization ability of the model. In this paper, we firstly use Generative Adversarial Networks(GAN) model to sample dataset. Then, multiple deep neural network (DNN) classifiers are established and special screening of the classifiers was carried out. Afterwards, all DNN classifiers were integrated based on AdaBoost integration algorithm. During the training of DNN classifiers, the training samples are sampled through an antagonistic generation network, which reduce the impact of data imbalance on classification performance of DNN classifiers. Finally, by conducting experiments with KDD 99 and NS-KDD data sets, the good stability and high accuracy of proposed model are verified.
Classification of Bisyllabic Lexical Stress Patterns Using Deep Neural Networks
Classification of Bisyllabic Lexical Stress Patterns Using Deep Neural Networks
IPGuard: Protecting Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundary
A deep neural network (DNN) classifier represents a model owner's intellectual property as training a DNN classifier often requires lots of resource. Watermarking was recently proposed to protect the intellectual property of DNN classifiers. However, watermarking suffers from a key limitation: it sacrifices the utility/accuracy of the model owner's classifier because it tampers the classifier's training or fine-tuning process. In this work, we propose IPGuard, the first method to protect intellectual property of DNN classifiers that provably incurs no accuracy loss for the classifiers. Our key observation is that a DNN classifier can be uniquely represented by its classification boundary. Based on this observation, IPGuard extracts some data points near the classification boundary of the model owner's classifier and uses them to fingerprint the classifier. A DNN classifier is said to be a pirated version of the model owner's classifier if they predict the same labels for most fingerprinting data points. IPGuard is qualitatively different from watermarking. Specifically, IPGuard extracts fingerprinting data points near the classification boundary of a classifier that is already trained, while watermarking embeds watermarks into a classifier during its training or fine-tuning process. We extensively evaluate IPGuard on CIFAR-10, CIFAR-100, and ImageNet datasets. Our results show that IPGuard can robustly identify post-processed versions of the model owner's classifier as pirated versions of the classifier, and IPGuard can identify classifiers, which are not the model owner's classifier nor its post-processed versions, as non-pirated versions of the classifier.
Read moreGrowing random forest on deep convolutional neural networks for scene categorization
Growing random forest on deep convolutional neural networks for scene categorization
Early detection of infestation by mustard aphid, vegetable thrips and two-spotted spider mite in bok choy with deep neural network (DNN) classification model using hyperspectral imaging data
Early detection of infestation by mustard aphid, vegetable thrips and two-spotted spider mite in bok choy with deep neural network (DNN) classification model using hyperspectral imaging data
Read moreGenetic Algorithm Based Over-Sampling with DNN in Classifying the Imbalanced Data Distribution Problem
Objective: Data imbalance exists in many real-life applications. In the imbalanced datasets, the minority class data creates a wrong inference during the classification that leads to more misclassification. More research has been done in the past to solve this issue, but as of now there is no global working solution found to do efficient classification. After analyzing various existing literatures, it is proposed to minimize the misclassification through genetic based oversampling and deep neural network (DNN) classifier. Method: In the proposed oversampling method synthetic samples are generated based on genetic algorithm. Initial populations for the genetic algorithm are generated using Gaussian weight initialization technique and the fittest individual from the population are selected by Euclidean distance for further processing to generate synthetic data in double the minority class size and the dataset is classified with the DNN. Findings: The performance of the oversampled training data with DNN Classifier is compared with C4.5 and Support Vector Machine (SVM) classifiers and found that the DNN classifier outperforms the other two classifiers. The data generated using SMOTE and ADASYN are considered for comparison. It is found that the proposed approach outperforms the other approaches. It is also proved from the experiment that misclassification is reduced and the proposed method is statistically significant and is comparatively better. Novelty: Initial population generation by Gaussian weight initialization, the fittest sample selection by Euclidean distance measure, synthetic samples with double the minority class size and DNN for classification to reduce the misclassification is novelty in this work. Keywords: Genetic algorithm; Gauss weight initialization; SMOTE; ADASYN; Imbalanced data; Classification
Read moreDNN Classifier and Decision Tree-Based Novel Methodology for Analyzing Road Accidents
Nation's social and economic improvement is highly based on the citizen's health profile. Road safety can be considered as one of the most crucial and vital aspects of every country. The trauma of road accidents is, it mainly affects developing countries like Sri Lanka, rather than the developed countries. In Sri Lanka, 2.8% of the deaths are occurred by road accidents which indicate the number of 3554 deaths in last year and over 180 US $ million annually have to spend on road accidents. Furthermore, to reduce the danger of road accidents and to improve road safety, an analysis of road accidents based on machine learning was proposed. The primary aim of this study is to develop a mechanism to predict the driver fault at the accident and identify the accident hot spot in the area, which can be effectively used for taking countermeasures to improve road safety in Sri Lanka. Deep Neural Networks (DNN) classifier, Decision tree, Linear classifier in deep learning have been used to accurately predict and uncover road accident patterns within the data set. Results revealed that the Decision Tree and the DNN classifier are more accurate and comparable than other machine learning techniques used and the first 25 km of the road is more accident-prone rather the other road segments in the road. The research will provide the information needed to guide the relevant decision- makers in adopting suitable measures to prevent and to reduce the accident rate.
Read moreLearning with noisy labels using collaborative sample selection and contrastive semi-supervised learning
Learning with noisy labels using collaborative sample selection and contrastive semi-supervised learning
Robust and Verifiable Information Embedding Attacks to Deep Neural Networks via Error-Correcting Codes
In the era of deep learning, a user often leverages a third-party machine learning tool to train a deep neural network (DNN) classifier and then deploys the classifier as an end-user software product (e.g., a mobile app) or a cloud service. In an information embedding attack, an attacker is the provider of a malicious third-party machine learning tool. The attacker embeds a message into the DNN classifier during training and recovers the message via querying the API of the black-box classifier after the user deploys it. Information embedding attacks have attracted growing attention because of various applications such as watermarking DNN classifiers and compromising user privacy. State-of-the-art information embedding attacks have two key limitations: 1) they cannot verify the correctness of the recovered message, and 2) they are not robust against post-processing (e.g., compression) of the classifier.
Read moreAE-CGAN Model based High Performance Network Intrusion Detection System
In this paper, a high-performance network intrusion detection system based on deep learning is proposed for situations in which there are significant imbalances between normal and abnormal traffic. Based on the unsupervised learning models autoencoder (AE) and the generative adversarial networks (GAN) model during deep learning, the study aim is to solve the imbalance of data and intrusion detection of high performance. The AE-CGAN (autoencoder-conditional GAN) model is proposed to improve the performance of intrusion detection. This model oversamples rare classes based on the GAN model in order to solve the performance degradation caused by data imbalance after processing the characteristics of the data to a lower level using the autoencoder model. To measure the performance of the AE-CGAN model, data is classified using random forest (RF), a typical machine learning classification algorithm. In this experiment, we used the canadian institute for cybersecurity intrusion detection system (CICIDS)2017 dataset, the latest public dataset of network intrusion detection system (NIDS), and compared the three models to confirm efficacy of the proposed model. We compared the performance of three types of models. These included single-RF, a classification model using only a classification algorithm, AE-RF which is processed by classifying data features, and the AE-CGAN model which is classified after solving the data feature processing and data imbalance. Experimental results showed that the performance of the AE-CGAN model proposed in this paper was the highest. In particular, when the data were unbalanced, the performances of recall and F1 score, which are more accurate performance indicators, were 93.29% and 95.38%, respectively. The AE-CGAN model showed much better performance.
Read moreInternet of things intrusion detection model and algorithm based on cloud computing and multi-feature extraction extreme learning machine
Internet of things intrusion detection model and algorithm based on cloud computing and multi-feature extraction extreme learning machine
Read moreDeep neural network classifier for hand movement prediction
The prediction of the hand movement based on Electromyography (EMG) signals has been extensively studied over the past three decades. However, recent EGM applications pose an emerging need of efficient classification of EMG signals. Toward this goal, we propose a deep neural network (DNN) classifier in this study to classify 6 different hand movement from EMG signals. DNN classifier has ability to extract new features from raw data and reduce the dimension of the data set. Our experimental results based on human subjects demonstrate that DNN classifier can efficiently classify the EMG signals to accurately distinguish different hand movement.
Read moreDevelopment of a Radiomic Signature from Pre-Treatment FDG-PET for Recurrence Prediction in Cervical Cancer.
Development of a Radiomic Signature from Pre-Treatment FDG-PET for Recurrence Prediction in Cervical Cancer.
Mapping integrated crop-livestock systems in Brazil with planetscope time series and deep learning
Mapping integrated crop-livestock systems in Brazil with planetscope time series and deep learning
AN ENHANCED METHOD OF LIVER LESION DETECTION USING DEEP NEURAL NETWORK, WATERSHED TRANSFORM AND GAUSSIAN MIXTURE MODEL TECHNIQUES IN MR IMAGES
Cancer of the liver is one of the leading causes of death all over the world. Physically recognising the malignancy tissue is a difficult and time-consuming task. In the future, a computer-aided diagnosis (CAD) will be used in dynamic movement to determine the precise position for care. As a result, the primary goal of this research is to use a robotized approach to precisely identify liver cancer. Methods: In this paper, we suggest a new approach called the watershed Gaussian based deep learning (WGDL) strategy for accurately portraying malignant growth sores in liver MRI images. This project used a total of 150 images to build the proposed model. The liver was first isolated using a marker-controlled watershed division scale, and the malignancy-induced injury was then divided using the Gaussian mixture model (GMM) algorithm. Different surface highlights were removed from the sectioned locale after tumour division. These jumbled highlights were fed into a deep neural network (DNN) classifier for a computerised classification of three types of liver cancer: haemangioma (HEM), hepatocellular carcinoma (HCC), and metastatic carcinoma (MET). The following are the outcomes: Using a Deep Neural Network classifier and an unimportant approval deficiency of 0.053 during the characterization period, we were able to achieve a grouping precision of 98.38 percent at 150 ages. The system in our proposed approach is suitable for testing with a large data set and can assist radiologists in detecting liver malignant growth using MR images. KEYWORDS: computer-aided diagnosis (CAD), watershed Gaussian based deep learning, Gaussian mixture model, hepatocellular carcinoma, metastatic carcinoma, Deep Neural Network classifier
Read moreRETRACTED: Breast cancer diagnosis using multiple activation deep neural network
Deep Neural Network (DNN) stands for multilayered Neural Network (NN) that is capable of progressively learn the more abstract and composite representations of the raw features of the input data received, with no need for any feature engineering. They are advanced NNs having repetitious hidden layers between the initial input and the final layer. The working principle of such a standard deep classifier is based on a hierarchy formed by the composition of linear functions and a defined nonlinear Activation Function (AF). It remains uncertain (not clear) how the DNN classifier can function so well. But it is clear from many studies that within DNN, the AF choice has a notable impact on the kinetics of training and the success of tasks. In the past few years, different AFs have been formulated. The choice of AF is still an area of active study. Hence, in this study, a novel deep Feed forward NN model with four AFs has been proposed for breast cancer classification: hidden layer 1: Swish, hidden layer, 2:-LeakyReLU, hidden layer 3: ReLU, and final output layer: naturally Sigmoidal. The purpose of the study is twofold. Firstly, this study is a step toward a more profound understanding of DNN with layer-wise different AFs. Secondly, research is also aimed to explore better DNN-based systems to build predictive models for breast cancer data with improved accuracy. Therefore, the benchmark UCI dataset WDBC was used for the validation of the framework and evaluated using a ten-fold CV method and various performance indicators. Multiple simulations and outcomes of the experimentations have shown that the proposed solution performs in a better way than the Sigmoid, ReLU, and LeakyReLU and Swish activation DNN in terms of different parameters. This analysis contributes to producing an expert and precise clinical dataset classification method for breast cancer. Furthermore, the model also achieved improved performance compared to many established state-of-the-art algorithms/models.
Read more