Botnet attack is a severe cyber security issue, which occurs in the Internet of Things (IoT). These attacks are carried out by hackers to acquire control of various IoT devices and carry out illegal activities. Though...
详细信息
Botnet attack is a severe cyber security issue, which occurs in the Internet of Things (IoT). These attacks are carried out by hackers to acquire control of various IoT devices and carry out illegal activities. Though several methods have been proposed to overcome these issues, the rapidly evolving nature of botnet makes attack detection complicated. Hence, in this paper a deep Learning (DL) model is introduced for identifying botnets in IoT. Initially, the IoT network is simulated, and the detection of attack is established using the log data. Afterwards, the log data is fed into data pre-processing, in which the data is pre-processed by Quantile normalization. Then, feature selection is effectuated by employing Information Gain (IG), and City Block Distance. Once the feature selection is performed, data augmentation is done with the use of oversampling to increase the samples. Lastly, the Botnet attack detection is carried out by using the proposed Convolutional Neural Network Fused with deep stacked autoencoder (CNN-FDSA), which is formed by fusing deep stacked autoencoder (DSA) and Convolutional Neural Network (CNN). Furthermore, the proposed CNN-FDSA attained the highest recall, precision, f-measure, and accuracy of 90.3 %, 91.6 %, 90.9 %, and 92.4 %, and then the lowest False Positive Rate (FPR) of 8.2 %.
With the rapid growth of Internet technology and social networks, the generation of text-based information on the web is increased. To ease the Natural Language Processing (NLP) tasks, analyzing the sentiments behind ...
详细信息
With the rapid growth of Internet technology and social networks, the generation of text-based information on the web is increased. To ease the Natural Language Processing (NLP) tasks, analyzing the sentiments behind the provided input text is highly important. To effectively analyze the polarities of sentiments (positive, negative and neutral), categorizing the aspects in the text is an essential task. Several existing studies have attempted to accurately classify aspects based on sentiments in text inputs. However, the existing methods attained limited performance because of reduced aspect coverage, inefficiency in handling ambiguous language, inappropriate feature extraction, lack of contextual understanding and overfitting issues. Thus, the proposed study intends to develop an effective word embedding scheme with a novel hybrid deep learning technique for performing aspectbased sentimental analysis in a social media text. Initially, the collected raw input text data are pre-processed to reduce the undesirable data by initiating tokenization, stemming, lemmatization, duplicate removal, stop words removal, empty sets removal and empty rows removal. The required information from the pre-processed text is extracted using three varied word-level embedding methods: Scored-Lexicon based Word2Vec, Glove modelling and Extended Bidirectional Encoder Representation from Transformers (E-BERT). After extracting sufficient features, the aspects are analyzed, and the exact sentimental polarities are classified through a novel PositionalAttention-based Bidirectional deep stacked autoencoder (PA_BiDSAE) model. In this proposed classification, the BiLSTM network is hybridized with a deep stacked autoencoder (DSAE) model to categorize sentiment. The experimental analysis is done by using Python software, and the proposed model is simulated with three publicly available datasets: SemEval Challenge 2014 (Restaurant), SemEval Challenge 2014 (Laptop) and SemEval Challenge 2015 (Restau
This research introduced the optimized deep stacked autoencoder (DSA) for performing Intrusion Detection (ID) in the IoT. Firstly, IoT simulation is carried out and then, the information is routed by using the Chronol...
详细信息
This research introduced the optimized deep stacked autoencoder (DSA) for performing Intrusion Detection (ID) in the IoT. Firstly, IoT simulation is carried out and then, the information is routed by using the Chronological War Strategy Optimization (CWSO). Here, the CWSO is newly designed by incorporating the chronological concept with the WSO. After the routing, the ID is completed at the Base station (BS) by executing the following steps. Initially, data is obtained from a database, after that, feature normalization is done using min-max normalization. Meanwhile, Canberra distance is applied to execute the feature selection process. Finally, ID is performed using DSA, which is trained using the Competitive Swarm Henry War Strategy Optimization algorithm (CSHWO). The experimental result confirms that the invented scheme accomplished the superior outcome by the energy, f-score, precision, and recall values of 0.379, 0.913, 0.918 and 0.912, respectively.
Phishing attacks have emerged as a major social engineering threat that affects businesses, governments, and general internet users. This work proposes a social engineering phishing detection technique based on deep L...
详细信息
Phishing attacks have emerged as a major social engineering threat that affects businesses, governments, and general internet users. This work proposes a social engineering phishing detection technique based on deep Learning (DL). Initially, website data is taken from the dataset. Then, the features of Natural Language Processing (NLP) like bag of words, n-gram, hashtags, sentence length, Term Frequency- Inverse Document Frequency of records (TF-IDF), and all caps are extracted and then web feature extraction is carried out. Later, the feature fusion is done using the Neyman similarity with deep Belief Network (DBN). Afterwards, oversampling is used for data augmentation to enhance the number of training samples. Lastly, the detection of phishing attacks is performed by employing the proposed Fuzzy deep Neural-stackedautoencoder (FDN-SA). Here, the proposed FDN-SA is developed by combining a deep Neural Network (DNN), and deep stacked autoencoder (DSA). Further, the investigation of FDN-SA is accomplished based on the accuracy, True Positive Rate (TPR), and True Negative Rate (TNR) and is observed to compute values of 0.920, 0.925, and 0.921, respectively.
Human motion analysis using a smartphone-embedded accelerometer sensor provided important context for the identification of static, dynamic, and complex sequence of activities. Research in smartphone-based motion anal...
详细信息
Human motion analysis using a smartphone-embedded accelerometer sensor provided important context for the identification of static, dynamic, and complex sequence of activities. Research in smartphone-based motion analysis are implemented for tasks, such as health status monitoring, fall detection and prevention, energy expenditure estimation, and emotion detection. However, current methods, in this regard, assume that the device is tightly attached to a pre-determined position and orientation, which might cause performance degradation in accelerometer data due to changing orientation. Therefore, it is challenging to accurately and automatically identify activity details as a result of the complexity and orientation inconsistencies of the smartphone. Furthermore, the current activity identification methods utilize conventional machine learning algorithms that are application dependent. Moreover, it is difficult to model the hierarchical and temporal dynamic nature of the current, complex, activity identification process. This paper aims to propose a deep stacked autoencoder algorithm, and orientation invariant features, for complex human activity identification. The proposed approach is made up of various stages. First, we computed the magnitude norm vector and rotation feature (pitch and roll angles) to augment the three-axis dimensions (3-D) of the accelerometer sensor. Second, we propose a deep stacked autoencoder based deep learning algorithm to automatically extract compact feature representation from the motion sensor data. The results show that the proposed integration of the deep learning algorithm, and orientation invariant features, can accurately recognize complex activity details using only smartphone accelerometer data. The proposed deep stacked autoencoder method achieved 97.13% identification accuracy compared to the conventional machine learning methods and the deep belief network algorithm. The results suggest the impact of the proposed method to imp
The innovation of technologies has become ubiquitous and imperative in day-to-day lives. Malware is the major threat to the network, and Ransomware is a special and harmful type of malware. Ransomware led to huge data...
详细信息
The innovation of technologies has become ubiquitous and imperative in day-to-day lives. Malware is the major threat to the network, and Ransomware is a special and harmful type of malware. Ransomware led to huge data losses and induced huge economic costs. Moreover, Ransomware detection is a crucial task to minimize analyst's workloads. This paper devises a novel deep learning method for detecting Ransomware using the blockchain network. Here, the sequence-based statistical feature extraction is performed, wherein the features are extracted using 2-gram and 3-gram opcodes. Also, the term frequency-inverse document frequency (TF-IDF) is discovered for each feature. Then the Box-Cox transformation is applied to transformation to the data for improved analysis. Also, the feature fusion is progressed using a fractional concept. Finally, the classification of Ransomware is done using deepstacked Auto-encoder (deep SAE), wherein the proposed Water wave-based Moth Flame optimization (WMFO) is adapted for generating the optimal weights. The WMFO is designed by integrating Water wave optimization (WWO) and Moth Flame optimization (MFO). The proposed WMFO-deep SAE outperformed other methods with maximal accuracy of 96.925%, sensitivity of 96.900%, and specificity of 97.920%.
The skills of forensic analysts are at risk to process the increasing data in the Internet of Things-based environment platforms. However, the technical issues like anti-forensics, variety of traffic formats, steganog...
详细信息
The skills of forensic analysts are at risk to process the increasing data in the Internet of Things-based environment platforms. However, the technical issues like anti-forensics, variety of traffic formats, steganography or encrypted data, and real-time live investigation degrades the performance of the cyber forensic framework. Therefore, an effective method named Sunflower Jaya Optimization-based deep stacked autoencoder (SFJO-based deep stacked autoencoder) is proposed to perform the cyber forensic framework. The finite element model of Sunflower optimization is integrated with the control parameters of Jaya optimization to solve the issues in the cyber forensic framework. The proposed SFJO-based deep stacked autoencoder uses the pollination and the peculiar behaviors to enable the cyber forensic framework based on the error value in the big data analytics model. Accordingly, the solution with the minimal value of error is accepted as the best optimal solution by computing the orientation vector. However, the proposed model is illustrated based on the unconstrained benchmark function, which in turn results in the fitness function to reveal the best candidate solution. The proposed SFJO-based deep stacked autoencoder attained better performance using metrics like precision, sensitivity, and specificity with the values of 0.9053, 0.8865, and 0.8839 using dataset-1.
Human action recognition plays a significant role in a number of computer vision applications. This work is based on three processing stages. In the first stage, discriminative frames are selected as representative fr...
详细信息
Human action recognition plays a significant role in a number of computer vision applications. This work is based on three processing stages. In the first stage, discriminative frames are selected as representative frames per action to minimize the computational cost and time. In the second stage, novel neighbourhood selection approaches based on geometric shapes including triangle, quadrilateral, pentagon, hexagon, octagon and heptagon are used in Volumetric Local Binary Pattern (VLBP) to extract the features from frame sequences based on motion and appearance information. Hexagonal Volume Local Binary Pattern (H-VLBP) descriptor has been found to produce better results among all other novel geometric shape based neighbourhood selection approaches for human action recognition. However, the dimensionality of extracted feature from H-VLBP is too large. Therefore, the deep stacked autoencoder is used for dimensionality reduction with the decoder layer replaced by softmax layer for performing multi-class recognition. The developed approach is applied to four publicly available benchmark datasets, namely KTH, Weizmann, UCF11 dataset and IXMAS dataset for human action recognition. The results obtained show that the proposed approach outperforms the state-of-art techniques. Moreover, the approach has been tested with a synthetic dataset and better results have been obtained. This illustrates the effectiveness of the approach in real time environment. (C) 2019 Elsevier B.V. All rights reserved.
Wind and solar energy are two popular forms of renewable energy used in microgrids and facilitating the transition towards net-zero carbon emissions by ***,they are exceedingly unpredictable since they rely highly on ...
详细信息
Wind and solar energy are two popular forms of renewable energy used in microgrids and facilitating the transition towards net-zero carbon emissions by ***,they are exceedingly unpredictable since they rely highly on weather and atmospheric *** microgrids,smart energy management systems,such as integrated demand response programs,are permanently established on a step-ahead basis,which means that accu-rate forecasting of wind speed and solar irradiance intervals is becoming increasingly crucial to the optimal operation and planning of *** this in mind,a novel“bidirectional long short-term memory network”(Bi-LSTM)-based,deepstacked,sequence-to-sequence autoencoder(S2SAE)forecasting model for predicting short-term solar irradiation and wind speed was developed and evaluated in *** create a deepstacked S2SAE prediction model,a deep Bi-LSTM-based encoder and decoder are stacked on top of one another to reduce the dimension of the input sequence,extract its features,and then reconstruct it to produce the *** of the proposed deepstacked S2SAE forecasting model were optimized using the Bayesian optimization ***,the forecasting performance of the proposed Bi-LSTM-based deepstacked S2SAE model was compared to three other deep,and shallow stacked S2SAEs,i.e.,the LSTM-based deepstacked S2SAE model,gated recurrent unit-based deepstacked S2SAE model,and Bi-LSTM-based shallow stacked S2SAE *** these models were also optimized and modeled in *** results simulated based on actual data confirmed that the proposed model outperformed the alternatives by achieving an accuracy of up to 99.7%,which evidenced the high reliability of the proposed forecasting.
Intrusion detection systems (IDS) are extensively employed for detecting suspicious behaviors in hosts. The ability of distributed IDS solutions makes it viable to combine and handle various kinds of sensors and gener...
详细信息
Intrusion detection systems (IDS) are extensively employed for detecting suspicious behaviors in hosts. The ability of distributed IDS solutions makes it viable to combine and handle various kinds of sensors and generate alerts to different hosts positioned in distributed platforms. However, to offer secure and feasible services in a cloud platform is an imperative issue due to the impacts of attacks. This paper devises a novel IDS framework using cloud data to counter the influence of attacks. Here, the spark architecture is employed for discovering the intrusions. The pre-processing is applied to the input data for removing artifacts and noise considering input data. Thereafter, the feature extraction and feature fusion are performed in slave nodes. The feature fusion is carried out with the proposed Exponential Squirrel Search Algorithm (ExpSSA) algorithm. The fused features are considered in a deep-stackedautoencoder (deep SAE) for performing effective intrusion detection. The proposed ExpSSA is adapted to train deep SAE for tuning optimum weights. The exponential weighted moving average (EWMA) and squirrel search algorithm (SSA) are combined to create the proposed ExpSSA. The proposed ExpSSA-based deep SAE offered improved performance compared to other techniques with the highest accuracy, detection rate of 0.846, and minimal FPR.
暂无评论