The activity recognition gained immense popularity due to increasing number of surveillance cameras. The purpose of activity recognition is to detect the actions from the series of examination by varying the environme...
详细信息
The activity recognition gained immense popularity due to increasing number of surveillance cameras. The purpose of activity recognition is to detect the actions from the series of examination by varying the environmental condition. In this paper, Chaotic Whale Atom Search Optimisation (CWASO)-based deep stacked autoencoder (CWASO-deep SAE) is proposed for crowd behaviour recognition. The key frames are subjected to the descriptor of feature to extort the features, which bring out the classifier input vector. In this model, the statistical features, optical flow features and visual features are conducted to extract important features. Furthermore, the significant features are shown in the deepstacked auto-encoder (deep SAE) for activity recognition, as the guidance of deep SAE is performed byCWASO, that is planned is designed by adjoining Atom search optimisation (ASO) algorithm and Chaotic Whale optimisation algorithm (CWOA). The proposed systems' performance is analysed using two datasets. By considering the training data, the projected method attains performance that is high for dataset-1 with maximum precision, sensitivity, and with specific value of 96.826%, 96.790%, and 99.395%, respectively. Similarly, by considering the K-Fold, this method attains the maximum precision of 96.897%, sensitivity of 96.885%, and with specific values of 97.245% for the dataset-1.
Ransomware is a kind of malevolent program software that encrypts the items on the hard disc and prevents the clients from accessing them until they are paid a ransom. Associations like monetary establishments and med...
详细信息
Ransomware is a kind of malevolent program software that encrypts the items on the hard disc and prevents the clients from accessing them until they are paid a ransom. Associations like monetary establishments and medical care areas (i.e., smart medical care) are mostly targeted by ransomware attacks. Ransomware assaults are crucial holes still in blockchain technology and prevent effective data communication in networks. This study aims to introduce an efficient system, named M-Net-based stackedautoencoder (M-Net_SA) for ransomware detection using blockchain data. Initially, the input data is taken from a dataset and then sent to the feature extraction process, which utilizes sequence-based statistical features. After that, data transformation is completed using the Yeo-Johnson transformation to transform the data into a usable format. After that, feature fusion is executed using a deep Q-network (DQN) with Lorentzian similarity to enhance the representativeness of the target features. Finally, ransomware detection is accomplished by the proposed M-Net_SA, which is the integration of MobileNet and deep stacked autoencoder (DSAE). The experimental validation of the proposed M-Net_SA is compared with other conventional techniques and the proposed model attained maximum accuracy, sensitivity, and specificity of 0.959, 0.967, and 0.957 respectively.
Due to the large volume of computational and storage requirements of content based image retrieval (CBIR), outsourcing image to cloud providers become an attractive research. Even though, the cloud service provides ef...
详细信息
Due to the large volume of computational and storage requirements of content based image retrieval (CBIR), outsourcing image to cloud providers become an attractive research. Even though, the cloud service provides efficient indexing of the condensed images, it remains a major issue in the process of incremental indexing. Hence, an effective incremental indexing mechanism named Black Hole Entropic Fuzzy Clustering +deepstacked incremental indexing (BHEFC+deepstacked incremental indexing) is proposed in this paper to perform incremental indexing through the retrieval of images. The images are encrypted and stored in cloud server for ensuring the security of image retrieval process. The trained images are clustered using the clustering mechanism BHEFC based on Tversky index. With the incremental indexing process, the new training images are encrypted and are converted into the decimal form such that the weight is computed using deepstacked auto-encoder that enable to update the centroid with new score values. The experimental evaluations on benchmark datasets shows that the proposed BHEFC+deepstacked incremental indexing model achieves better results compared to the existing methods by obtaining maximum accuracy of 96.728%, maximum F-measure of 83.598%, maximum precision of 84.447%, and maximum recall of 94.817%, respectively.
Sensor nodes in Wireless sensor network (WSN) are distributed over a large area for sensing the pressure, temperature, humidity, and so on. They are at risk due to several attacks. In an attack like a black hole, the ...
详细信息
Sensor nodes in Wireless sensor network (WSN) are distributed over a large area for sensing the pressure, temperature, humidity, and so on. They are at risk due to several attacks. In an attack like a black hole, the malicious node captures the whole data without any consideration of the active route, thus the source node are secured for communication. Hence, a new method name, Taylor SailFish Optimizer (TaylorSFO) is proposed to predict blackhole attacks in WSN. The training of the deep stacked autoencoder is done through proposed Taylor-SFO, which is the integration of Taylor Series, and SailFish Optimizer (SFO). The newly developed Taylor-SFO is then applied for routing and blackhole attack detection at the WSN base station. Overall, two phases are included in the proposed model, which involves routing and blackhole attack detection at the base station. Initially, the WSN nodes are given to the routing module. Here, the routing is done based on the proposed TaylorSFO. Energy, distance as well as delay are the three fitness parameters considered for the routing. The proposed method shows the lowest delay of 21.23 ms, minimal FNR of 0.083, minimal FPR of 0.134, highest PDR of 94.87%, the highest throughput rate of 119.98 kbps, respectively.
Recognition of emotions using facial expression is an active research topic in the field of computer vision. In this paper, a novel feature descriptor proposed for facial expression recognition using modified Histogra...
详细信息
Recognition of emotions using facial expression is an active research topic in the field of computer vision. In this paper, a novel feature descriptor proposed for facial expression recognition using modified Histogram of Oriented Gradients (HOG) and Local Binary Pattern (LBP) feature descriptor. Firstly, viola-Jones face detection used to detect the face region, Then, Butterworth high pass filter utilized to enhance the detected region to find the eye, nose and mouth region detection using Viola-Jones approach. Secondly, the proposed modified HOG and LBP feature descriptor are used to extract the features of the detected eye, nose and mouth regions. The extracted features of these three regions are concatenated and reduced its dimensionality using deep stacked autoencoders. Finally, multi-class Support Vector Machine is used for classification and recognition. Experimental results show that the proposed modified feature descriptors can effectively recognize emotions on CK+ dataset and JAFFE dataset.
With the significant increase in integration of renewable energy generation into the electric grid, market-based transactive exchanges between energy producers and prosumers will become more common. Transactive energy...
详细信息
With the significant increase in integration of renewable energy generation into the electric grid, market-based transactive exchanges between energy producers and prosumers will become more common. Transactive energy systems (TESs) employ economic and control mechanisms to dynamically balance the demand and supply across the electrical grid. Emerging transactive control mechanism depends on a large number of distributed edge-computing and Internet of Things (IoT) devices making autonomous/semi-autonomous decisions on energy production, and demand response. However, the electric grid cyber assets and the IoT devices are increasingly vulnerable to attack. TES will likely have similar vulnerabilities and cyber attacks especially with financial interest motives of stakeholders, which could affect the operation of the power grid. Therefore, new analytical methods are needed to continuously monitor these systems operations and detect malicious activity. In this research work, various components of transactive energy systems are modeled and simulated in detail. Various cyber attack models are developed based on threats identified in TES. A deep learning approach called deep stacked autoencoder (SAE) is utilized to detect possible anomalies in the market and physical system measurements. The proposed unsupervised technique is validated for satisfactory performance to detect anomalies and trigger a further investigation for root cause analysis using end-to-end TES testbed and use case.
The goal is an improvement on learning of deep neural networks. This improvement is here called the CollabNet network, which consists of a new method of insertion of new layers hidden in deep feedforward neural networ...
详细信息
ISBN:
(纸本)9789897583506
The goal is an improvement on learning of deep neural networks. This improvement is here called the CollabNet network, which consists of a new method of insertion of new layers hidden in deep feedforward neural networks, changing the traditional way of stacking autoencoders. The new form of insertion is considered collaborative and seeks to improve the training against approaches based on stackedautoencoders. In this new approach, the addition of a new layer is carried out in a coordinated and gradual way, keeping under the control of the designer the influence of this new layer in training and no longer in a random and stochastic way as in the traditional stacking. The collaboration proposed in this work consists of making the learning of newly inserted layer continuing the learning obtained from previous layers, without prejudice to the global learning of the network. In this way, the freshly added layer collaborates with the previous layers and the set works in a way more aligned to the learning. CollabNet has been tested in the Wisconsin Breast Cancer Dataset database, obtaining a satisfactory and promising result.
暂无评论