The Institute of Engineering and Technology, Lucknow (IET, Lucknow) is a state government-funded technical institute in Lucknow, Uttar Pradesh, India. It is a constituent college of Dr. A.P.J. Abdul Kalam Technical University (erstwhile Uttar Pradesh Technical University). It is popularly known as " Engineering College" in Lucknow. Students for the undergraduate program are admitted through UPSEE exam on the basis of rank obtained by the candidate in this examination. At present this examination is conducted by AKTU. Around 2,00,000 students appear in this examination every year seeking admission to more than 800 engineering colleges affiliated to AKTU. A.P.J.
Deep learning models are widely adopted in many areas due to their remarkable success in solving different challenging tasks. Despite their great success, adversarial attacks in deep learning manipulate the input, leading to inaccurate predictions. Nowadays, various methods are used to perform formal verification on deep learning. However, these techniques suffer from poor robustness and often suffer from misclassifications in the perturbation bound. In this paper, the deep stacked Autoencoder_Taylor weighted binary softmax (DSA_TaylorWBS) is introduced for adversarial robust learning with abstract interpretation in federated learning framework. The federated learning process is executed in different entities, like node and aggregation server, where the local training is executed in the local data. In training model, the adversarial attack against a network intrusion detection system (NIDS) model is taken under consideration. The input network traffic data is normalized at first, and then augmented using borderline synthetic minority oversampling technique (SMOTE). Following this, the relevant features are selected and the data is finally classified with abstract interpretation using DSA_TaylorWBS. Thereafter, local updation and aggregation are done at the server concerning trust parameters. Further, the DSA_TaylorWBS attained mean square error (MSE) of 0.159, true positive rate (TPR) of 98.888
The information sharing on behalf of the delivery of the packet in the network router and the original information that is share to the correct person is enabled for the analysis and then the analysis is done. The traffic related problem based on the sharing the information is occur when two or more sis sent in the same routing path. So the packet or the information has been sent using the single router or an execution time delivery for the analysis. The method of novel QoS Routing, fault tolerance is used in this study for the analysis of the system to produce the formation and the analysis of the packet routing. Fault tolerance is used in the deliver the packets without fail and to deliver it in the fast manner. The QoS is used for managing the information or the packets which makes and send the data which is the high priority of the data and the analysis of the dependency is analysed. The finding of the CRAFT related protocol and the efficient routing has been found. Routing system the effective method for the analysis and the protocol transfer has been enabled using the CRAFT method. The suggested system explains the algorithms for enhancing fault detection, fault isolation, data redundancy, robustness against coalescing innovative QoS routing, and fault tolerance improving QoS parameters in the ad-hoc wireless network utilising CRAFT protocol. Compared to the early existing system, fault detection is now three times better. The execution time is 96% faster, and the decreased latency is less than 2 ms. The data redundancy rate is likely about 90% when restricted to the current services, which have improved in terms of resilience by 93%, jitter by 7%, and packet arrival time by over 50 ms per transmission.
Recently, with the meteoric evolution in the wireless communication technologies, countless real world applications which will reshape the way of seeking in robotic exploration, commercial, military, battle-field surveillance, border control and health-related areas. Due to its open nature, the network is easily prone to DoS attacks and can have significant influence on the behavior of Wireless Sensor Networks (WSN). Because of node energy capability the node verification using crypto analysis is a difficult one. In this paper, use of spatial information is used to detect and localize the multiple adversaries in both same and different node identity. This paper describes the scalable and energy efficient cluster based anomaly detection (SEECAD) mechanism to identify DoS attacks without the key management schemes to increase the lifetime of the network. Detection rate, false positive rate, packet delivery ratio, overhead, energy consumption and average delay of packets are various types of network parameters by which the performance can be measured. The result shows that the hit rate is achieved and high reliability in detecting and localizing multiple adversaries than previous systems is also achieved.
Knowing the lateral load-carrying capacity of a pile is essential to assess its ability to resist static and dynamic horizontal forces, usually verified through an in-situ load test. Using actual field soil stratification and laboratory-tested soil properties to attain a permissible deflection of 5 mm, this paper aims to validate the lateral deflection at the pile top against the calculated lateral load capacity of a 1000-mm diameter, 25-m-long free-head cast-in-situ pile of M35 grade concrete in cohesionless soil. Real in-situ load-deflection results from a lateral pile load test, conducted according to the current Indian Standard code of practice, are compared with those from the finite difference method-based Ensoft L-Pile software and the finite element method-based PLAXIS 3D software in reference to its MC, HS, and HSS models.
The present study explores a polynomial chaos expansion (PCE) based adaptive metamodeling approach for reliability analyses using sparse PCE models from a pool of sparse regressors. In detail, each sparse PCE model predicts the model response from the candidate set, and a reduced subset is obtained using multiple sparse PCE model predictions. The local error is estimated using the variance of the predictions. Unlike adding important training data iteratively from the entire input space in the usual active learning approach, the present study adds data points during iteration from a moving reduced space. The reduced space enforces the learning function to select a point near the predicted limit state surface with the highest discordance among the different regressors. This makes the learning highly focused on choosing adaptive samples on the local region near the predicted limit state surface, leading to faster convergence for reliability estimates. The reliability results obtained by the proposed approach are compared with those obtained by the bootstrap resampling-based PCE Monte Carlo simulation (MCS) approach and PCE with active Kriging approach, considering the direct MCS-based results as the benchmark to demonstrate the effectiveness of the present approach.
