No abstract

Abstract. In Wireless Local Area Networks (WLAN), beacon, probe request and response messages are unprotected, so the information is visible to sniffers. Probe requests can be sent by anyone with a legitimate Media Access Control (MAC) address, as association to the network is not required at this stage. Legitimate MAC addresses can be easily spoofed to bypass Access Point (AP) access lists. Attackers take advantage of these vulnerabilities and send a flood of probe request frames which can lead to a Denial-of-Service (DoS) to legitimate stations. This paper discusses an intelligent approach to recognise probe request attacks in WLANs. The research investigates and analyses WLAN traffic captured on a home wireless network, and uses supervised feedforward neural network with 4 input neurons, 2 hidden layers and an output neuron to determine the results. The computer simulation results demonstrate that this approach improves detection of MAC spoofing and probe request attacks considerably.

No abstract

This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and education use, including for instruction at the authors institution and sharing with colleagues.Other uses, including reproduction and distribution, or selling or licensing copies, or posting to personal, institutional or third party websites are prohibited. a b s t r a c tAbout 15% of all proteins in a genome contain a signal peptide (SP) sequence, at the N-terminus, that targets the protein to intracellular secretory pathways. Once the protein is targeted correctly in the cell, the SP is cleaved, releasing the mature protein. Accurate prediction of the presence of these short aminoacid SP chains is crucial for modelling the topology of membrane proteins, since SP sequences can be confused with transmembrane domains due to similar composition of hydrophobic amino acids. This paper presents a cascaded Support Vector Machine (SVM)-Neural Network (NN) classification methodology for SP discrimination and cleavage site identification. The proposed method utilises a dual phase classification approach using SVM as a primary classifier to discriminate SP sequences from Non-SP. The methodology further employs NNs to predict the most suitable cleavage site candidates. In phase one, a SVM classification utilises hydrophobic propensities as a primary feature vector extraction using symmetric sliding window amino-acid sequence analysis for discrimination of SP and Non-SP. In phase two, a NN classification uses asymmetric sliding window sequence analysis for prediction of cleavage site identification.The proposed SVM-NN method was tested using Uni-Prot non-redundant datasets of eukaryotic and prokaryotic proteins with SP and Non-SP N-termini. Computer simulation results demonstrate an overall accuracy of 0.90 for SP and Non-SP discrimination based on Matthews Correlation Coefficient (MCC) tests using SVM. For SP cleavage site prediction, the overall accuracy is 91.5% based on cross-validation tests using the novel SVM-NN model.

End-to-end learning for autonomous driving uses a convolutional neural network (CNN) to predict the steering angle from a raw image input. Most of the solutions available for end-to-end autonomous driving are computationally too expensive, which increases the inference of autonomous driving in real time. Therefore, in this paper, CNN architecture has been trained which is lightweight and achieves comparable results to Nvidia’s PilotNet. The data used to train and evaluate the network is collected from the Car Learning to Act (CARLA) simulator. To evaluate the proposed architecture, the MSE (mean squared error) is used as the performance metric. Results of the experiment shows that the proposed model is 4x lighter than Nvidia’s PilotNet in term of parameters but still attains comparable results to PilotNet. The proposed model has achieved 5.1 × 10 − 4 MSE on testing data while PilotNet MSE was 4.7 × 10 − 4 .