Sort by
A robust Artificial Intelligence based Software Modelling Tool for automatically detecting and characterizing web attacks

Online applications are frequently vulnerable and network accessible over the internet. Web applications are appealing targets in the eyes of cyber attackers. The most frequent types of attacks that can disable online services include SQL injection, Cross-Site Scripting (XSS), Database Attacks, Dynamic Code Execution (DCE), and Remote Code Execution (RCE). These attacks can cause significant financial losses for service providers and clients. To understand the execution behaviour of a web application, these attacks should be tracked and automatically characterised. A new, robust Artificial Intelligence (AI) based Software Modelling Tool for automatically detecting and characterising web attacks is provided by the proposed work, which is described here. It uses Long Short-Term Memory (LSTM) to detect web attacks and includes record traces, datasets, sampling, training data, test data, LSTM models, threshold, and classification and model evaluation. The suggested study makes use of the Long Short-Term Memory (LSTM) Model to raise the Software Modeling Tool’s prediction accuracy. Support Vector Machine (SVM), Naive Bayes, and Autoencoder Deep Learning algorithms are examples of prior art that are contrasted with the principal implementations of the present invention. The Long Short-Term Memory (LSTM) Model transforms unlabeled data into deep learning features without the need for labelled input data during model training. The proposed work has a Fscore of 90.49%, Accuracy of 97.61%, Precision of 90%, Recall of 90.99%. The dataset utilised in the current disclosure has a total of 666 records, of which 532 records are used to train the AI-based Software Modelling Tool and 134 records to test it.

Open Access
Relevant
Analyzing Patient Motion and Brain Activity with Machine Learning and Internet of Things

Improvements in wireless technology have helped a variety of medical professions. There are a lot of places out there that use a pulse monitor, but all they do is record the information that comes out of it. But, it is not only difficult but also costly to acquire access to sophisticated medical gear. The suggested real-time heart rate monitoring system uses a web server and an Arduino microcontroller to link the heart rate to the internet, retrieve heart rate values, store them in a cloud service, and alert the treating physician. The filter bank that was developed by extrapolating heart rates from BBIs shows the extrapolated heart rates as zero crossings in the output signal. Before alerting medical personnel, an algorithm assesses the reliability of the observed heart rate in describing the patient’s condition. Extract BBIs are then used to derive HRV features. Once a threat has been recognised, a notification is sent to the appropriate expert as soon as possible. The patient’s movements are tracked using an infrared (IR) sensor linked to an Arduino microcontroller, and the controller or specialist is alerted to any abnormalities via a buzzer. The proposed framework is used by a variety of customers, not just the informed expert (User agreeable). By employing this method, you can expect precise, speedy, and cheap outcomes. This procedure will be utilised in the development of an Arduinobased Heart Rate Monitor System with a Heartbeat Sensor. By contrasting the results with those obtained by analysing an ECG signal with an oscilloscope and by manually calculating the heart rate, the show reveals a far more beneficial setup.

Open Access
Relevant
Object Detection for Signboard using Deep Neural Network

The goal of this work is to help the visually impaired by making it possible for them to recognize hidden images on signs, which will hopefully lead to fewer accidents. Although traffic signs are essential for maintaining order, they can also increase the risk of accidents if they are obstructed. Individuals who are visually impaired, such as the blind, can benefit greatly from this technique. Furthermore, the proposed system is conducive to the operation of autonomous cars, as the billboards can be read automatically and the vehicles may be directed by the proposed system. When a potentially dangerous image is received, a warning is displayed to the driver. Throughout this piece, ”input image” will refer to the footage recorded by a camera situated at the front of the car. After converting the image to grayscale, a resizing method is applied, and a filter is used to get rid of any noticeable noise that remains. In the end, feature extraction and feature reduction methods are used to priorities certain features over others. Hence, the DNN procedure is an integral aspect of the system, as it is used for both speech recognition and image recognition. This project’s main goal is to recognize incoming photos by comparing them to data sets stored in a database, with successful matches sounding an alarm for the driver.

Open Access
Relevant