The extensive use of distributed vehicle platoon controllers has resulted in several benefits for transportation systems, such as increased traffic flow, fuel efficiency, and decreased pollution. The rising reliance on interconnected systems and communication networks, on the other hand, exposes these controllers to potential cyber-attacks, which may compromise their safety and functionality. This thesis aims to improve the security of distributed vehicle platoon controllers by investigating attack scenarios and assessing their influence on system performance. Various attack techniques, including man-in-the-middle (MITM) and false data injection (FDI), are simulated using Model Predictive Control (MPC) controller to identify vulnerabilities and weaknesses of the platoon controller. Countermeasures are offered and tested, that includes attack analysis and reinforced communication protocols using Machine Learning techniques for detection. The findings emphasize the significance of integrating security issues into their design and implementation, which helps to construct safe and resilient distributed platoon controllers.

In this article, a new solution for the convex hull problem has been presented. The convex hull is a widely known problem in computational geometry. As nature is a rich source of ideas in the field of algorithms, the solution has been inspired by nature. A tight elastic band is modeled using agents and also nails as points of the problem. By simulating an elastic band with nails in an environment, solving the convex hull problem will be possible. The algorithm runs in O(t) in which t is the time that an elastic band will get fixed.

Real-world data is messy and usually holds a lot of missing values. Missing data can skew anything for data scientists and, A data scientist doesn't want to design biased estimates that point to invalid results. Behind, any analysis is only as great as the data. Missing data appear when no value is available in one or more variables of an individual. Due to Missing data, the statistical power of the analysis can reduce, which can impact the validity of the results.

It is rare that acquired data contains values for all features of all instances. Values can go missing for a number of reasons -- for example, through a faulty sensor, software bug, mapping issues from the source system or being left intentionally blank in a survey. To be able to use such a data set for model training, since machine learning algorithms require a value to work with, a quick and easy solution is to delete either the entire instances (rows) with missing values or delete the feature (column). However, doing so negatively impacts model training as deleting instances not only decreases the amount of training data, but also creates an imbalance in the example training data. In addition, removing features altogether affects the predictive power of the resulting model (Figure 1).

In this you will learn how to create and use a neural network to classify articles of clothing. To achieve this, we will use a sub module of TensorFlow called keras. Before we dive in and start discussing neural networks, I'd like to give a breif introduction to keras. "Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano. It was developed with a focus on enabling fast experimentation. Keras is a very powerful module that allows us to avoid having to build neural networks from scratch. It also hides a lot of mathematical complexity (that otherwise we would have to implement) inside of helpful packages, modules and methods. In this guide we will use keras to quickly develop neural networks. So, what are these magical things that have been beating chess grandmasters, driving cars, detecting cancer cells and winning video games? A deep neural network is a layered representation of data. The term "deep" refers to the ...

Code obfuscation aims at protecting Intellectual Property and other secrets embedded into software from being retrieved. Recent works leverage advances in artificial intelligence with the hope of getting blackbox deobfuscators completely immune to standard (whitebox) protection mechanisms. While promising, this new field of AI-based blackbox deobfuscation is still in its infancy. In this article we deepen the state of AI-based blackbox deobfuscation in three key directions: understand the current state-of-the-art, improve over it and design dedicated protection mechanisms. In particular, we define a novel generic framework for AI-based blackbox deobfuscation encompassing prior work and highlighting key components; we are the first to point out that the search space underlying code deobfuscation is too unstable for simulation-based methods (e.g., Monte Carlo Tres Search used in prior work) and advocate the use of robust methods such as S-metaheuritics; we propose the new optimized AI-based blackbox deobfuscator Xyntia which significantly outperforms prior work in terms of success rate (especially with small time budget) while being completely immune to the most recent anti-analysis code obfuscation methods; and finally we propose two novel protections against AI-based blackbox deobfuscation, allowing to counter Xyntia's powerful attacks.

Step 1: We will use the python package NumPy for working with a sample dataset and Matplotlib to plot various graphs for visualisation. Step 2: Let us consider a simple scenario where a single input /independent variable controls the outcome/dependent variable value. In the code below, we have declared two NumPy arrays to hold the values of the independent and dependent variables. Step 3: Let us quickly draw a scatter plot to understand the data points. Our goal is to formulate a linear equation which can predict the dependent variable value with minimum error for an independent/input variable.

Privacy is a term used to describe an individual's anonymity and how safe they feel in a location preferably in Internet, which is one of the most sensitive and concerned'concept' at present. In the current situation crowd sourcing is the most popular source of collecting data directly from people for many research topics. Generally it is being done through several online site or portal in Internet. But there are some basic issues regarding the whole survey process, like (a) the system of survey should be convincing enough to gain the participants trust,(b) the processes after the survey should be effective enough to ensure the'truthfulness' of the participants to the researchers, (c) The processes of research should be robust enough to guarantee the leak proof of the research architecture model, (d) The system of survey should still produce a'good result' in terms of gaining an insight of the problem in spite of the'noise' in the data. Therefore it promises a large research field in case of statistical databases where a leak of small amount of data may lead to a personal identification which might be a concern for that person in his or her personal life .

We show how to adjust the coefficient of determination ($R^2$) when used for measuring predictive accuracy via leave-one-out cross-validation.