Network attacks (i.e., man-in-the-middle (MTM) and denial of service (DoS) attacks) allow several attackers to obtain and steal important data from physical connected devices in any network. This research used several machine learning algorithms to prevent these attacks and protect the devices by obtaining related datasets from the Kaggle website for MTM and DoS attacks. After obtaining the dataset, this research applied preprocessing techniques like fill the missing values, because this dataset contains a lot of null values. Then we used four machine learning algorithms to detect these attacks: random forest (RF), eXtreme gradient boosting (XGBoost), gradient boosting (GB), and decision tree (DT). To assess the performance of the algorithms, there are many classification metrics are used: precision, accuracy, recall, and f1-score. The research achieved the following results in both datasets: i) all algorithms can detect the MTM attack with the same performance, which is greater than 99% in all metrics; and ii) all algorithms can detect the DoS attack with the same performance, which is greater than 97% in all metrics. Results showed that these algorithms can detect MTM and DoS attacks very well, which is prompting us to use their effectiveness in protecting devices from these attacks.

Many applications, such as interactive data analysis and sign detection, can benefit from hand gesture recognition. We offer a low-cost approach based on human-computer interaction for predicting hand movements in real time. Our technique involves using a color glove to train a random forest classifier and then predicting a naked hand at the pixel level. Our algorithm anticipates all pixels at a rate of around 3 frames per second and is unaffected by differences in the surroundings. It's also been proven that HCI-based data augmentation is more effective than any other way for enhancing interactive data. In addition, the augmentation experiment was carried out on multiple subsets of the original hand skeleton sequence dataset, each with a different number of classes, as well as on the entire dataset. On practically all subsets, the proposed base architecture improved classification accuracy. When the entire dataset was used, there was even a modest improvement. Correct identification could be regarded as a quality indicator. The best accuracy score was 94.02 percent for the HCI-model with support vector machine (SVM) classifier.

No abstract

In the research, a software for ECG signal based on Chaos encryption based on C#-programmed and Kit of Microsoft Visual Studio Development was implemented. A chaos logic map (ChLMp ) and its initial value are utilized to create Level-1 ECG signal based on Chaos encryption bit streams. A ChLMp, an initial value, a ChLMp bifurcation parameter, and two encryption level parameters are utilized to create level-2 ECG signal based on Chaos encryption bit streams. The level-3 ECG signal based on Chaos encryption software utilizes two parameters for the level of encryption, a permutation mechanism, an initial value, a bifurcation parameter of the level of encryption, and a ChLMp. We assess 16-channel ECG signals with great resolution utilizing encryption software. The level-3 ECG signal based on Chaos encryption program has the slowest and most reliable encryption speed. The encryption effect is superior, according to test findings, and when the right decoding parameter is utilized, the ECG signals may be completely recovered. The high resolution 16-channel ECG signals (HRMCECG) won't be recovered if an invalid input parameter occurred, such as a 0.00001% initial point error, which will result in chaotic encryption bit streams.