The current streaming platform era requires precise high-quality movie recommendations to boost user satisfaction and platform engagement. Traditional filtering which utilizes word search year of production, number of views, or movie rating may not provide best user experience. Thus, in this research we introduce a Movie Quality Recommendation System which uses machine learning methods to suggest movies and forecast their quality through analysis of genre and popularity alongside ratings and textual descriptions. Our system uses content-based filtering and collaborative filtering and hybrid recommendation models together with regression-based quality prediction to deliver precise personalized movie suggestions. The architecture adopts a network-based perspective through modeling user–item interactions and content similarities as interconnected graphs which enables structured reasoning across relationships. The system shows how machine learning enhances movie recommendation systems through its implementation of Python and Flask together with Scikit-learn and TensorFlow.

Operations sampling inspections, manual verification, user applications and other labor-intensive methods are commonly used for energy meter error analysis in the power industry. Accurate fault detection in electric energy meters is crucial for achieving reliable measurements. The fundamental issue with on-site testing of electrical energy metering equipment is the characteristics of electric power meters under dynamic settings. This research develops a deep learning-assisted prediction model (DLPM) to address the problem of inaccurate energy power meters. Electricity is measured precisely and the meters can pinpoint the most consequential deviations between the predicted and actual trajectories. The results of this research point to the widespread adoption of a consistent and autonomous method for analyzing discrepancies in energy meters. Compared to the traditional way, this technology considerably improves the electric intelligent meter deviance computation, providing exact data assistance for analysis and diagnostics of the source of the electric smart meter abnormality. The simulation results show that the suggested DLPM model has better prediction accuracy (99.2%), performance (97.8%), efficiency (98.9%), average consumption (10.3%) and root mean square error (11.2%) than the state-of-the-art.

This study applies the Levanon-Mozeson MATLAB code to evaluate the ambiguity function (AF) across a diverse array of radar signals, presenting detailed three-dimensional visualizations under various operational parameters such as amplitude, phase, signal period, and propagation delays. Through systematic testing, the interaction of each signal with the AF was quantitatively assessed. Notably, the Costas signal exhibited the most distinctive pattern, characterized by a nearly flat Doppler response throughout the entire 3D plot, with zero-cut Doppler values significantly flattened compared to other signals. In contrast, pulse train signals consistently showed substantial decorrelation, indicating lower consistency with the AF. This empirical analysis revealed that the Costas signal maintained a high degree of clarity in the AF, with minimal variance at the zero-cut points, while other tested signals such as the Barker 13 and Frank 16 exhibited varied AF profiles, with Barker codes achieving a maximum Doppler spread of ±60 Hz and Frank codes showing notable phase stability across different sampling rates. These insights provide valuable implications for enhancing radar signal processing, bridging theoretical constructs with real-world signal behavior to advance the functionality of radar systems.

In the current digital age, the volume of data generated by various cyber activities has become enormous and is constantly increasing. The data may contain valuable insights that can be harnessed to improve cyber security measures. However, much of this data is unclassified and qualitative, which poses significant challenges to traditional analysis methods. In order to over- come these challenges, clustering, a crucial method in machine learning (ML) and data analysis, has become increasingly effective. Clustering facilitates the identification of hidden patterns and structures in data through grouping sim- ilar data points, which makes it simpler to identify and address threats. Clus- tering can be defined as a data mining (DM) approach, which uses similarity calculations for dividing a data set into several categories. Each data cluster that the clustering algorithm has identified has a high degree of similarity, and there is a fair amount of similarity between other clusters of data. Hierar- chical, density-based, along with partitioning clustering algorithms are typi- cal. The presented work use K-means algorithm, which is a popular clustering technique. Utilizing K-means algorithm, we worked with two different types of data: first, we gathered data with the use of XG-boost algorithm fol- lowing completing the aggregation with K-means algorithm. Data was gath- ered utilizing Kali Linux environment, cicflowmeter traffic, and Putty Soft- ware tools with the use of diverse and simple attacks. The concept could assist in identifying new attack types, which are distinct from the known attacks, and labeling them based on the characteristics they will exhibit, as the dy- namic nature regarding cyber threats means that new attack types of- ten emerge, for which labeled data might not yet exist. The model counted the attacks and assigned numbers to each one of them. Secondly, We tried the same work on the ready data inside the Kaggle repository called (Intrusion Detection in Internet of Things Network), and the clustering model worked well and detected the number of attacks correctly as shown in the results sec- tion.

Cloud computing has made internet communication and data sharing easier and more flexible since the user can access stored data from any place and manage applications on different platforms, without having to worry about hardware failure or maintenance. A Cloud Service provider (CSP) should ensure the security of data transactions and verify logged-on users to encourage people to adopt cloud computing services without worrying about their confidential data. Several approaches were developed to ensure the security of the data itself and the security of data transactions.The proposed system in this research is concerned with cases where the cookie file that contains users’ credentials gets hijacked, and the hacker gets unauthorized access to users’ data. The proposed system employs encryption of the user’s device's MAC address with other attributes using the famous and reliable RSA encryption technique. Testing the system shows that hijacking the cookie file would be useless to the hacker under this technique, and no authorization is granted.