The expansion of web applications like e-commerce and other services yields an exponential increase in offers and choices in the web. From these needs, the recommender system applications have arisen. This research proposed a recommender system that uses user's reviews as implicit feedback to extract user preferences from their reviews to enhance personalization in addition to the explicit ratings. Diversity also improved by using k-furthest neighbor algorithm upon user's clusters. The system tested using Douban movie standard dataset from Kaggle, and show good performance. 

In this paper, we use concepts and results from percolation theory to investigate and characterize the effects of multi-channels on the connectivity of Dynamic Spectrum Access networks. In particular, we focus on the scenario where the secondary nodes have plenty of vacant channels to choose from-a phenomenon which we define as channel abundance. To cope with the existence of multi-channels, we use two types of rendezvous protocols: naive ones which do not guarantee a common channel and advanced ones which do. We show that, with more channel abundance, even with the use of either type of rendezvous protocol, it becomes difficult for two nodes to agree on a common channel, thereby potentially remaining invisible to each other. We model this

Anomaly detection is still a difficult task. To address this problem, we propose to strengthen DBSCAN algorithm for the data by converting all data to the graph concept frame (CFG). As is well known that the work DBSCAN method used to compile the data set belong to the same species in a while it will be considered in the external behavior of the cluster as a noise or anomalies. It can detect anomalies by DBSCAN algorithm can detect abnormal points that are far from certain set threshold (extremism). However, the abnormalities are not those cases, abnormal and unusual or far from a specific group, There is a type of data that is do not happen repeatedly, but are considered abnormal for the group of known. The analysis showed DBSCAN using the

Modern civilization increasingly relies on sustainable and eco-friendly data centers as the core hubs of intelligent computing. However, these data centers, while vital, also face heightened vulnerability to hacking due to their role as the convergence points of numerous network connection nodes. Recognizing and addressing this vulnerability, particularly within the confines of green data centers, is a pressing concern. This paper proposes a novel approach to mitigate this threat by leveraging swarm intelligence techniques to detect prospective and hidden compromised devices within the data center environment. The core objective is to ensure sustainable intelligent computing through a colony strategy. The research primarily focusses on the

     Theoretically, an eight-term chaos system is presented. The effect of changing the initial conditions values on behavior Chen system was studied. The basic dynamical properties of system are analyzed like time series, attractor, FFT spectrum, and bifurcation. Where the system appears steady state behavior at initial condition x_{i ,} y_i , z_i equal (0, 0, 0) respectively and it convert to quasi-chaotic at x_i ,y_i ,z_i  equal (-0.1, 0.5,-0.6). Finally, the system become hyper chaotic at x_i ,y_i ,z_i equal(-0.5, 0.5,-0.6 ) that can used it in many applications like secure communication.

For several applications, it is very important to have an edge detection technique matching human visual contour perception and less sensitive to noise. The edge detection algorithm describes in this paper based on the results obtained by Maximum a posteriori (MAP) and Maximum Entropy (ME) deblurring algorithms. The technique makes a trade-off between sharpening and smoothing the noisy image. One of the advantages of the described algorithm is less sensitive to noise than that given by Marr and Geuen techniques that considered to be the best edge detection algorithms in terms of matching human visual contour perception.