CPU load prediction using neuro-fuzzy and Bayesian inferences

Ensuring adequate use of the computing resources for highly fluctuating availability in multi-user computational environments requires effective prediction models, which play a key role in achieving application performance for large-scale distributed applications. Predicting the processor availability for scheduling a new process or task in a distributed environment is a basic problem that arises in many important contexts. The present paper aims at developing a model for single-step-ahead CPU load prediction that can be used to predict the future CPU load in a dynamic environment. Our prediction model is based on the control of multiple Local Adaptive Network-based Fuzzy Inference Systems Predictors (LAPs) via the Naïve Bayesian Network inference between clusters states of CPU load time points obtained by the C-means clustering process. Experimental results show that our model performs better and has less overhead than other approaches reported in the literature.     

3HA: Hybrid Hole Healing Algorithm in a Wireless Sensor Networks

In wireless sensor networks (WSNs), the appearance of coverage holes over a large target field is mostly possible. Those holes reduce network performance and may affect the network efficiency. Several approaches were proposed to heal coverage holes in WSNs, but they still suffer from some weaknesses. In this paper we suggest a distributed algorithm, named hybrid hole healing algorithm (3HA), to find the minimum effective patching positions to deploy additional nodes to cover the holes. A hole manager node of each hole is responsible for operating the 3HA algorithm which requires two phases. The first phase finds all candidate patching positions using a Voronoi diagram. It takes all Voronoi vertices within the hole as the initial patching positions list. The second phase reduces as much as possible this list based on integer linear programming and on a probabilistic sensor model. The 3HA algorithm repeats the above phases in rounds, until all Voronoi vertices are covered. Simulation results show that our solution offers a high coverage ratio for various forms and sizes of holes and reduces the number of additional sensors when compared to some algorithms like the Perimeter-based, the Delaunay triangulation-based, the Voronoi-based, and the Trees-based coverage hole healing methods.

     

Correction to: SPMI: Single Phase Multiple Initiator Protocol for Coverage in Wireless Sensor Networks

One of the complex problems nowadays in communication systems is the lack of frequency spectrum. To solve this problem, cognitive radio is considered the best candidate that can opportunistically exploit the spectrum. The periodogram based spectrum sensing technique can be used to detect the spectrum in cognitive radio. It is a useful technique since does not need to prior information about the primary signal. In this paper, a new periodogram is presented using the Discrete Cosine Transform (DCT). Results are analyzed and compared with the current raw periodogram. It is observed that the DCT periodogram outperforms the raw technique in terms of probabilities of false alarm and detection, variance, and complexity. In addition, the lowest power of DCT coefficients can be removed without compromising the sensing performance. The proposed system shows high probability of detection with low probability of false alarm even in the case of low Signal-to-Noise Ratio (SNR).     

Fingerprint matching from minutiae texture maps

The fingerprint matching using the original FingerCode generation has proved its effectiveness but it suffers from some limitations such as the reference point localization and the recourse to the relative fingerprint pre-alignment stage. In this paper, we propose a new hybrid fingerprint matching technique based on minutiae texture maps according to their orientations. Therefore, rather than exploiting the eight fixed directions of Gabor filters for all original fingerprint images filtering process, we construct absolute images starting from the minutiae localizations and orientations to generate our weighting oriented Minutiae Codes. The extracted features are invariant to translation and rotation, which allows us avoiding the fingerprint pair relative alignment stage. Results are presented demonstrating significant improvements in fingerprint matching accuracy through public fingerprint databases.     

Password hardened fuzzy vault for fingerprint authentication system

The present work attempts to build a bio-cryptographic system that combines transformed minutiae pairwise feature and user-generated password fuzzy vault. The fingerprint fuzzy vault is based on a new minutiae pairwise structure, which overcomes the fingerprint feature publication while the secret binary vault code is generated according to the fingerprint fuzzy vault result. The authentication process involves two stages: fuzzy vault matching and secret vault code validation. Our minutiae pairwise transformation produces different templates thus resolving the problem of cross matching attacks in fingerprint fuzzy vault. So, the original fingerprint template cannot be recreated because it is protected by the key generated from the user password. In addition, the proposed bio-cryptographic system ensures an acceptable security level for user authentication.     

DoS-DDoS: TAXONOMIES OF ATTACKS,COUNTERMEASURES, AND WELL-KNOWN DEFENSE MECHANISMS IN CLOUD ENVIRONMENT

Cloud computing has become a suitable provider of services for organizations as well as individuals through the Internet. Generally, these services become unavailable because of Denial of Service (DoS) and Distributed Denial of Service (DDoS) attacks that can deny the legitimate users access to the service delivered by cloud. Taxonomy is an important opportunity for researchers and cloud service providers. Therefore, it provides researchers with a general view about some contributions to understand and ameliorate their limitations and helps cloud service providers to select the best defense strategy to protect their cloud service against DoS and DDoS attacks. In this article, we present taxonomies of DoS and DDoS attacks in cloud environment, countermeasures, and highlight their solutions with another taxonomy of well-known defense mechanisms.     

Efficient deterministic method for detecting new U2R attacks

The purpose of this study is to describe an efficient deterministic intrusion detection approach that detects both old and new attacks. We especially focused on detecting the user to root (U2R) attacks of the 1999 DARPA evaluation dataset. The main idea of our approach is to test if an unknown behavior is close enough to a known behavior (attack or normal) such as we can conclude that it belongs to its class. To achieve that, we formulate the problem of intrusion detection as a linear programming system (LPS). The objective function of this LPS leads to minimize the distance between an unknown behavior and one of the known behaviors, by respect of some constraints. The solution of such a problem is a set of bivalent variables x_ij. If (x_ij = 1) then we can conclude that the unknown behavior i belong to the class of behaviors j. Our experiments demonstrated the efficiency of our approach.