Search

Educational systems have advanced with the use of electronic learning (e-learning), which is a promising solution for long-distance learners. Students who engage in e-learning can access tests and exams online, making education more flexible and accessible. This work reports on the design of an e-learning system that makes recommendations to students to improve their learning. This artificial intelligence-based student assessment and recommendation (AISAR) system consists of score estimation, clustering, performance prediction, and recommendation. In addition, the importance of student authentication is recognised in situations in which students must authenticate themselves prior to using the e-learning system using their identity, password, and personal identification number. Individual scores are determined using a recurrent neural network (RNN) based on student engagement and examination scores. Then, a density-based spatial clustering algorithm (DBSCAN) using Mahalanobis distance clustering is implemented to group students based on their obtained score values. The constructed clusters are validated by estimating purity and entropy. Student performance is predicted using a threshold-based MapReduce (TMR) procedure from the score-based cluster. When predicting student performance, students are classified into two groups: average and poor, with the former being divided into below- and above-average students and the latter into poor and very poor students. This categorisation aims to provide useful recommendations for learning. A recommendation reinforcement learning algorithm, the rule-based state–action–reward–state–action (R-SARSA) algorithm, is incorporated for evaluation. Students were required to work on their subjects according to the provided recommendations. This e-learning recommendation system achieves better performance in terms of true-positives, false-positives, true-negatives, false-negatives, precision, recall, and accuracy. [ABSTRACT FROM AUTHOR]

Fingerprinting is a process of identifying the remote network devices and services running on the devices, including operating systems (OS) of the devices, and hosts running different OSs. Several research proposals and commercial products are available in the market to defeat fingerprinting. However, they have performance limitations and expose themselves to attackers. In this paper, we utilize some real-time fault-tolerance concepts (viz. real-time/dynamic, detection/locating, confinement/localizing and masking/decoy) to propose a plug-and-play adaptive middleware architecture called Secure Dynamic Middleware (SDMw) with a view to defeat attackers fingerprinting the network, without exposing itself to the attackers. We verify that the proposed scheme works seamlessly and requires zero-configuration at the client side. [ABSTRACT FROM AUTHOR]

The graph centroids defined through a topological property of a graph called g-convexity found its application in various fields. They have classified under the "facility location" problem. However, the g-centroid location for an arbitrary graph is NP -hard. Thus, it is necessary to devise an approximation algorithm for general graphs and polynomial-time algorithms for some special classes of graphs. In this paper, we study the relationship between the g-centroids of composite graphs and their factors under various well-known graph operations such as graph Joins, Cartesian products, Prism, and the Corona. For the join of two graphs G 1 and G 2 , the weight sequence of the composite graph does not depend on the weight sequences of its factors; rather it depends on the incident pattern of the maximum cliques of G 1 and G 2 . We also characterize the structure of the g-centroid under various cases. For the Cartesian product of G 1 and G 2 and the prism of a graph, we establish the relationship between the g-centroid of a composite graph and its factors. Our results will facilitate the academic community to focus on the factor graphs while designing an approximate algorithm for a composite graph. [ABSTRACT FROM AUTHOR]

The Internet Protocol (IP) version 4 (IPv4) has several known vulnerabilities. One of the important vulnerabilities is that the protocol does not validate the correctness of the source address carried in an IP packet. Users with malicious intentions may take advantage of this vulnerability and launch various attacks against a target host or a network. These attacks are popularly known as IP Address Spoofing attacks. One of the classical IP-spoofing attacks that cost several million dollars worldwide is the DNS-amplification attack. Currently, the availability of solutions is limited, proprietary, expensive, and requires expertise. The Internet is subjected to several other forms of amplification attacks happening every day. Even though IP-Spoofing is one of the well-researched areas since 2005, there is no holistic solution available to solve this problem from the gross-root. Also, every solution assumes that the attackers are always from outside networks. In this paper, we provide an efficient and scalable solution to solve the IP-Spoofing problem that arises from malicious or compromised inside hosts. We use a modified form of Network Address Translation (NAT) to build our solution framework. We call our framework as NAT++. The proposed infrastructure is robust, crypto-free, and easy to implement. Our simulation results have shown that the proposed NAT++ infrastructure does not consume more than the resources required by a simple NAT. [ABSTRACT FROM AUTHOR]

Internet Protocol (IP) multicasting is a method for one-to-many and many-to-many communication between hosts in an IP network. This communication happens in a real-time synchronous fashion. It is a useful mechanism for distributing management data in a Local Area Network (LAN). Management data includes frequent updating of host Operating System (OS), security patches, OS update for network hardware, new configuration updates, etc. In the absence of any admission control or a source identification, any host with malicious intent can disseminate malicious codes or rootkits exploiting the underlying multicast framework. Routing protocols like RIPv2 and OSPF use a certain form of authentication to exchange routing information with their peer routers. However, their authentication and the distribution of routing information in its present form has several security and performance-related issues. Motivated through these problems, in this paper, we propose an efficient and scalable multicast architecture for distributing management and routing information in a LAN. We use Core-based Tree (CBT) for constructing the multicast delivery tree and the pseudo identity-based encryption of the underlying cryptosystem. We also demonstrate that our proposed multicast architecture is immune to a number of popular attacks. [ABSTRACT FROM AUTHOR]

The broadcast performance of the 802.11 wireless protocol depends on several factors. One of the important factor is the number of nodes simultaneously contending for the shared channel. The Medium Access Control (MAC) technique of 802.11 is called the Distributed Coordination Function (DCF). DCF is a Carrier Sense Multiple Access with Collision Avoidance (CSMA/CA) scheme with binary slotted exponential backoff. A collision is the result of two or more stations transmitting simultaneously. Given the simplicity of the DCF scheme, it was adapted for Dedicated Short Range Communication (DSRC) based vehicular communication. A broadcast mechanism is used to disseminate emergency and safety related messages in a vehicular network. Emergency and safety related messages have a strict end-to-end latency of 100 ms and a Packet Delivery Ratio (PDR) of 90% and above. The PDR can be evaluated through the packet loss probability. The packet loss probability P L is given by, P L = 1 − ( 1 − P e )( 1 − P C ), where P e is the probability of channel error and P C is the probability of collision. P e depends on several environmental and operating factors and thus cannot be improved. The only way to reduce P L is by reducing P C . Currently, expensive radio hardware are used to measure P L . Several adaptive algorithms are available to reduce P C . In this paper, we establish a closed relation between P C and the Stirling number of the second kind. Simulation results are presented and compared with the analytical model for accuracy. Our simulation results show an accuracy of 99.9% compared with the analytical model. Even on a smaller sample size, our simulation results show an accuracy of 95% and above. Based on our analytical model, vehicles can precisely estimate these real-time requirements with the least expensive hardware available. Also, once the distribution of P C and P L are known, one can precisely determine the distribution of P e . [ABSTRACT FROM AUTHOR]

Broadcasting is one of the essential features in the Internet Protocol Ver 4 (IPv4). Attackers often exploit this feature of the IP protocol to launch several attacks against a network or an individual host. Attackers may either be a part of a Local Area Network (LAN) or outside a LAN to launch these attacks. There are numerous papers available in the literature to solve problems resulting from IP broadcasting. However, all these solutions target a specific problem that results from IP broadcasting. Furthermore, these solutions use either a computationally-intensive cryptographic scheme, the a priori relation between the host and the network or a modified protocol stack at every host. In this paper, we provide a seamless and transparent solution to eliminate IP broadcasting and thus eliminate all problems related to IP broadcasting. Our proposed solution is crypto-free and does not need any modification to the protocol stack. [ABSTRACT FROM AUTHOR]

In this paper, we introduce the notion of g-convex weight sequence (gcws) for connected graphs based on the concept of g-convexity and g-weight. g-weight is a natural generalization of the notion of branch weight for trees. We investigate the various questions of realization of an integer sequence as a g-convex weight sequence for trees and some special classes of graphs such as complete graphs, windmill and degenerate windmill graphs and wheels. [ABSTRACT FROM AUTHOR]