A mobile ad-hoc network (MANET) is a temporary network of wireless mobile nodes. In a MANET, it is assumed that all of the nodes cooperate with each other to transfer data packets in a multi-hop fashion. However, some malicious nodes don’t cooperate with other nodes and disturb the network through false routing information. In this paper, we propose a prominent technique, called dual attack detection for black and gray hole attacks (DDBG), for MANETs. The proposed DDBG technique selects the intrusion detection system (IDS) node using the connected dominating set (CDS) technique with two additional features; the energy and its nonexistence in the blacklist are also checked before putting the nodes into the IDS set. The CDS is an effective, distinguished, and localized approach for detecting nearly-connected dominating sets of nodes in a small range in mobile ad hoc networks. The selected IDS nodes broadcast a kind of status packet within a size of the dominating set for retrieving the complete behavioral information from their nodes. Later, IDS nodes use our DDBG technique to analyze the collected behavioral information to detect the malicious nodes and add them to the blacklist if the behavior of the node is suspicious. Our experimental results show that the quality of the service parameters of the proposed technique outperforms the existing routing schemes.

Short-term traffic state prediction has become an integral component of an advanced traveler information system (ATIS) in intelligent transportation systems (ITS). Accurate modeling and short-term traffic prediction are quite challenging due to its intricate characteristics, stochastic, and dynamic traffic processes. Existing works in this area follow different modeling approaches that are focused to fit speed, density, or the volume data. However, the accuracy of such modeling approaches has been frequently questioned, thereby traffic state prediction over the short-term from such methods inflicts an overfitting issue. We address this issue to accurately model short-term future traffic state prediction using state-of-the-art models via hyperparameter optimization. To do so, we focused on different machine learning classifiers such as local deep support vector machine (LD-SVM), decision jungles, multi-layers perceptron (MLP), and CN2 rule induction. Moreover, traffic states are evaluated using traffic attributes such as level of service (LOS) horizons and simple if–then rules at different time intervals. Our findings show that hyperparameter optimization via random sweep yielded superior results. The overall prediction performances obtained an average improvement by over 95%, such that the decision jungle and LD-SVM achieved an accuracy of 0.982 and 0.975, respectively. The experimental results show the robustness and superior performances of decision jungles (DJ) over other methods.

Due to the dynamism of topology, sharing of bandwidth and constraint of resources in wireless nodes, the provision of quality of service (QoS) for routing in mobile ad hoc networks (MANETs) presents a great challenge. Security is another crucial aspect of providing QoS since the existence of malicious nodes present all kinds of threats to MANETs. Although a number of mechanisms have been proposed for protecting MANETs, most of the solutions are only effective for a particular kind of attacks or provide security at the cost of sacrificing QoS. In this paper, we propose a trust-based secure QoS routing scheme by combining social and QoS trust. The primary approach of the proposed scheme relies on mitigating nodes that exhibit various packet forwarding misbehavior and on discovering the path that ensures reliable communication through the trust mechanism. The scheme would select the best forwarding node based on packet forwarding behavior as well as capability in terms of QoS parameters, such as residual energy, channel quality, link quality, etc. We will present an adversary model for packet dropping attack against which we evaluate the proposed scheme. Simulation experiment using Network Simulator-2 (NS2) and under various network conditions show that mixing social and QoS trust parameters can greatly improve security and quality of service routing in terms of overhead, packet delivery ratio and energy consumption.

In recent years, information security has become a very important topic for researchers as well as military and government officials. For secure communication, it is necessary to develop novel ways to hide information. For this purpose, steganography is commonly used to send secret information to its destination using different techniques. In this article, our main focus is on text-based steganography. Hidden information in text files is difficult to discover as text data has low redundancy in comparison to other mediums of steganography. Hence, we use Arabic text to hide secret information using a combination of Unicode character's zero-width-character and zero-width-joiner in our proposed algorithm. The experimental results show hidden data capacity per word is significantly increased in comparison to the recently proposed algorithms. The major advantage of our proposed algorithm over previous research is the high visual similarity in both cover and stego-text that can reduce the attention of intruders.

Text segmentation (TS) is the process of dividing multi-topic text collections into cohesive segments using topic boundaries. Similarly, text clustering has been renowned as a major concern when it comes to multi-topic text collections, as they are distinguished by sub-topic structure and their contents are not associated with each other. Existing clustering approaches follow the TS method which relies on word frequencies and may not be suitable to cluster multi-topic text collections. In this work, we propose a new ensemble clustering approach (ECA) is a novel topic-modelling-based clustering approach, which induces the combination of TS and text clustering. We improvised a LDA-onto (LDA-ontology) is a TS-based model, which presents a deterioration of a document into segments (i.e. sub-documents), wherein each sub-document is associated with exactly one sub-topic. We deal with the problem of clustering when it comes to a document that is intrinsically related to various topics and its topical structure is missing. ECA is tested through well-known datasets in order to provide a comprehensive presentation and validation of clustering algorithms using LDA-onto. ECA exhibits the semantic relations of keywords in sub-documents and resultant clusters belong to original documents that they contain. Moreover, present research sheds the light on clustering performances and it indicates that there is no difference over performances (in terms of F-measure) when the number of topics changes. Our findings give above par results in order to analyse the problem of text clustering in a broader spectrum without applying dimension reduction techniques over high sparse data. Specifically, ECA provides an efficient and significant framework than the traditional and segment-based approach, such that achieved results are statistically significant with an average improvement of over 10.2%. For the most part, proposed framework can be evaluated in applications where meaningful data retrieval is useful, such as document summarization, text retrieval, novelty and topic detection.