Wireless Brain Computer Interface for Smart Home and Medical System

Wireless Personal Communications - The number of aged and disabled people has been increasing worldwide. To look after these people is a big challenge in this era. However, scientists overcome the...     

Exploitation of Social Media for Emergency Relief and Preparedness: Recent Research and Trends

Online Social Media, such as Twitter, Facebook and WhatsApp, are important sources of real-time information related to emergency events, including both natural calamities, man-made disasters, epidemics, and so on. There has been lot of recent work on designing information systems that would be useful for aiding post-disaster relief operations, as well as for pre-disaster preparedness. A special issue on “Exploitation of Social Media for Emergency Relief and Preparedness” was conducted for the journal Information Systems Frontiers. The objective of this special issue was to present a platform for dissemination of the empirical results of various technologies for extracting vital and actionable information from social media content in disaster situations. The papers included in this issue are expected to be the stepping stones for future explorations and technical innovations towards technologies meant for utilizing various online and offline information sources for enhancing pre-disaster preparedness and post-disaster relief operations.     

Classifying and Summarizing Information from Microblogs During Epidemics

During a new disease outbreak, frustration and uncertainties among affected and vulnerable population increase. Affected communities look for known symptoms, prevention measures, and treatment strategies. On the other hand, health organizations try to get situational updates to assess the severity of the outbreak, known affected cases, and other details. Recent emergence of social media platforms such as Twitter provide convenient ways and fast access to disseminate and consume information to/from a wider audience. Research studies have shown potential of this online information to address information needs of concerned authorities during outbreaks, epidemics, and pandemics. In this work, we target three types of end-users (i) vulnerable population—people who are not yet affected and are looking for prevention related information (ii) affected population—people who are affected and looking for treatment related information, and (iii) health organizations—like WHO, who are interested in gaining situational awareness to make timely decisions. We use Twitter data from two recent outbreaks (Ebola and MERS) to build an automatic classification approach useful to categorize tweets into different disease related categories. Moreover, the classified messages are used to generate different kinds of summaries useful for affected and vulnerable communities as well as health organizations. Results obtained from extensive experimentation show the effectiveness of the proposed approach.     

CDCSS: cluster-based distributed cooperative spectrum sensing model against primary user emulation (PUE) cyber attacks

In cognitive radio network, the secondary users (SUs) use the spectrum of primary users for communication which arises the security issues. The status of SUs as legitimate users is compulsory for the stability of the system. This paper addresses the issue of delay caused by a band-selection decision process that directly affects the security and performance. The model cluster-based distributed cooperative spectrum sensing is proposed. In this model, cluster heads (CHs) exchange control information with other CHs and ordinary nodes. This model significantly reduced the delay, sensing, convergence, routing, in band-selection process. This also reduces the energy consumption while sensing the spectrum which seriously leads to performance upgradation. The simulated results show the improved performance of cognitive radio networks in terms of delay, packet loss ratio and bandwidth usage as compared to cluster-based cooperative spectrum sensing model. The opportunity for primary user emulation attacker is minimized as the overall delay is reduced.     

A machine learning approach for feature selection traffic classification using security analysis

Class imbalance has become a big problem that leads to inaccurate traffic classification. Accurate traffic classification of traffic flows helps us in security monitoring, IP management, intrusion detection, etc. To address the traffic classification problem, in literature, machine learning (ML) approaches are widely used. Therefore, in this paper, we also proposed an ML-based hybrid feature selection algorithm named WMI_AUC that make use of two metrics: weighted mutual information (WMI) metric and area under ROC curve (AUC). These metrics select effective features from a traffic flow. However, in order to select robust features from the selected features, we proposed robust features selection algorithm. The proposed approach increases the accuracy of ML classifiers and helps in detecting malicious traffic. We evaluate our work using 11 well-known ML classifiers on the different network environment traces datasets. Experimental results showed that our algorithms achieve more than 95% flow accuracy results.     

Fault tolerance aware scheduling technique for cloud computing environment using dynamic clustering algorithm

In cloud computing, resources are dynamically provisioned and delivered to users in a transparent manner automatically on-demand. Task execution failure is no longer accidental but a common characteristic of cloud computing environment. In recent times, a number of intelligent scheduling techniques have been used to address task scheduling issues in cloud without much attention to fault tolerance. In this research article, we proposed a dynamic clustering league championship algorithm (DCLCA) scheduling technique for fault tolerance awareness to address cloud task execution which would reflect on the current available resources and reduce the untimely failure of autonomous tasks. Experimental results show that our proposed technique produces remarkable fault reduction in task failure as measured in terms of failure rate. It also shows that the DCLCA outperformed the MTCT, MAXMIN, ant colony optimization and genetic algorithm-based NSGA-II by producing lower makespan with improvement of 57.8, 53.6, 24.3 and 13.4 % in the first scenario and 60.0, 38.9, 31.5 and 31.2 % in the second scenario, respectively. Considering the experimental results, DCLCA provides better quality fault tolerance aware scheduling that will help to improve the overall performance of the cloud environment.

     

A survey of decision making methods based on two classes of hybrid soft set models

To the best of our knowledge, the tool of soft set theory is a new efficacious technique to dispose uncertainties and it focuses on the parameterization, while fuzzy set theory emphasizes the truth degree and rough set theory as another tool to handle uncertainties, it places emphasis on granular. However, the real-world problems that under considerations are usual very complicated. Consequently, it is very difficult to solve them by a single mathematical tool. It is worth noting that decision making (briefly, DM) in an imprecise environment has been showing more and more role in real-world applications. Researches on the idiographic applications of the above three uncertain theories as well as their hybrid models in DM have attracted many researchers’ widespread interest. DM methods are not yet proposed based on fusions of the above three uncertain theories. In view of the reason, by compromising the above three uncertain theories, we elaborate some reviews to DM methods based on two classes of hybrid soft models: SRF-sets and SFR-sets. We test all algorithms for DM and computation time on data sets produced by soft sets and FS-sets. The numerical experimentation programs are written for given pseudo codes in MATLAB. At the same time, the comparisons of all algorithms are given. Finally, we expatiate on an overview of techniques based on the involved hybrid soft set models.     

Magnetohydrodynamic stagnation point flow of third-grade liquid toward variable sheet thickness

Neural Computing and Applications - The current study examines the boundary layer stagnation point flow of third-grade fluid toward a stretching surface with variable thickness. Electrically...     

Toward analyzing impact of disjoint axioms for merging heterogeneous ontologies

In recent years, the question on Automatic Ontology Merging (AOM) become challenging to address for the researchers. Our research and development for the Disjoint Knowledge Perservation based Automatic Ontology Merging (DKP-AOM) is a milestone in the same direction. This paper provides a more specific discussion about disjoint knowledge axioms in DKP-AOM and makes an assessment of our merge algorithm that looks-up within disjoint partitions of concept hierarchies of ontologies. The significant use of disjoint knowledge is corroborated by testing conference and vertebrate ontologies. The results reveal that disjoint knowledge axioms help identifying initial inaccurate mappings and remove ambiguity when the concept with same symbolic identifier has a different meaning in different local ontologies in the process of ontology merging. Disjoint axioms separate the knowledge in distinct chunks and enable concept matching within the boundaries of sub-hierarchies of the entire ontology concept hierarchy. While finding matches between concepts of ontologies, disjoint partitions with the disjoint knowledge about concepts in source ontologies minimize the search space and reduce the runtime complexity of ontology merging. We also discuss encouraging results obtained by our DKP-AOM system within the OAEI 2015 campaign.     

Scale coding bag of deep features for human attribute and action recognition

Most approaches to human attribute and action recognition in still images are based on image representation in which multi-scale local features are pooled across scale into a single, scale-invariant encoding. Both in bag-of-words and the recently popular representations based on convolutional neural networks, local features are computed at multiple scales. However, these multi-scale convolutional features are pooled into a single scale-invariant representation. We argue that entirely scale-invariant image representations are sub-optimal and investigate approaches to scale coding within a bag of deep features framework. Our approach encodes multi-scale information explicitly during the image encoding stage. We propose two strategies to encode multi-scale information explicitly in the final image representation. We validate our two scale coding techniques on five datasets: Willow, PASCAL VOC 2010, PASCAL VOC 2012, Stanford-40 and Human Attributes (HAT-27). On all datasets, the proposed scale coding approaches outperform both the scale-invariant method and the standard deep features of the same network. Further, combining our scale coding approaches with standard deep features leads to consistent improvement over the state of the art.