Search

With the advent of the Internet of Things (IoT) paradigm and the prolific growth in technology, the volume of data generated by intelligent devices has increased tremendously. Cloud computing provides unlimited processing and storage capabilities to process and store the generated data. However, the cloud computing paradigm is associated with high transmission latency, high energy consumption, and a lack of location awareness. On the other hand, the data generated by the intelligent devices is delay-sensitive and needs to be processed on the fly. Thus, cloud computing isn’t suitable for the execution of this delay-sensitive data. To curtail the issues associated with the cloud paradigm, the fog paradigm, which allows data to be processed at the proximity of IoT devices, was introduced. One common feature of the fog paradigm is its limitations in capabilities, which make it unsuitable for processing large volumes of data. To ensure the smooth execution of delay-sensitive application tasks and the large volume of data generated, there is a need for the fog paradigm to collaborate with the cloud paradigm to achieve a common goal. In this paper, an efficient resource allocation framework is proposed to efficiently and effectively utilise the fog and cloud resources for executing delay-sensitive tasks and the huge volume of data generated by end users. The allocation of resources to tasks is done in two stages. Firstly, the tasks in the arrival queue are classified based on the task guarantee ratio on the cloud and fog layers and allocated to suitable resources in the layers of their respective classes. Secondly, we apply Bayes’ classifier to previous allocation history data to classify newly arrived tasks and allocate suitable resources to the tasks for execution in the layers of their respective classes. A Crayfish Optimization Algorithm (COA) is used to generate an optimal resource allocation in both the fog and cloud layers that reduces the delay and execution time of the system. The proposed method is implemented using the iFogSim simulator toolkit, and the execution results prove more promising in comparison with the state-of-the-art methods.

Wireless sensor devices are affected by internal constraints and the external environment, generating abnormal data. Currently, many anomaly detection schemes ignore the correlation between screening nodes, wasting resources due to excessive communication. Therefore, this paper proposes a distributed anomaly detection scheme based on adaptive grouping using the correlation between nodes in wireless sensor networks. Limiting the scope of collaboration between nodes can reduce the waste of resources due to excessive communication. Since the computing resources of sensor nodes are limited, an edge-cloud framework is established. The scheme uses Spatio-temporal correlation and graph theory for wireless sensor networks to determine node groups with solid correlations on the cloud server. Based on the grouping results, anomaly detection is implemented locally. A Bayesian network model is constructed at the node within the group, and outlier detection is realized by inference on nodes. A correlation consistency evaluation method is proposed to improve anomaly detection accuracy to check the data consistency on the cluster head. The proposed scheme is verified by a generated data set and the real data of Intel Berkeley Research Lab. The effectiveness of the proposed method is verified by comparing it with three existing algorithms. Experimental results show that the method improves detection accuracy and reduces false detection. [ABSTRACT FROM AUTHOR]

In FCA, we often deal with a formal context K = (G , M , I) that is only partially known, i.e. only the attributes that belong to an observable set N ⊂ M are known. There must also exist a part H of the object set G – called a training set – that consists of elements with all attributes known. The concepts of K have to be determined using the subcontexts corresponding to the training object set H and to the observable attribute set N. In our paper, this problem is examined within the extended framework of the semiconcepts of the original context, which are generalizations of its concepts. Each semiconcept of the original context induces a semiconcept in both subcontexts. In this way, each semiconcept of the context is represented by an induced pair of semiconcepts, which can also be considered its approximations — as in the case of rough sets. We describe the properties of the mapping defined by this representation and prove that the poset formed by these semiconcept pairs is a union of two complete lattices. We show that these induced semiconcept pairs can be generated by using a simplified representation of them. As the number of semiconcepts grows exponentially with the size of the training set and the observable attribute set, an algorithm that selects the representation pairs for which their support and relevance reach a certain threshold is also presented. [ABSTRACT FROM AUTHOR]