Most environmental monitoring application periodically senses and aggregated data by sensor networks which usually exhibits high temporal redundancies. An enormous amount of energy is depleted in transmitting this redundant information making it extremely difficult to achieve an acceptable network lifespan, which has become a bottleneck in scaling such applications. To efficiently manage the energy depletion in concurrent data collection rounds, a prediction model based on Extended Cosine Regression (ECR) for Data Aggregation is proposed. The proposed technique delivers prediction with high accuracy and the energy consumption is minimized with successful predictions and thereby increases the data cycles and network lifetime. ECR also uses a two-vector model in the intra-cluster transmissions to synchronize the predicted data values and therefore minimizes cumulative errors from continuous predictions. The proposed ECR technique is simulated using NS2-34 shows high-energy efficiency as compared with the existing schemes. Results demonstrate high prediction accuracy, a number of successful predictions and a lesser degree of prediction errors, which obviously improve the network’s lifetime.

An energy-efficient prediction model for data aggregation in sensor network

The rapid advancement of technologies has enabled businesses to carryout their activities seamlessly and revolutionised communications across the globe. There is a significant growth in the amount and complexity of Internet of Things devices that are deployed in a wider range of environments. These devices mostly communicate through Wi-Fi networks and particularly in smart environments. Besides the benefits, these devices also introduce security challenges. In this paper, we investigate and leverage effective feature selection techniques to improve intrusion detection using machine learning methods. The proposed approach is based on a centralised intrusion detection system, which uses the deep feature abstraction, feature selection and classification to train the model for detecting the malicious and anomalous actions in the traffic. The deep feature abstraction uses deep learning techniques of artificial neural network in the form of unsupervised autoencoder to construct more features for the traffic. Based on the availability of cumulative features, the system then employs a variety of wrapper-based feature selection techniques ranging from SVM and decision tree to Naive Bayes for selecting high-ranked features, which are then combined and fed into an artificial neural network classifier for distinguishing attack and normal behaviors. The experimental results reveal the effectiveness of the proposed method on Aegean Wi-Fi Intrusion Dataset, which achieves high detection accuracy of up to 99.95%, relatively competitive to the existing machine learning works for the same dataset.

Effective combining of feature selection techniques for machine learning-enabled IoT intrusion detection

https://ietresearch.onlinelibrary.wiley.com/doi/pdf/10.1049/cmu2.12262

A reliable and energy efficient dual prediction data reduction approach for WSNs based on Kalman filter

Load Balanced Node Clustering scheme using Improved Memetic Algorithm based Meta-heuristic Technique for Wireless Sensor Network

Environmental monitoring is among the most significant applications of wireless sensor networks (WSNs), which results in sensing, communicating, aggregating and transmitting large volumes of data over a very short period. Thus, a lot of energy is consumed in transmitting this redundant and correlated data to the basestation (BS) making it enormously challenging to achieve an acceptable network lifetime, which has become a bottleneck in scaling such applications. In order to proficiently deal with the energy utilization in successive data aggregation cycles, we propose a data prediction-based aggregation model, which will reduce data transmission by establishing relationship between sensor readings. The purpose of the proposed model is to exempt the sensor nodes (SN) from sending huge volumes of data for a specific duration during which the BS will predict the future data values and thus minimize the energy utilization of WSN. The study suggested an extended linear regression model, which determines resemblance in shape of data curve of contiguous data periods. We have used real sensor dataset of 54 SN that was deployed in the Intel Berkeley Research laboratory. We tested and compared our work with the recent prediction-based data reduction method. Results reveal that the proposed ELR model works better when compared with the other techniques in many assessment indicators.

A Novel Data Prediction Technique Based on Correlation for Data Reduction in Sensor Networks

In wireless sensor networks (WSNs), each sensor node is proficient to transmit data packets dynamically deprived of any constraint of fixed infrastructure. Sensor nodes (SNs) intermittently travels within the network from one cluster to another, which makes the network topology unsteady, uncertain, and unreliable. Consequently, it turns to be an immense challenge to sustain network stability and durability. In this work, the authors have presented a resilient steady clustering technique (RSCT) that will maintain durability and steadiness to the sensor network by reducing the unnecessary and avoidable cluster head (CH) changes and minimizing clustering and networking overheads. In the presented technique, they have introduced a new SN that acts as a standby node (SBN) in the cluster. This SBN performs the tasks of CH whenever the actual CH moves from the cluster. Later the CH re-elect the new SBN. This process keeps the network available and serviceable without any interruption. The decision for selecting the CH and SBN depends on the optimal CH threshold function and an energy threshold function.

A Resilient Steady Clustering Technique for Sensor Networks

Continuous-monitoring applications in sensor network applications require periodic data transmissions to the base-station (BS), which may lead to unnecessary energy depletion. The energy-efficient data aggregation solutions in sensor networks have evolved as one of the favorable fields for such applications. Former research works have recommended many spatial-temporal designs and prototypes for successfully minimizing the data-gathering overheads, but these are constrained to their relevance. This work has proposed a data aggregation technique for homogeneous application set-ups in sensor networks. For this, the authors have employed two ways of model generation for reducing correlated spatial-temporal data in cluster-based sensor networks: one at the Sensor nodes (SNs) and the other at the Cluster heads (CHs). Building on this idea, the authors propose two types of data filtration, first at the SNs for determining temporal redundancies (TRs) in data readings by both relative deviation (RD) and adaptive frame method (AFM) and second at the CHs for determining spatial redundancies (SRs) by both RD and AFM.

Energy-Efficient Data-Aggregation Technique for Correlated Spatial and Temporal Data in Cluster-Based Sensor Networks

For mobile clients, sufficient resources with the assurance of efficient performance and energy efficiency are the core concerns. This article mainly considers this need and proposes a resourceful architecture, called mRARSA that addresses the critical need in a mobile cloud environment. This architecture consists of cloud resources, mobile devices, and a set of functional components. The performance efficiency evaluates implementing the proposed context-aware multi-criteria decision offloading algorithm. This algorithm considers both device context (network parameters) and application content (task size) at run time when offloading an executable code to allocate the cloud resources. The appropriate resources select based on offloading decisions and via the wireless communication channels. The architecture’s remarkable component is the signal strength analyzer that determines the signal quality (e.g.-60 dBm) and contributes to performance efficiency. The proposed prototype model has implemented several times to monitor the performance efficiency, mobility, performance at communication barriers, and the outcomes of resource-demanding application’s execution. Results indicate performance improvement, such as the algorithm appropriately decides the cloud resources based on device network context, application content, mobility, and the signal strength quality and range. Moreover, the results also show significant improvement in achieving performance and energy efficiency. Sufficient resources and performance efficiency are the most significant features that distinguish this framework from the other existing frameworks.

/pdf/efficient-resourceful-mobile-cloud-architecture-mrarsa-for-1o9g9jvxzz.pdf

Anoop Kumar

Papers

An energy-efficient prediction model for data aggregation in sensor network

A Novel Data Prediction Technique Based on Correlation for Data Reduction in Sensor Networks

A Resilient Steady Clustering Technique for Sensor Networks

Energy-Efficient Data-Aggregation Technique for Correlated Spatial and Temporal Data in Cluster-Based Sensor Networks

Efficient resourceful mobile cloud architecture (mRARSA) for resource demanding applications