Fuzzy-Based Flat Anomaly Diagnosis and Relief Measures in Distributed Wireless Sensor Network

Nisha, U. Barakkath; Maheswari, N.; Venkatesh, R.; Abdullah, R. Yasir

doi:10.1007/s40815-016-0253-2

Cited by 8 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Security should be designed into devices, but manufacturers have little incentive to consistently do this work. 14,15 On the other hand, consumer privacy concerns inhibit the adoption of IoT devices. A lot of data generated by IoT devices about consumers can directly and indirectly reveal their activities.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A lightweight hierarchical method for improving security in the internet of things using fuzzy logic

Doostani,

Barati,

Barati

2023

Concurrency and Computation

View full text Add to dashboard Cite

SummaryThe internet of things (IoT) refers to the interconnection of various devices through the internet. With the help of IoT, different applications and devices can interact with each other and even with humans through the internet. However, the widespread use of IoT in homes, offices, and private companies has raised concerns about privacy and security. The theft of user information by hackers is a major challenge that has hindered the adoption of IoT. This paper proposes a method for improving security on two levels: intra‐cluster and inter‐cluster. In the intra‐cluster phase, the cluster head uses fuzzy logic to measure the trust level of nodes. If the node is trusted, the information is received and sent to the destination. In the inter‐cluster phase, data between cluster heads is encrypted using column transposition encryption. The encryption is hop by hop, and the encryption key is changed at each hop. The proposed method is simulated using NS‐2 software. A comparison of the proposed method's performance with conventional methods shows that the proposed method results in better packet delivery rate, throughput, and prevention of link spoofing attacks.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Several methods for security in IoT and their advantages and disadvantages are reviewed in this section. Security should be designed into devices, but manufacturers have little incentive to consistently do this work 14,15 . On the other hand, consumer privacy concerns inhibit the adoption of IoT devices.…”

Section: Related Workmentioning

confidence: 99%

A lightweight hierarchical method for improving security in the internet of things using fuzzy logic

Doostani,

Barati,

Barati

2023

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…In this section, to determine utilization of energy during anomaly detection in the sensor node, complexity analysis is performed. Table 6provides the complexity analysis used in similar approaches [42]. The computational complexity of FANN is 𝑂(𝑟𝑛𝑔)based on the evaluation of 'r'-number of inputs at the time, 'n'total dimension of the instances and 'g'-number of aggregators and the communication overhead obtained is 𝑂((𝑟 − 𝑎)𝑛)where 'a'number of abnormal instances that are removed as it uses deep leaning model.…”

Section: Energy Performancementioning

confidence: 99%

Anomaly Detection with Improved Data Accuracy and False Positive Reduction in Distributed Wireless Sensor Network

Venkatesan

2022

Preprint

View full text Add to dashboard Cite

Data reliability in Wireless Sensor Networks (WSNs) has a substantial influence in their smooth functioning and resource limitations. In WSN the data aggregated from clustered sensor nodes are forwarded to base station for analysis. This data aggregation suffers in handling abnormal data instances that need to be filtered before transmission. Anomaly Detection (AD) focuses on detecting unreliable data thereby ensuring consistency during data aggregation. As WSNs have critical resource limitation with respect to energy consumption and sensor node lifetime, AD is supposed to provide data integrity with minimum energy consumption which imparts to an essential research focus. Hence, researchers are striving for methods to improve the accuracy of data handled with concern on constraints to WSN. In current decades, the researcher’s spotlight on unsupervised anomaly detection practice as it uses real data to perceive occurrences. This article introduces a Feed-forward Autoencoder Neural Network (FANN) model to detect abnormal instances with improved accuracy and minimum power. The proposed model also acts as False Positive Reducer avoiding data loss by reducing the false alarms. The proposed model is compared with other dominant unsupervised algorithms over robustness and other significant metrics for real time dataset. Relatively, our proposed model yields high accuracy with less false alarms up to 16% during detection. Experimental analysis of FANN AD infers a reduced data transmission cost with minimum energy supporting a sustainable WSN life time.

show abstract

“…Barakkath Nisha et al propose a fuzzy‐based approach for anomaly detection. The dataset used in this work is divided into sets where the likenesses inside these sets are greater between peers.…”

Section: Outlier Detection In Wsnsmentioning

confidence: 99%

“…The noise-generation algorithm chooses randomly data from the matrix D and adds noise to this data based on Noiselevel matrix. The output of this function is the NoisData matrix as shown by Equation (30).…”

mentioning

confidence: 99%

Standalone noise and anomaly detection in wireless sensor networks: A novel time‐series and adaptive Bayesian‐network‐based approach

Safaei

Ismail

Chizari³

et al. 2020

Softw Pract Exp

View full text Add to dashboard Cite

Summary Wireless sensor networks (WSNs) consist of small sensors with limited computational and communication capabilities. Reading data in WSN is not always reliable due to open environmental factors such as noise, weakly received signal strength, and intrusion attacks. The process of detecting highly noisy data is called anomaly or outlier detection. The challenging aspect of noise detection in WSN is related to the limited computational and communication capabilities of sensors. The purpose of this research is to design a local time‐series‐based data noise and anomaly detection approach for WSN. The proposed local outlier detection algorithm (LODA) is a decentralized noise detection algorithm that runs on each sensor node individually with three important features: reduction mechanism that eliminates the noneffective features, determination of the memory size of data histogram to accomplish the effective available memory, and classification for predicting noisy data. An adaptive Bayesian network is used as the classification algorithm for prediction and identification of outliers in each sensor node locally. Results of our approach are compared with four well‐known algorithms using benchmark real‐life datasets, which demonstrate that LODA can achieve higher (up to 89%) accuracy in the prediction of outliers in real sensory data.

show abstract

Fuzzy-Based Flat Anomaly Diagnosis and Relief Measures in Distributed Wireless Sensor Network

Cited by 8 publications

References 32 publications

A lightweight hierarchical method for improving security in the internet of things using fuzzy logic

A lightweight hierarchical method for improving security in the internet of things using fuzzy logic

Anomaly Detection with Improved Data Accuracy and False Positive Reduction in Distributed Wireless Sensor Network

Standalone noise and anomaly detection in wireless sensor networks: A novel time‐series and adaptive Bayesian‐network‐based approach

Contact Info

Product

Resources

About