On semantic clustering and adaptive robust regression based energy-aware communication with true outliers detection in WSN

Chowdhury, Srijit; Roy, Ambarish; Benslimane, Abderrahim; Giri, Chandan

doi:10.1016/j.adhoc.2019.101934

Cited by 11 publications

(9 citation statements)

References 27 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the algorithm will produce L 1 = (3, 5, 1, 7), L 2 = (9, 2), and L 3 = (4, 8, 6). That is, the UAV will collect the data of the SNs (3, 5, 1, 7), in order, while hovering atop their centroid, then moves to the centroid of (9, 2) to collect their data, and finally moves to the centroid of (4,8,6) to collect their data, completing the exercise of data transmission by the SNs and collection by the UAV.…”

Section: Endmentioning

confidence: 99%

See 1 more Smart Citation

An Efficient Framework for Sensor Data Collection by UAV Based on Clustering, Two-Fold Ant Colony Optimization and Node Grouping

Shayboub,

Reda,

Al-Mahdi

et al. 2023

Preprint

View full text Add to dashboard Cite

Unmanned Aerial Vehicles (UAVs) are a promising solution for sensor data collection (DC) in large-scale area. The challenge is to minimize the DC route, which will reduce UAV energy consumption and data latency. We propose a three-phase efficient solution with innovative algorithms to address this challenge. First, an initial shortest route that traverses all SNs is established based on the ant colony optimization (ACO) and the $K$-means algorithms. Second, we group the sensor nodes (SNs) along the initial route using the footprint of the UAV, so that the latter can collect the data of the group in one stop, instead of stopping at each SN. By sequencing the hovering locations, we obtain a (shorter) intermediate route. Third, we shorten this route even further, by applying ACO to the set of hovering locations of the intermediate route. The solution has been implemented fully in Python. The results show that the route length gets shorter progressively with each phase. To evaluate the performance of the solution objectively, we have compared it with four states of the art solutions. The results show vividly that the proposed solution produces a DC route 19.28\% shorter than the shortest route produced by the four competitive solutions. Moreover, it demonstrates a remarkable improvement by retaining 44\% of energy in most SNs while over 99\% energy depletion observed in the five state-of-the-art competitive solutions.

show abstract

Section: Endmentioning

confidence: 99%

“…This low latency is highly valuable for real-time applications. However, if real time DC is not a critical factor, utilizing a WSN may not be advisable due to its many drawbacks [6].…”

Section: Introductionmentioning

confidence: 99%

An Efficient Framework for Sensor Data Collection by UAV Based on Clustering, Two-Fold Ant Colony Optimization and Node Grouping

Shayboub,

Reda,

Al-Mahdi

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…It was also applicable for large real‐world sensor networks, but the network lifetime was not considered. Chowdhury et al [37] presented the Robust and Efficient Weighted Least Square (REWLS) method for accurate prediction of data with insignificant mistakes. It is highly assisted in data reduction, which saved energy to a greater extend, but this scheme failed to assess real‐time applications.…”

Section: Motivationmentioning

confidence: 99%

Simultaneous wireless information and power transmission‐based power transfer and energy prediction for efficient communication with golden Taylor sea lion optimization in wireless sensor network

Sureshkumar

Vimala

2023

Int J Communication

View full text Add to dashboard Cite

Summary Wireless Sensor Network (WSN) is an emerging lower cost and resourceful solution, which enables controlled observation of the environment. The high amount of energy is required in wireless networks during the transmission of data. Here, Golden Ant Lion Whale Optimization (GALWO) and Golden Taylor Sea Lion Optimization (GTSLnO) techniques are presented for cluster head (CH) selection and prediction of neighbor nodes' age. The six stages performed in this work are setup, steady‐state, prediction, power transfer, communication or route discovery, and route maintenance stages. In the setup level, CH selection is carried out by GALWO, which is the combination of Ant Lion Whale Optimization (ALWO) with Golden Search Optimization (GSO). Moreover, ALWO is an integration of Ant Lion Optimizer (ALO) with the Whale Optimization Algorithm (WOA). In the steady state, the distance, energy, delay, throughput, and trust update are considered as objective functions. In the prediction stage, the Deep Convolutional Neural Network (Deep CNN) is utilized for age prediction of neighbor nodes, wherein Deep CNN is tuned by employing GTSLnO. The GTSLnO is an incorporation of GSO and Taylor series with Sea Lion Optimization (SLnO). Then, the power transfer stage is done utilizing simultaneous wireless information and power transmission (SWIPT). Thereafter, the communication/route discovery stage is conducted for path selection through neighbor node, and lastly, the route maintenance stage is carried out. The GTSLnO–Deep CNN achieved a minimal delay of 0.089 s, maximal residual energy, throughput, and trust of 0.500 J, 98,843 kbps, and 0.452 for DoS attack.

show abstract

“…However, the effectiveness of the dual prediction scheme in reducing data transmissions depends on the accuracy of the prediction model. Thus, extended dual prediction methods were presented in the literature to tackle the problem of eliminating erroneous sensor data (outliers) that lead to wrong predictions [30].…”

Section: Dual Predictionmentioning

confidence: 99%

Data Transmission Reduction in Wireless Sensor Network for Spatial Event Detection

Lewandowski

Płaczek

2021

Sensors

View full text Add to dashboard Cite

Wireless sensor networks have found many applications in detecting events such as security threats, natural hazards, or technical malfunctions. An essential requirement for event detection systems is the long lifetime of battery-powered sensor nodes. This paper introduces a new method for prolonging the wireless sensor network’s lifetime by reducing data transmissions between neighboring sensor nodes that cooperate in event detection. The proposed method allows sensor nodes to decide whether they need to exchange sensor readings for correctly detecting events. The sensor node takes into account the detection algorithm and verifies whether its current sensor readings can impact the event detection performed by another node. The data are transmitted only when they are found to be necessary for event detection. The proposed method was implemented in a wireless sensor network to detect the instability of cargo boxes during transportation. Experimental evaluation confirmed that the proposed method significantly extends the network lifetime and ensures the accurate detection of events. It was also shown that the introduced method is more effective in reducing data transmissions than the state-of-the-art event-triggered transmission and dual prediction algorithms.

show abstract

On semantic clustering and adaptive robust regression based energy-aware communication with true outliers detection in WSN

Cited by 11 publications

References 27 publications

An Efficient Framework for Sensor Data Collection by UAV Based on Clustering, Two-Fold Ant Colony Optimization and Node Grouping

An Efficient Framework for Sensor Data Collection by UAV Based on Clustering, Two-Fold Ant Colony Optimization and Node Grouping

Simultaneous wireless information and power transmission‐based power transfer and energy prediction for efficient communication with golden Taylor sea lion optimization in wireless sensor network

Data Transmission Reduction in Wireless Sensor Network for Spatial Event Detection

Contact Info

Product

Resources

About