K-predictions based data reduction approach in WSN for smart agriculture

Salim, Christian; Mitton, Nathalie

doi:10.1007/s00607-020-00864-z

Cited by 29 publications

(18 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Salim & Mitton, 2021 proposed a novel data reduction and prediction model using K‐possible prediction strategies. This existing scheme contributed for deploying WSN nodes among crop fields to monitor the field environmental conditions.…”

Section: Related Workmentioning

confidence: 99%

“…For example, they are limited to real‐time data processing components, field dependency and less accuracy rate. Several research works contributed to constructing smart crop field management systems (Cicioğlu & Çalhan, 2021; García et al, 2020; 2021; Salim & Mitton, 2021; Vijayakumar & Balakrishnan, 2021). They deployed sensors such as soil monitoring sensors, humidity sensors, temperature sensors, water level sensors and moisture sensors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Internet of things‐based deeply proficient monitoring and protection system for crop field

et al. 2021

View full text Add to dashboard Cite

The production rate of crops is significantly declining due to natural disasters, animal interventions and plant diseases. Internet of things (IoT) and wireless sensor networks are widely applied in crop field monitoring systems to observe the quality of each plant and the field. This work proposes IoT based crop field protection system (ICFPS) that monitors and protects the crop fields from animal intrusions. This proposed system uses ultrasonic sensors, hyperspectral cameras, voice recorded buzzers and other agriculture sensors to protect the entire crop field. This system uses numerous sensor nodes and cameras for gathering field objects (images and environmental objects). The proposed ICFPS creates deep learning techniques such as recurrent convolutional neural networks (RCNN) and recurrent generative adversarial neural networks (RGAN) for feature extraction, disease detection and field data monitoring practices. This proposed work develops a smart city-based agriculture system using cognitive learning approaches. This proposed system analyses crop field data and provide automatic alerts regarding animal interferences and crop diseases. Moreover, the cognitive smart crop field system observes various field conditions which support for good production rate. In this system, sensors and camera-enabled agriculture drones are coordinated with each other to collect the field data regularly. At the same time, the proposed work trains the RCNN and RGAN units using effective crop field datasets to attain realistic decisions within minimal time intervals. The experiment details and results show the proposed ICFPS works with 8%-10% of more classification accuracy than existing systems.cognitive smart systems, crop field, deep learning and data analysis, internet of things, smart cities, wireless sensor networks | INTRODUCTIONCrop field monitoring systems and smart agriculture systems are the emerging technologies for developing automatic field control frameworks.Researchers develop smart agriculture systems for monitoring the crop field environment (soil, weather, water level, irrigation and disease) using various sensors. Recently, wireless sensor networks (WSN) frameworks and internet of things (IoT) platforms control the operations of smart field management models. On the other view, research works contributed to use the field sensor data and learning models for increasing the accuracy of decision-making systems.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Internet of things‐based deeply proficient monitoring and protection system for crop field

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In [11], the authors proposed a correlation system based on a Bayesian inference approach in order to avoid transmitting data that can be reconstructed from other data. Machine learning for data prediction is widely used for data reduction as in [18], [13], [15], [14] and [7]. In the dual prediction model [18], the sensor node and the sink both predict the next values of the monitored feature simultaneously.…”

Section: Background and Related Workmentioning

confidence: 99%

On-Node Correlation Based Data Reduction in WSN for Smart Agriculture

Salim

Mitton

2020

2020 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS)

Self Cite

View full text Add to dashboard Cite

Nowadays, climate change is one of the numerous factors affecting the agricultural sector. Optimizing the usage of natural resources is one of the challenges this sector faces. For this reason, it could be necessary to locally monitor weather data and soil conditions to make faster and better decisions locally adapted to the crop. Wireless sensor networks (WSNs) can serve as a monitoring system for these types of parameters. However, in WSNs, sensor nodes suffer from limited energy resources. The process of sending a large amount of data from the nodes to the sink results in high energy consumption at the sensor node and significant use of network bandwidth, which reduces the lifetime of the overall network. In this paper, for data reduction, a data correlation and prediction technique is proposed both at the sensor node level and at the sink level. The aim of this approach is to reduce the amount of transmitted data to the sink, depending on the degree of correlation between different parameters. In this work we propose the Pearson Data Correlation and Prediction (PDCP) algorithm to detect this correlation. This data reduction maintains the accuracy of the information while reducing the amount of data sent from the nodes to the sink. This approach is validated through simulations on MATLAB using real meteorological data-sets from Weather-Underground sensor network. The results show the validity of our approach by reducing the amount of data by a percentage up to 69% while maintaining the accuracy of the information. The humidity values prediction based on the temperature parameter is accurate and the deviation from the real value does not surpass 7% of humidity.

show abstract

“…They simulated the method on real temperature data set from weather‐underground sensor network and reported more than 70 % data reduction and 30 % –50 % when compared to other state‐of‐the‐art methods. In their extension work, 61 authors have also investigated data correlation, which was combined with data prediction technique to recover the information mathematically.…”

Section: Introductionmentioning

confidence: 99%

Data reduction and recovery in wireless communication system: An extensive experimental evaluation using PSK and QAM modulations

Panem

Vetrekar

Gad

2022

Int J Communication

View full text Add to dashboard Cite

Summary The evolution of technologies in data communication system has resulted in generation of large data. With the availability of limited bandwidth and to maintain the energy efficiency of the wireless communication system, data reduction plays a significant amount of role in preserving the lifetime of wireless communication system. Considering the significance of this problem in wireless communication system, in this work, we present data reduction and recovery or reconstruction on multivariate data using principal component analysis (PCA). In general, we send the eigen coefficients from the source and use these coefficients at the destination to recover or reconstruct the original data back in wireless communication system. We employ in our work two different digital modulation techniques such as phase‐shift keying (PSK) and quadrature amplitude modulation (QAM) with seven different bit rate to demonstrate our approach. We carry the experiments independently using five different signal ensemble and four different multiple‐input, multiple‐output (MIMO) configuration along with Rayleigh fading. This work presents an extensive simulated benchmark results based on performance matrix such as root mean square error (RMSE) and bit error rate (BER) at different values of signal‐to‐noise ratio (SNR). We further validate our approach by presenting synthesis of our proposed model using Xilinx target device Virtex‐6 LX240T Field Programmable Gate Array (FPGA). The experimental results reported based on simulation, synthesis, and validation of model demonstrate the applicability of our proposed approach in real‐time scenario.

show abstract

K-predictions based data reduction approach in WSN for smart agriculture

Cited by 29 publications

References 28 publications

Internet of things‐based deeply proficient monitoring and protection system for crop field

Internet of things‐based deeply proficient monitoring and protection system for crop field

On-Node Correlation Based Data Reduction in WSN for Smart Agriculture

Data reduction and recovery in wireless communication system: An extensive experimental evaluation using PSK and QAM modulations

Contact Info

Product

Resources

About