BSDP: Big Sensor Data Preprocessing in Multi-Source Fusion Positioning System Using Compressive Sensing

Zhao, Wanlong; Han, Shuai; Meng, Weixiao; Sun, Dong; Hu, Rose Qingyang

doi:10.1109/tvt.2019.2929560

Cited by 30 publications

(17 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, sensor fusion techniques have been adopted in the wireless localization system [33], [34]. These techniques utilize several types of sensor data to improve wireless localization performance.…”

Section: F Impact Of Environmentsmentioning

confidence: 99%

State-Aware Rate Adaptation for UAVs by Incorporating On-Board Sensors

Wang

Yang

et al. 2020

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

Nowadays unmanned aerial vehicles (UAVs) are being widely applied to a wealth of civil and military applications. Robust and high-throughput wireless communication is the crux of these UAV applications. Yet, air-to-ground links suffer from time-varying channels induced by the agile mobility and dynamic environments. Rate adaptation algorithms are generally used to choose the optimal data rate based on the current channel conditions. State-of-the-art approaches leverage physical layer information for rate adaptation, and they work well under certain conditions. However, the above protocols still have limitation under constantly changing flight states and environments for airto-ground links. To solve this problem, we propose StateRate, a state-optimized rate adaptation algorithm that fully exploits the characteristics of UAV systems using a hybrid deep learning model. The key observation is that the rate adaptation strategy needs to be adjusted according to motion-dependent channel models, which can be reflected by flight states. In this work, the rate adaptation protocol is enhanced with the help of the on-board sensors in UAVs. To make full use of the sensor data, we introduce a learning-based prediction module by leveraging the internal state to dynamically store temporal features under variable flight states. We also present an online learning algorithm by employing the pre-trained model that adapts the rate adaptation algorithm to different environments. We implement our algorithm on a commercial UAV platform and evaluate it in various environments. The results demonstrate that our system outperforms the best-known rate adaptation algorithm up to 53% in terms of throughput when the velocity is 2-6 m/s.

show abstract

Section: F Impact Of Environmentsmentioning

confidence: 99%

State-Aware Rate Adaptation for UAVs by Incorporating On-Board Sensors

Wang

Yang

et al. 2020

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

show abstract

“…Such packet loss ''Association Effect'' is given rise to by the superimposing of data collected at each not of the multi-hop link during the CS compression sampling process. The closer the node S k where the packet loss occurs to the Sink, the greater the ''Association Effect'' of the loss of the packet, especially, of the Sink's one-hop neighbor node packet is lost, the association influence will cause the collected data of all nodes in the network to be lost [39], [40]. After that, according to Formula (4), every round of CS data collection is divided into M observations and performed separately.…”

Section: Data Packet Loss Modelmentioning

confidence: 99%

“…The consumption of the energy of wireless sensor networks adopts the energy consumption model described in paper [20], as shown in Formula (39) and (40), where E T (d, l) indicates the energy consumption for sending l-bit data, and d indicates the transmission distance α 1 indicates the power consumption of transmitting and receiving circuits, α 2 indicates the distance attenuation coefficient, n is the path loss factor (2 < n < 5, generally n = 2 in free space); E R (l) indicates the energy consumption of receiving l-bit data.…”

Section: Simulation and Analysismentioning

confidence: 99%

Edge Computing in Internet of Things: A Novel Sensing-Data Reconstruction Algorithm Under Intelligent-Migratoin Stragegy

2020

View full text Add to dashboard Cite

“…The large number of features in the datasets however causes a major problem for classification algorithms known as the curse of dimensionality [7], [8]. This problem increases both computational time, overfitting problem and complexity of the classification model and reduces classification accuracy [8], [9]. Specifically, redundant features are seen as the main reason for the overfitting problem [8].…”

Section: Introductionmentioning

confidence: 99%

Enhanced Binary Cuckoo Search With Frequent Values and Rough Set Theory for Feature Selection

Alia¹,

Taweel

2021

IEEE Access

View full text Add to dashboard Cite

Redundant and irrelevant features in datasets decrease classification accuracy, and increase computational time of classification algorithms, overfitting problem and complexity of the underlying classification model. Feature selection is a preprocessing technique used in classification algorithms to improve the selection of relevant features. Several approaches that combine Rough Set Theory (RST) with Nature Inspired Algorithms (NIAs) have been used successfully for feature selection. However, due to the inherit limitations of RST for some data types and the inefficient convergence of NIAs for high dimensional datasets, these approaches have mainly focused on a specific type of low dimensional nominal dataset. This paper proposes a new filter feature selection approach based on Binary Cuckoo Search (BCS) and RST, which is more efficient for low and high dimensional nominal, mixed and numerical datasets. It enhances BCS by developing a new initialization and global update mechanisms to increase the efficiency of convergence for high dimensional datasets. It also develops a more efficient objective function for numerical, mixed and nominal datasets. The proposed approach was validated on 16 benchmark datasets; 4 nominal, 4 mixed and 8 numerical drawn from the UCI repository. It was also evaluated against standard BCS; five NIAs with fuzzy RST approaches; two popular traditional FS approaches; and multi objective evolutionary, Genetic, and Particle Swarm Optimization (PSO) algorithms. Decision tree and naive Bayes algorithms were used to measure the classification performance of the proposed approach. The results show that the proposed approach achieved improved classification accuracy while minimizing the number of features compared to other state-of-the-art methods. The code is available at https://github.com/abualia4/EBCS.

show abstract

BSDP: Big Sensor Data Preprocessing in Multi-Source Fusion Positioning System Using Compressive Sensing

Cited by 30 publications

References 46 publications

State-Aware Rate Adaptation for UAVs by Incorporating On-Board Sensors

State-Aware Rate Adaptation for UAVs by Incorporating On-Board Sensors

Edge Computing in Internet of Things: A Novel Sensing-Data Reconstruction Algorithm Under Intelligent-Migratoin Stragegy

Enhanced Binary Cuckoo Search With Frequent Values and Rough Set Theory for Feature Selection

Contact Info

Product

Resources

About