Mobile crowd location prediction with hybrid features using ensemble learning

Zhao, Zhongliang; Karimzadeh, Mostafa; Gerber, Florian; Braun, Torsten

doi:10.1016/j.future.2018.06.025

Cited by 16 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Authors in [35], have proposed method to predict users next movement in the future time interval. In this model uses ensemble technique during training phase to predict user's next movement location along with the pattern during movement.…”

Section: Related Workmentioning

confidence: 99%

Establishing Self-Healing and Seamless Connectivity among IoT Networks Using Kalman Filter

Srinidhi

Shreyas²,

Naresh

2022

Journal of Robotics and Control

View full text Add to dashboard Cite

The Internet of Things (IoT) is the extension of Internet connectivity into physical devices and to everyday objects. Efficient mobility support in IoT provides seamless connectivity to mobile nodes having restrained resources in terms of energy, memory and link capacity. Existing routing algorithms have less reactivity to mobility. So, in this work, a new proactive mobility support algorithm based on the Kalman Filter has been proposed. Mobile nodes are provided with a seamless connectivity by minimizing the switching numbers between point of attachment which helps in reducing signaling overhead and power consumption. The handoff trigger scheme which makes use of mobility information in order to predict handoff event occurrence is used. Mobile nodes new attachment points and its trajectory is predicted using the Kalman-Filter. Kalman-Filter is a predictor-estimator method used for movement prediction is used in this approach. Kalman Filtering is carried out in two steps: i) Predicting and ii) Updating. Each step is investigated and coded as a function with matrix input and output. Self-healing characteristics is being considered in the proposed algorithm to prevent the network from failing and to help in efficient routing of data. Proposed approach achieves high efficiency in terms of movement prediction, energy efficiency, handoff delay and fault tolerance when compared to existing approach.

show abstract

Section: Related Workmentioning

confidence: 99%

Establishing Self-Healing and Seamless Connectivity among IoT Networks Using Kalman Filter

Srinidhi

Shreyas²,

Naresh

2022

Journal of Robotics and Control

View full text Add to dashboard Cite

show abstract

“…Various classifiers were applied on various features that had achieved better performance. In [12], ensembling of J48, NB, and ANN was achieved for predicting the locations of mobile crowd. Hybrid features were utilized to achieve the performance further.…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence and Metaheuristic-Based Location-Based Advertising

Rohilla

Chakraborty²,

Kaur

2022

Scientific Programming

View full text Add to dashboard Cite

Location-based services (LBS) are necessary for obtaining the important details since the user needs vary based on the location. Location-based advertising (LBA) are utilized for abandoning the user location and to offer assistance by using the obtained information. Therefore, an efficient machine learning and metaheuristic-based model referred as GANM is designed for LBS. Initially, the potential location information is evaluated utilizing the geographic information system (GIS). Thereafter, significant features are computed using the location data. Obtained features are then segmented to improve the process of LBS. Adaptive network-based fuzzy inference system (ANFIS) is then utilized to efficiently classify the user data. Finally, the optimization of classified documents is achieved using the nondominated sorting genetic algorithm-III (NSGA-III). Extensive experiments are performed to validate GANM for LBS. Comparative analyses reveal that GANM outperforms the competitive LBS models in terms of F-score, accuracy, sensitivity, specificity, and area under curve by 2.2734%, 2.3981%, 2.3947%, 2.4271%, and 2.1638%, respectively.

show abstract