Keyword search (3,448 papers available)


Cluster based statistical feature extraction method for automatic bleeding detection in wireless capsule endoscopy video.

Author(s): Ghosh T, Fattah SA, Wahid KA, Zhu WP, Ahmad MO

Comput Biol Med. 2018 03 01;94:41-54 Authors: Ghosh T, Fattah SA, Wahid KA, Zhu WP, Ahmad MO

Article GUID: 29407997
A Crowdsensing Based Analytical Framework for Perceptional Degradation of OTT Web Browsing.

Author(s): Li K, Wang H, Xu X, Du Y, Liu Y, Ahmad MO

Sensors (Basel). 2018 May 15;18(5): Authors: Li K, Wang H, Xu X, Du Y, Liu Y, Ahmad MO

Article GUID: 29762493
Image denoising via overlapping group sparsity using orthogonal moments as similarity measure.

Author(s): Kumar A, Ahmad MO, Swamy MNS

ISA Trans. 2019 Feb;85:293-304 Authors: Kumar A, Ahmad MO, Swamy MNS

Article GUID: 30392726
Big Data-Driven Cellular Information Detection and Coverage Identification.

Author(s): Wang H, Xie S, Li K, Ahmad MO

Sensors (Basel). 2019 Feb 22;19(4): Authors: Wang H, Xie S, Li K, Ahmad MO

Article GUID: 30813353
Title:Big Data-Driven Cellular Information Detection and Coverage Identification.
Authors:Wang H,  Xie S,  Li K,  Ahmad MO
Link:https://www.ncbi.nlm.nih.gov/pubmed/30813353?dopt=Abstract
Category:Sensors (Basel)
PMID:30813353
Dept Affiliation: ENCS
1 College of Smart City, Beijing Union University, Beijing 100101, China. 161081210208@buu.edu.cn.
2 College of Smart City, Beijing Union University, Beijing 100101, China. 171081210207@buu.edu.cn.
3 College of Smart City, Beijing Union University, Beijing 100101, China. like@buu.edu.cn.
4 Department of Electrical and Computer Engineering, Concordia University, Montreal, QC H3G IM8, Canada. omair@ece.concordia.ca.

Description:

Big Data-Driven Cellular Information Detection and Coverage Identification.

Sensors (Basel). 2019 Feb 22;19(4):

Authors: Wang H, Xie S, Li K, Ahmad MO

Abstract

As one of the core data assets of telecom operators, base station almanac (BSA) plays an important role in the operation and maintenance of mobile networks. It is also an important source of data for the location-based service (LBS) providers. However, it is always less timely updated, nor it is accurate enough. Besides, it is not open to third parties. Conventional methods detect only the location of the base station (BS) which cannot satisfy the needs of network optimization and maintenance. Because of these drawbacks, in this paper, a big-data driven method of BSA information detection and cellular coverage identification is proposed. With the help of network-related data crowd sensed from the massive number of smartphone users in the live network, the algorithm can estimate more parameters of BSA with higher accuracy than conventional methods. The coverage capability of each cell was also identified in a granularity of small geographical grids. Computational results validate the proposed algorithm with higher performance and detection ability over the existing ones. The new method can be expected to improve the scope, accuracy, and timeliness of BSA, serving for wireless network optimization and maintenance as well as LBS service.

PMID: 30813353 [PubMed - indexed for MEDLINE]