Distance-Constraint k-Nearest Neighbor Searching in Mobile Sensor Networks

Han, Youn-Hee; Park, Kisung; Hong, Jun-Ki; Ulamin, Noor; Lee, Young Koo

doi:10.3390/s150818209

Cited by 8 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As it has been shown, those models that include high computation seem to perform better. Actually, K-nearest neighbor outperformed many other solutions; however, its implementation in battery feed devices could drain the battery in a relatively short period of time [ 40 ].…”

Section: Fall Detection With a Wrist-worn Sensormentioning

confidence: 99%

Improving Fall Detection Using an On-Wrist Wearable Accelerometer

Khojasteh

Villar

Chira

et al. 2018

Sensors

121

101

View full text Add to dashboard Cite

Fall detection is a very important challenge that affects both elderly people and the carers. Improvements in fall detection would reduce the aid response time. This research focuses on a method for fall detection with a sensor placed on the wrist. Falls are detected using a published threshold-based solution, although a study on threshold tuning has been carried out. The feature extraction is extended in order to balance the dataset for the minority class. Alternative models have been analyzed to reduce the computational constraints so the solution can be embedded in smart-phones or smart wristbands. Several published datasets have been used in the Materials and Methods section. Although these datasets do not include data from real falls of elderly people, a complete comparison study of fall-related datasets shows statistical differences between the simulated falls and real falls from participants suffering from impairment diseases. Given the obtained results, the rule-based systems represent a promising research line as they perform similarly to neural networks, but with a reduced computational cost. Furthermore, support vector machines performed with a high specificity. However, further research to validate the proposal in real on-line scenarios is needed. Furthermore, a slight improvement should be made to reduce the number of false alarms.

show abstract

Section: Fall Detection With a Wrist-worn Sensormentioning

confidence: 99%

Improving Fall Detection Using an On-Wrist Wearable Accelerometer

Khojasteh

Villar

Chira

et al. 2018

Sensors

121

101

View full text Add to dashboard Cite

show abstract

“…Moreover, several works on similarity queries in sensor network are also proposed [25][26][27][28][29][30][31][32]. In this paper, we focus on the spatial search in road sensor networks on the air by proposing a fully distributed air index (called IEI) to process different spatial queries, including kNN query, range query, and CkNN query.…”

Section: Data Broadcast Algorithms For Spatial Search In Road Networkmentioning

confidence: 99%

A novel distributed air index for efficient spatial query processing in road sensor networks on the air

Shu

Zhu

et al. 2016

Int J Communication

View full text Add to dashboard Cite

Recent development of wireless technology and smart mobile devices has spurred intense research efforts to address spatial queries. In particular, an increasing interest for tackling spatial query processing in broadcast environments has been observed. To the best of our knowledge, most of the existing work on this problem has assumed an Euclidean space. However, for real applications, query clients move within a road sensor network, where the distance between a data object and a query is determined by the connectivity of the road sensor network. This paper explores the problem of spatial query processing in road sensor networks by means of wireless data broadcast. We present an efficient method to partition the recordkeeping information about the underlying road sensor network and its associated objects, by which we develop a fully distributed air index, called integrated exponential index, based on an extended version of the Hilbert curve. We also propose efficient client-side algorithms to facilitate the processing of several kinds of spatial queries, including kNN query, CkNN query, and range query. Finally, extensive simulation experiments have been conducted to demonstrate the strengths of our proposed techniques. access for relatively heavily loaded systems. A year and a half ago, soccer fans from around the world arrived in Brasilia to watch the 2014 FIFA World Cup. After a game, many people would like to locate good nearby restaurants. Because there could be tons of people doing the search at the same time, an ideal solution in this case would be to provide spatial query processing using data broadcast.Earlier approaches to designing broadcast-based spatial query processing methods [2-7] had assumed that MCs and searched objects were located in an Euclidean space. In real-life situations, however, MCs normally move along a road sensor network, and the Euclidean distance may not properly reflect real road sensor network distance [8]. Thus, the existing spatial query processing methods proposed for Euclidean space are inapplicable to process spatial queries in road sensor networks. Recently, researchers have begun to zero in on the problem. Li et al. [9] addressed the issue of processing CNN queries in road networks on the air and proposed an network Voronoi diagrams (NVDs)-based distributed air index to support query processing. One key limitation of the proposed method is that it processes CkNN queries with k D 1. Sun et al. [10] presented an air index called network partition index (NPI) to support spatial query processing in road networks on the air and proposed efficient algorithms to process different spatial queries such as kNN query, range query, and CNN query. NPI is, however, not a fully distributed structure, and thus, each query client will have to wait for the arrival of the index part followed by the whole index before starting its query processing, which could lead to long access latency and tuning time. In this paper, we aim to overcome these limitations and propose a fully distributed air ...

show abstract

“…A straightforward, well-known approach of interpreting such feature vectors are k -Nearest Neighbor ( k -NN) classifiers [ 42 ]. There is no need to train k -NNs, but the distance of the features of a sample to all training samples has to be computed, in order to classify the sample as those class, that is mostly represented in the k closest training samples.…”

Section: Introductionmentioning

confidence: 99%

Synthesis of Common Arabic Handwritings to Aid Optical Character Recognition Research

Dinges

Al-Hamadi

Elzobi

et al. 2016

Sensors

View full text Add to dashboard Cite

Document analysis tasks such as pattern recognition, word spotting or segmentation, require comprehensive databases for training and validation. Not only variations in writing style but also the used list of words is of importance in the case that training samples should reflect the input of a specific area of application. However, generation of training samples is expensive in the sense of manpower and time, particularly if complete text pages including complex ground truth are required. This is why there is a lack of such databases, especially for Arabic, the second most popular language. However, Arabic handwriting recognition involves different preprocessing, segmentation and recognition methods. Each requires particular ground truth or samples to enable optimal training and validation, which are often not covered by the currently available databases. To overcome this issue, we propose a system that synthesizes Arabic handwritten words and text pages and generates corresponding detailed ground truth. We use these syntheses to validate a new, segmentation based system that recognizes handwritten Arabic words. We found that a modification of an Active Shape Model based character classifiers—that we proposed earlier—improves the word recognition accuracy. Further improvements are achieved, by using a vocabulary of the 50,000 most common Arabic words for error correction.

show abstract

Distance-Constraint k-Nearest Neighbor Searching in Mobile Sensor Networks

Cited by 8 publications

References 19 publications

Improving Fall Detection Using an On-Wrist Wearable Accelerometer

Improving Fall Detection Using an On-Wrist Wearable Accelerometer

A novel distributed air index for efficient spatial query processing in road sensor networks on the air

Synthesis of Common Arabic Handwritings to Aid Optical Character Recognition Research

Contact Info

Product

Resources

About