Fall detection by using K-nearest neighbor algorithm on WSN data

Erdoğan, Şenol Zafer; Bilgin, Turgay Tugay; Cho, Juphil

doi:10.1109/glocomw.2010.5700306

Cited by 11 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As our project is based on image classification, video frames were extracted from the set of videos in (Erdogan et al, 2010). These videos contain falls and other normal physical activities scenes, such as sitting down, walking and standing up.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Fall Detection Using the Histogram of Oriented Gradients and Decision-Based Fusion

Ismail¹,

AlGabas²,

Bchir³

2020

Journal of Computer Science

View full text Add to dashboard Cite

As the number of fall incidents among elderly people and patients are continuously growing, researches boosted their researches to propose efficient automatic fall detection systems. In particular, they formulated the fall detection problem as a supervised learning task where some visual features are extracted from the video frames and used to automatically identify the position of a human as "Fall" or "Non-Fall" based on a model learned using labeled training frames. Despite the promising reported results, existing fall detection systems exhibit noticeable room for improvement. Learner fusion which builds multiple models and aggregates their respective decisions is an alternative that would improve the fall detection performance. In this paper, an image-based fall detection system that captures the visual property and the spatial position of the human body using the Histogram of Oriented Gradient from the video frames is proposed. Then, the extracted features are used to train three classification models. Namely, the Naïve Bayes, the K-Nearest Neighbors and the Support Vector Machine algorithms are adopted. Next, the majority vote is used to aggregate the decisions of the individual learners. The proposed system was assessed using a standard dataset and yielded promising results. Standard performance measures along with the statistical significance t-test were used to prove that the fall detection system based on majority vote fusion outperforms the individual classifier based approaches.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Samples from the dataset videos: (a) home, (b) coffee room, (c) office, (d) classroom(Erdogan et al, 2010).…”

mentioning

confidence: 99%

Fall Detection Using the Histogram of Oriented Gradients and Decision-Based Fusion

Ismail¹,

AlGabas²,

Bchir³

2020

Journal of Computer Science

View full text Add to dashboard Cite

show abstract

“…Then, cluster-head nodes detect the event type by matching the predefined event model and call corresponding actor nodes to move toward to the event area. Finally, actor nodes get the priority of events processing using a modified k-nearest neighbor algorithm (KNN) [10] with the slope information of event data. The logical diagram for 3-CEDF displayed in Fig.…”

Section: Concepts and Definitionsmentioning

confidence: 99%

“… , in which  is the expect value and 2  is the standard deviation. In all, there are 12 kinds of independent are randomly assigned in interval[1,10] separately. Different types of events will occur randomly in R at every moment during the simulation.…”

mentioning

confidence: 99%

A Novel Event Detection Framework for Wireless Sensor and Actor Networks

Wang¹,

Fei²,

Liu³

et al. 2016

jcm

View full text Add to dashboard Cite

Abstract-Wireless Sensor and Actor Network (WSAN) can observe the physical world using event detection methods by sensor nodes and implement appropriate operation by actor nodes. Compared with Wireless Sensor Network (WSN), WSAN set high requests for real-time, collaboration, mobility, etc. Therefore, the event detection methods applied to WSN cannot be adopted for WSAN. In this paper, we present a threelayer Cooperative Event Detection Framework (3-CEDF) for WSAN. Firstly, sensor nodes cooperate with each other to affirm the occurrence of events via voting mechanism. Then, cluster-head nodes use a modified K-means algorithm and a proposed type matching mechanism to detect the event types with the boundary information of event data. Finally, actor nodes get the priority of events processing using a modified knearest neighbor algorithm with the slope similarity measure. The performances of effectiveness, real-time, mobility and communication traffic for 3-CEDF are obtained through analysis and simulations, when 3-CEDF is compared to the centralized event detection method adopted for WSN.Index Terms-Wireless sensor and actor network, event detection, cooperative algorithm, type matching, similarity measure

show abstract

“…As researchers deepen their focus on fall algorithms, they began to study hidden Markov chains [6], dynamic naive Bayesian networks [8], support vector machines [9], Multi-weight neural network [9], and k nearest neighbors [11]. All of above based on the pattern recognition method applied to fall detection, these methods abstract the model data collected by the sensor for the classification of fall behavior, and have strong adaptability.…”

Section: Introductionmentioning

confidence: 99%

Fall detection system based on BiLSTM neural network

Ye¹,

2019

TMLAI

View full text Add to dashboard Cite

The purpose of this article is to analyze the characteristics of human fall behavior to design a fall detection system. The existing fall detection algorithms have problems such as poor adaptability, single function and difficulty in processing large data and strong randomness. Therefore, a long-term and short-term memory recurrent neural network is used to improve the effect of falling behavior detection by exploring the internal correlation between sensor data. Firstly, the serialization representation method of sensor data, training data and detection input data is designed. The BiLSTM network has the characteristics of strong ability to sequence modeling and it is used to reduce the dimension of the data required by the fall detection model. then, the BiLSTM training algorithm for fall detection and the BiLSTM-based fall detection algorithm convert the fall detection into the classification problem of the input sequence; finally, the BiLSTM-based fall detection system was implemented on the TensorFlow platform. The detection and analysis of system were carried out using a bionic experiment data set which mimics a fall. The experimental results verify that the system can effectively improve the accuracy of fall detection to 90.47%. At the same time, it can effectively detect the behavior of Near-falling, and help to take corresponding protective measures.

show abstract

Fall detection by using K-nearest neighbor algorithm on WSN data

Cited by 11 publications

References 12 publications

Fall Detection Using the Histogram of Oriented Gradients and Decision-Based Fusion

Fall Detection Using the Histogram of Oriented Gradients and Decision-Based Fusion

A Novel Event Detection Framework for Wireless Sensor and Actor Networks

Fall detection system based on BiLSTM neural network

Contact Info

Product

Resources

About