Inferring Human Activity Recognition with Ambient Sound on Wireless Sensor Nodes

  title={Inferring Human Activity Recognition with Ambient Sound on Wireless Sensor Nodes},
  author={Etto L. Salomons and Paul J. M. Havinga and Henk van Leeuwen},
  journal={Sensors (Basel, Switzerland)},
A wireless sensor network that consists of nodes with a sound sensor can be used to obtain context awareness in home environments. However, the limited processing power of wireless nodes offers a challenge when extracting features from the signal, and subsequently, classifying the source. Although multiple papers can be found on different methods of sound classification, none of these are aimed at limited hardware or take the efficiency of the algorithms into account. In this paper, we compare… 
Human activity recognition using sensor recordings from passive infrared and microwave radar sensors
An experiment has been conducted by installing three identical data collection modules in a controlled environment for human activity recording and different approaches for feature extraction and preliminary tests for activity recognition were conducted.
Data Collection Module for Human Activity Recognition
A data collection system that will enable detection and monitoring of human activity using very low-cost, unobtrusive passive infrared and microwave radar sensors and is composed of Arduino microcontroller, SD card module and real time clock module.
Evaluation of Five Classifiers for Children Activity Recognition with Sound as Information Source and Akaike Criterion for Feature Selection
This work uses environmental sound as data source to perform the activities recognition and classification, evaluating the accuracy of the k-Nearest Neighbor (kNN), Support Vector Machines (SVM), Random Forests (RF), Extra Trees (ET) and Gradient Boosting (GB) algorithms in the generation of a Recognition and classification model.
Audio Features Extraction to Develop a Child Activity Recognition Model Using Support Vector Machine to Monitoring Security in a Smart City
A model for classifying children’s activities is presented based on the Support Vector Machine (SVM) algorithm, which is trained with features extracted from the audio samples of each of the activities defined for analysis: running, playing, crying and walking.
A Novel Approach Based on Time Cluster for Activity Recognition of Daily Living in Smart Homes
A two-stage approach is proposed to recognize the activities of a single resident using temporal and spatial features and demonstrates that the proposed approach favorably outperforms the one-dimensional model.
Machine Learning as enabler of Design -to-Robotic -Operation
This essay promotes Artificial Intelligence (AI) via Machine Learning (ML) as a fundamental enabler of technically intelligent built-environments. It does this by detailing ML’s successful
A High-Resolution Intelligence Implementation based on Design-to-Robotic-Production and -Operation Strategies
The present implementation attempts to provide a fundamentally different approach to intelligent built-environments, and to promote a highly sophisticated alternative to existing intelligent solutions whose disconnection between architectural considerations and computational services limits their operational scope and impact.
Robotic Building as Integration of Design-to-Robotic-Production & Operation
Robotic Building (RB) implies both physically built robotic environments and robotically supported building processes that require design-to-production and operation chains that may be robotically driven.
Correction to: Robotic Building as Integration of Design-to-Robotic-Production and -Operation
This chapter describes previous work aiming to integrate D2RP&O processes by linking performance-driven design with robotic production and user-driven building operation.


A Survey on the Feasibility of Sound Classification on Wireless Sensor Nodes
This work surveys how sound is used in the literature for global sound classification, age and gender classification, emotion recognition, person verification and identification and indoor and outdoor environmental sound classification to conclude that for indoor context awareness, the low-cost algorithms for feature extraction perform equally well as the more computationally-intensive variants.
A Study on Versatile Recognition using Haar-like Features
A world first versatile recognition algorithm has been proposed to process image, sound, and 3-D acceleration signals with a common framework at low computational cost and is evaluated on various sound recognition problems such as speech/nonspeech classification, gender recognition, speaker recognition, emotion recognition, and environmental sound recognition.
A Survey of Online Activity Recognition Using Mobile Phones
This paper reviews the studies done so far that implement activity recognition systems on mobile phones and use only their on-board sensors, and discusses their limitations and present various recommendations for future research.
Multioccupant Activity Recognition in Pervasive Smart Home Environments
An overview of existing approaches and current practices for activity recognition in multioccupant smart homes is provided, which presents the latest developments and highlights the open issues in this field.
On the use of spectro-temporal features for the IEEE AASP challenge ‘detection and classification of acoustic scenes and events’
It is demonstrated that the proposed spectro-temporal features achieve a better recognition accuracy than MFCCs.
Acoustic Scene Classification
An account of the state-of-the-art in acoustic scene classification (ASC), the task of classifying environments from the sounds they produce, and a range of different algorithms submitted for a data challenge to provide a general and fair benchmark for ASC techniques.
Acoustic Scene Classification: Classifying environments from the sounds they produce
An account of the state of the art in acoustic scene classification (ASC), the task of classifying environments from the sounds they produce, and a range of different algorithms submitted for a data challenge to provide a general and fair benchmark for ASC techniques.
Low-Complex Environmental Sound Recognition Algorithms for Power-Aware Wireless Sensor Networks
This paper aims to provide a chronology of the events leading up to and including the publication of the manuscript, as well as some of the individuals who contributed to it.
Survey on speech emotion recognition: Features, classification schemes, and databases
Comparative Study of the Baum-Welch and Viterbi Training Algorithms Applied to Read and Spontaneous Speech Recognition
Though Viterbi training yields a good performance in most cases, sometimes it leads to suboptimal models, specially when using discrete HMMs to model spontaneous speech, when using continuous HMMs, Viter bi training reveals as good as Baum-Welch at a much lower cost.