Filters








227,854 Hits in 4.4 sec

Performance metrics for activity recognition

Jamie A. Ward, Paul Lukowicz, Hans W. Gellersen
2011 ACM Transactions on Intelligent Systems and Technology  
In this article, we introduce and evaluate a comprehensive set of performance metrics and visualisations for continuous activity recognition (AR).  ...  Building on an earlier initial work on the topic, we develop a frame-based visualisation and corresponding set of class-skew invariant metrics for the one class versus all evaluation.  ...  Judging by Performance Metrics for Activity Recognition • 6:15 Note that it is permissible for r x to overlap with both part of e 1 and part of e 2 (and possibly more events).  ... 
doi:10.1145/1889681.1889687 fatcat:rya4nlcaureb7ii7kc7i2rxkpi

Exploring Techniques for Vision Based Human Activity Recognition: Methods, Systems, and Evaluation

Xin Xu, Jinshan Tang, Xiaolong Zhang, Xiaoming Liu, Hong Zhang, Yimin Qiu
2013 Sensors  
In this paper, we provide a comprehensive survey of the recent development of the techniques, including methods, systems, and quantitative evaluation of the performance of human activity recognition.  ...  In image and video analysis, human activity recognition is an important research direction.  ...  Evaluation Metrics for Activity Recognition Effectively evaluating the performance of methods and systems for activity recognition in videos or image sequences is important for the improvement of surveillance  ... 
doi:10.3390/s130201635 pmid:23353144 pmcid:PMC3649413 fatcat:pssdgo3rpbak7czx6zn47rvjla

Introduction to the special issue on intelligent systems for activity recognition

Daqing Zhang, Matthai Philipose, Qiang Yang
2011 ACM Transactions on Intelligent Systems and Technology  
Jamie Ward, Paul Lukowicz, and Hans Gellersen propose a set of new performance metrics for activity recognition in "Performance Metrics for Activity Recognition."  ...  -Evaluation metric for activity recognition is a fundamental research issue that is worth studying.  ... 
doi:10.1145/1889681.1889682 fatcat:y7vxivvkfrhxnf7e4alq4adcsi

A statistical framework to evaluate virtual screening

Wei Zhao, Kirk E Hevener, Stephen W White, Richard E Lee, James M Boyett
2009 BMC Bioinformatics  
Although many other metrics, such as RIE, BEDROC, and pROC that emphasize "early recognition" have been proposed, there are no rigorous statistical guidelines for determining the thresholds and performing  ...  Also no comparisons have been made between these metrics under a statistical framework to better understand their performances.  ...  Ball for his suggestive comments and the St Jude Hartwell Center for providing computational assistance.  ... 
doi:10.1186/1471-2105-10-225 pmid:19619306 pmcid:PMC2722655 fatcat:zaxfqbfg6rh57lmyfiypznq6ui

Comparative Performance Analysis of Neural Networks Architectures on H2O Platform for Various Activation Functions [article]

Yuriy Kochura, Sergii Stirenko, Yuri Gordienko
2017 arXiv   pre-print
In this paper, we present the results of testing neural networks architectures on H2O platform for various activation functions, stopping metrics, and other parameters of machine learning algorithm.  ...  This result can have crucial influence for opitmization of available and new machine learning methods, especially for image recognition problems.  ...  We found that generalization performance has very strong dependence on activation function and very slight dependence on stopping metric.  ... 
arXiv:1707.04940v1 fatcat:fohdbbdsbjg7fba2kz4aszxtdi

Human Health Activity Recognition Algorithm in Wireless Sensor Networks Based on Metric Learning

Dejie Sun, Jie Zhang, Shuai Zhang, Xin Li, Hangong Wang, Xin Ning
2022 Computational Intelligence and Neuroscience  
Based on the small sample problem and the linear indivisibility of real samples encountered in metric learning, this paper proposes a human activity recognition algorithm for wireless sensor networks.  ...  Human activity recognition algorithm for wireless sensor networks uses human activity recognition algorithm to solve the singularity of intraclass divergence matrix, so as to reduce the impact of small  ...  Human Activity Recognition Algorithm for Wireless Sensor Networks Based on Metric Learning. Metric learning can be traced back to some early research.  ... 
doi:10.1155/2022/4204644 pmid:35479601 pmcid:PMC9038378 fatcat:e5bjjij5bbfnti57pf4bjb4baa

Robust Human Activity Recognition based on Deep Metric Learning

Mubarak Abdu-Aguye, Walid Gomaa
2019 Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics  
In this work we investigate the use of Deep Metric Learning in the domain of activity recognition.  ...  We use a deep Triplet Network to generate fixed-length descriptors from activity samples for purposes of classification.  ...  In this work we apply deep metric learning specifically to activity recognition data.  ... 
doi:10.5220/0007916806560663 dblp:conf/icinco/Abdu-AguyeG19a fatcat:6hp3p5t3izfrbbxqfmad6npbie

Selective Sampling Strategies to Conserve Power in Context Aware Devices

Brian French, Daniel P. Siewiorek, Asim Smailagic, Michael Deisher
2007 2007 11th IEEE International Symposium on Wearable Computers  
These metrics include: accuracy as the percentage of time between samples that sampled activity matches true activity, average latency of detecting a change in activity, the percentage of missed activities  ...  We analyze the use of selective sampling strategies to aid in power conservation in sensor platforms for context-aware systems.  ...  Acknowledgments Additionally, we would like to thank Uwe Maurer and Anthony Rowe for eWatch support.  ... 
doi:10.1109/iswc.2007.4373783 dblp:conf/iswc/FrenchSSD07 fatcat:khr6iegf3fak3ib4qpexd4wqeq

Dendritic morphology predicts pattern recognition performance in multi-compartmental model neurons with and without active conductances

Giseli de Sousa, Reinoud Maex, Rod Adams, Neil Davey, Volker Steuber
2014 Journal of Computational Neuroscience  
All relationships found for passive neuron models also hold, even in more accentuated form, for neurons with active membranes.  ...  In this paper we examine how a neuron's dendritic morphology can affect its pattern recognition performance.  ...  To study the effect of active conductances on the relationship between dendritic morphology and pattern recognition performance, and to compare this relationship for active and passive model neurons with  ... 
doi:10.1007/s10827-014-0537-1 pmid:25380637 pmcid:PMC4350002 fatcat:czggp6kxj5b2hlmkukoutfzb2y

Towards a Clustering Guided Hierarchical Framework for Sensor-Based Activity Recognition

Aiguo Wang, Shenghui Zhao, Huan-Chao Keh, Guilin Chen, Diptendu Sinha Roy
2021 Sensors  
Accordingly, how to measure the relationships among activities and construct an activity recognizer for better distinguishing the confusing activities remains critical.  ...  Afterwards, we design a hierarchical activity recognition framework under the guidance of the confusion relationships to reduce the recognition errors between similar activities.  ...  For performance metrics, accuracy, precision, recall, and F1 are used to assess the power of an activity recognizer. F1, the harmonic mean of precision and recall.  ... 
doi:10.3390/s21216962 pmid:34770269 pmcid:PMC8587318 fatcat:zpmd2qilmrg5jmrmvd5sixeep4

Co-recognition of Human Activity and Sensor Location via Compressed Sensing in Wearable Body Sensor Networks

Wenyao Xu, Mi Zhang, Alexander A. Sawchuk, Majid Sarrafzadeh
2012 2012 Ninth International Conference on Wearable and Implantable Body Sensor Networks  
Existing research work either extracts location information from certain activity signals or takes advantage of the sensor location information as a priori to achieve better activity recognition performance  ...  To validate the effectiveness of our approach, we did a pilot study for the task of recognizing 14 human activities and 7 on body-locations.  ...  Hassan Ghasemzadeh of Wireless Health Institute in UCLA for the experimental dataset and discussion.  ... 
doi:10.1109/bsn.2012.14 dblp:conf/bsn/XuZSS12 fatcat:4vbj5kai2fe4dgadsqueqc5rii

An online method for estimating grazing and rumination bouts using acoustic signals in grazing cattle

José O. Chelotti, Sebastián R. Vanrell, Luciano S. Martinez Rau, Julio R. Galli, Alejandra M. Planisich, Santiago A. Utsumi, Diego H. Milone, Leonardo L. Giovanini, H. Leonardo Rufiner
2020 Computers and Electronics in Agriculture  
In this study, an online algorithm called bottom-up foraging activity recognizer (BUFAR) is proposed. The method is based on the recognition of jaw movements  ...  However, there is no online acoustic method for the recognition of rumination and grazing bouts that can be implemented in a low-cost device.  ...  The recognition of grazing and rumination bouts was evaluated with specific metrics for activity recognition.  ... 
doi:10.1016/j.compag.2020.105443 fatcat:xv3n4kky5rfrlfqtpupmaz66wa

The effect of dendritic morphology on pattern recognition in the presence of active conductances

Giseli de Sousa, Maex Reinoud, Adams Rod, Davey Neil, Steuber Volker
2011 BMC Neuroscience  
We also investigated suitable ranges for model parameters such as dendritic compartment length and synaptic strength, among other Figure 1 Pattern recognition performance in active and passive models.  ...  In the present study, we analyse how the dendritic morphology affects the pattern recognition performance in active models.  ...  for active as compared to passive dendrites.  ... 
doi:10.1186/1471-2202-12-s1-p315 fatcat:wdcrrsd4pzhipmns5spzz4cvfu

Privacy Enhanced Multimodal Neural Representations for Emotion Recognition

Mimansa Jaiswal, Emily Mower Provost
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this work, we show how multimodal representations trained for a primary task, here emotion recognition, can unintentionally leak demographic information, which could override a selected opt-out option  ...  emotion recognition.  ...  We define performance for emotion recognition as the ability of the model to correctly classify either activation or valence into 3 categories: low, medium, and high.  ... 
doi:10.1609/aaai.v34i05.6307 fatcat:r6iazmlvjzdavopnx6nlhoc6uq

A novel smartphone-based activity recognition modeling method for tracked equipment in forest operations

Ryer M. Becker, Robert F. Keefe, Peng Chen
2022 PLoS ONE  
, and delay) were classified with the performance metrics for individual elements of the best model (50 Hz, 10 second window, 90% window overlap) falling within the following ranges: area under the curve  ...  This study is the first example of developing a smartphone-based activity recognition model for ground-based forest equipment.  ...  Acknowledgments The authors would like to thank University of Idaho Experimental Forest undergraduate forestry staff who planned and administered these stand treatments and Triple B Excavation for allowing  ... 
doi:10.1371/journal.pone.0266568 pmid:35385537 pmcid:PMC8985955 fatcat:4qwu5gtapjhjxcydamzinlycca
« Previous Showing results 1 — 15 out of 227,854 results