scholarly journals Error Bounds for Online Predictions of Linear-Chain Conditional Random Fields: Application to Activity Recognition for Users of Rolling Walkers

2011 ◽  
Author(s):  
M. Sinn ◽  
P. Poupart
Keyword(s):  
Activity Recognition ◽  
Error Bounds ◽  
Random Fields ◽  
Conditional Random Fields ◽  
Linear Chain

Semi-Markov conditional random fields for accelerometer-based activity recognition

2010 ◽  
Vol 35 (2) ◽  
pp. 226-241 ◽  
Author(s):  
La The Vinh ◽  
Sungyoung Lee ◽  
Hung Xuan Le ◽  
Hung Quoc Ngo ◽  
Hyoung Il Kim ◽  
...  
Keyword(s):  
Activity Recognition ◽  
Random Fields ◽  
Conditional Random Fields

Inference of activity patterns from urban sensing data using conditional random fields

2021 ◽  
pp. 239980832110168
Author(s):  
Yi Zhu
Keyword(s):  
Smart Card ◽  
Random Fields ◽  
Conditional Random Fields ◽  
Linear Chain ◽  
Major Barrier ◽  
Sensing Data ◽  
Activity Types ◽  
Urban Sensing ◽  
Spatio Temporal ◽  
Transit Smart Card

The study of human activity–travel patterns for urban planning has evolved a long way in theories, methodologies, and applications. However, the scarcity of data has become a major barrier for the advancement of research in the field. Recently, the proliferation of urban sensing and location-based devices generates voluminous streams of spatio-temporal registered information. In this study, we propose an approach using the linear-chain Conditional Random Fields (CRFs) model to learn the spatio-temporal correspondences of different types of activities and the inter-dependencies among sequential activities from training dataset such as the household travel or time use surveys, and to infer the hidden activity types associated with urban sensing data. The performance of the CRFs model is compared against the Random Forest (RF) model, which has been used in a number of existing studies. The results show that the linear-chain CRFs models generally outperform the RF counterparts with respect to classification accuracy of activity types, in particular for those travelers having more outdoor daily activities. The proposed methodology is demonstrated by reconstructing the activity landscape of the surrounding area of a major Mass Rail Transit station in Singapore using the transit smart card transaction data. The inferred activities from the transit smart card data are expected to complement the ground surveys and improve our understanding of the interactions of different components of activities/travels as well as the relationship between urban space and human activities.

scholarly journals Human activity recognition using conditional random fields and privileged information

2016 ◽  
Author(s):  
Μιχαήλ Βρίγκας
Keyword(s):  
Activity Recognition ◽  
Human Activity ◽  
Random Fields ◽  
Conditional Random Fields ◽  
Human Activity Recognition ◽  
Privileged Information

Η διατριβή ασχολείται με το πρόβλημα της αναγνώρισης της ανθρώπινης δραστηριότητας από εικονοσειρές και απλές εικόνες, το οποίο ανήκει στην ευρύτερη περιοχή της υπολογιστικής όρασης. Για την επίλυση του προβλήματος χρησιμοποιήθηκαν τα υπό συνθήκη τυχαία πεδία συνδυάζοντας δεδομένα από πολλαπλές πηγές. Επιπλέον, προτάθηκε μια καινούρια μέθοδος ταξινόμησης που βασίζεται στην προνομιακή πληροφορία, η oποία δίδεται ως επιπλέων είσοδος στο μοντέλο και είναι διαθέσιμη μόνο στην φάση της εκπαίδευσης αλλά όχι στην φάση του ελέγχου. Τα πειραματικά αποτελέσματα δείχνουν ότι αυτού του είδους η πληροφορία βοηθά στο να δημιουργήσουμε έναν ισχυρότερο ταξινομητή απ' ότι κάποιος θα μάθαινε χωρίς αυτήν, ενώ αυξάνει σημαντικά την ακρίβεια της αναγνώρισης του μοντέλου.

scholarly journals Beyond Word Attention: Using Segment Attention in Neural Relation Extraction

2019 ◽  
Author(s):  
Bowen Yu ◽  
Zhenyu Zhang ◽  
Tingwen Liu ◽  
Bin Wang ◽  
Sujian Li ◽  
...  
Keyword(s):  
Random Fields ◽  
Latent Variables ◽  
Large Scale ◽  
Conditional Random Fields ◽  
Marginal Distribution ◽  
State Of The Art ◽  
Linear Chain ◽  
Relation Extraction ◽  
Word Attention ◽  
Attention Weight

Relation extraction studies the issue of predicting semantic relations between pairs of entities in sentences. Attention mechanisms are often used in this task to alleviate the inner-sentence noise by performing soft selections of words independently. Based on the observation that information pertinent to relations is usually contained within segments (continuous words in a sentence), it is possible to make use of this phenomenon for better extraction. In this paper, we aim to incorporate such segment information into neural relation extractor. Our approach views the attention mechanism as linear-chain conditional random fields over a set of latent variables whose edges encode the desired structure, and regards attention weight as the marginal distribution of each word being selected as a part of the relational expression. Experimental results show that our method can attend to continuous relational expressions without explicit annotations, and achieve the state-of-the-art performance on the large-scale TACRED dataset.

Sign in / Sign up

Export Citation Format

Share Document