Proceedings Article10.1109/UEMCON.2018.8796766
Activity Learning and Recognition Using Margin Setting Algorithm in Smart Homes
Ogbonna Michael Igwe,Yi Wang,George C. Giakos +2 more
- 01 Nov 2018
- pp 653-658
6
TL;DR: A novel supervised learning algorithm called margin setting (MSA) is introduced and applied to ARAS (Activity Recognition with Ambient Sensing) dataset to help recognize patterns in the activities of daily living of two residents in a smart home intelligent environment.
read more
Abstract: Intelligent environments is receiving lots of attention in the research community. With lots of algorithms developed over the years to model activity and pattern recognition, most algorithms are still not suitable for activity learning. Early research was focused on home automation but recent research is moving towards an intelligent environment that is capable of identifying trends and patterns and make effective decisions. Making this feat a possibility requires extensive research in the fields of artificial intelligence, machine learning and statistical learning. These tools enable an intelligent environment to analyze, control and make intelligent decision according to the condition set by the user. In this paper, we introduce a novel supervised learning algorithm called margin setting (MSA) and apply it to ARAS (Activity Recognition with Ambient Sensing) dataset to help recognize patterns in the activities of daily living (ADL) of two residents in a smart home intelligent environment. Our goal is to introduce an accurate pattern recognition and activity learning method. The experimental results show the accuracy and efficiency of the proposed method using the dataset, which contains 20 different binary sensors with 27 different activities.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A novel parallel learning algorithm for pattern classification
Yi Wang,Jian Fu,Bingyang Wei +2 more
- 01 Dec 2019
TL;DR: The results show the proposed PMSA gains significant improvements in terms of execution time, with a promising speedup compared to the single-threaded CPU counterpart, and is compared with another two state-of-the-art classification algorithms: the artificial neural network and the support vector machine.
Predicting of Sleep Behaviour in Smart Homes Based on Multi-residents Using Machine Learning Techniques
Manjaiah Doddaghatta Huchaiah,John W. Kasubi +1 more
- 01 Jul 2021
TL;DR: In this paper, the authors used Logistic regression (RL), Linear Discriminant Analysis (LDA), KNN, Naive Bayes (NB), Classification and Regression Trees (CRT) and Support Vector Machine (SVM) to learn and analyze sleep behavior in relation to other activities of which impacts to the health issues of the residents.
2
Feature Selection Strategy for Multi-residents Behavior Analysis in Smart Home Environment
John W. Kasubi,D. H. Manjaiah +1 more
- 01 Jan 2022
TL;DR: In this article, a predictive model that performs best for daily living activities (ADLs) using Activity Recognition with Ambient Sensing (ARAS) using ARAS dataset was developed.
2
Review on the Application Areas of Decision-Making Algorithms in Smart Homes
TL;DR: In this paper , the authors present a literature review on the current state of decision-making algorithms in smart homes and identify the current intentions of involving humans in-the-loop.
Inferring Human Activity Using Wearable Sensors
Sudarshan S. Chawathe
TL;DR: This paper presents methods using wearable sensors to infer human activities and identify individuals, achieving higher classification accuracy than previous work, with minimal impact from reduced sensor data streams, beneficial for network bandwidth and energy efficiency.
References
Anomaly detection: A survey
TL;DR: This survey tries to provide a structured and comprehensive overview of the research on anomaly detection by grouping existing techniques into different categories based on the underlying approach adopted by each technique.
Isolation Forest
F.T. Liu,Kai Ming Ting,Zhi-Hua Zhou +2 more
- 15 Dec 2008
TL;DR: The use of isolation enables the proposed method, iForest, to exploit sub-sampling to an extent that is not feasible in existing methods, creating an algorithm which has a linear time complexity with a low constant and a low memory requirement.
5.4K
•Proceedings Article
Activity recognition from accelerometer data
Nishkam Ravi,Nikhil Dandekar,Preetham Mysore,Michael L. Littman +3 more
- 09 Jul 2005
TL;DR: This paper reports on the efforts to recognize user activity from accelerometer data and performance of base-level and meta-level classifiers, and Plurality Voting is found to perform consistently well across different settings.
Learning Setting-Generalized Activity Models for Smart Spaces
TL;DR: Smart home activity recognition systems can learn generalized models for common activities that span multiple environment settings and resident types to help solve the challenge of integrating smart home technology into everyday life.
Distributed recognition of human actions using wearable motion sensor networks
Allen Y. Yang,Roozbeh Jafari,S. Shankar Sastry,Ruzena Bajcsy +3 more
- 01 Apr 2009
TL;DR: A distributed recognition framework to classify continuous human actions using a low-bandwidth wearable motion sensor network, called distributed sparsity classifier (DSC), validates the robustness of the distributed recognitionframework on an unreliable wireless network and demonstrates the ability of DSC to conserve sensor energy for communication while preserve accurate global classification.