INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
I propose a novel active learning framework for activity recognition and server monitoring. My work is unique in that it takes limitations of the oracle into account when selecting sensor data for annotation by the oracle. This capacity constraint is manifested not only in the number of queries that a person can respond to in a given time-frame but also in the time lag between the query issuance and the oracle response. I introduce the notion of mindful active learning and propose a computational framework, called EMMA, to maximize the active learning performance taking informativeness of system data, query budget, and human memory into account. I formulate this optimization problem, propose an approach to model memory retention, discuss the complexity of the problem, and propose a greedy heuristic to solve the optimization problem.
I design an approach to perform mindful active learning in batch where multiple system observations are selected simultaneously for querying the oracle. I demonstrate the effectiveness of our approach using three publicly available activity datasets and by simulating oracles with various memory strengths. I show that the activity recognition accuracy ranges from 21% to 97% depending on memory strength, query budget, and difficulty of the machine learning task. Moreover, I show that the performance of our approach is at most 20% less than the experimental upper-bound and up to 80% higher than the experimental lower-bound.
To evaluate the performance of EMMA for batch active learning, I design two instantiations of EMMA to perform active learning in batch mode. I show that these algorithms improve the algorithm training time at the cost of a reduced accuracy in performance. Another finding in our work is that integrating clustering into the process of selecting sensor observations for batch active learning improves the activity learning performance by 11.1% on average, mainly due to reducing the redundancy among the selected sensor observations. I observe that mindful active learning is most beneficial when the query budget is small and/or the oracle’s memory is weak. This observation emphasizes advantages of utilizing mindful active learning strategies in mobile health settings that involve interaction with older adults and other populations with cognitive impairments.
"Memory Aware Active Learning Sensor for System Server Monitoring", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 9, page no.a245-a255, September-2023, Available :http://www.ijnrd.org/papers/IJNRD2309030.pdf
Downloads:
000118760
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn