Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386484865> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4386484865 endingPage "10031" @default.
- W4386484865 startingPage "10031" @default.
- W4386484865 abstract "Robot vacuum cleaners have gained widespread popularity as household appliances. One significant challenge in enhancing their functionality is to identify and classify small indoor objects suitable for safe suctioning and recycling during cleaning operations. However, the current state of research faces several difficulties, including the lack of a comprehensive dataset, size variation, limited visual features, occlusion and clutter, varying lighting conditions, the need for real-time processing, and edge computing. In this paper, I address these challenges by investigating a lightweight AI model specifically tailored for robot vacuum cleaners. First, I assembled a diverse dataset containing 23,042 ground-view perspective images captured by robot vacuum cleaners. Then, I examined state-of-the-art AI models from the existing literature and carefully selected three high-performance models (Xception, DenseNet121, and MobileNet) as potential model candidates. Subsequently, I simplified these three selected models to reduce their computational complexity and overall size. To further compress the model size, I employed post-training weight quantization on these simplified models. In this way, our proposed lightweight AI model strikes a balance between object classification accuracy and computational complexity, enabling real-time processing on resource-constrained robot vacuum cleaner platforms. I thoroughly evaluated the performance of the proposed AI model on a diverse dataset, demonstrating its feasibility and practical applicability. The experimental results show that, with a small memory size budget of 0.7 MB, the best AI model is L-w Xception 1, with a width factor of 0.25, whose resultant object classification accuracy is 84.37%. When compared with the most accurate state-of-the-art model in the literature, this proposed model accomplished a remarkable memory size reduction of 350 times, while incurring only a slight decrease in classification accuracy, i.e., approximately 4.54%." @default.
- W4386484865 created "2023-09-07" @default.
- W4386484865 creator A5083824997 @default.
- W4386484865 date "2023-09-06" @default.
- W4386484865 modified "2023-09-27" @default.
- W4386484865 title "Towards Indoor Suctionable Object Classification and Recycling: Developing a Lightweight AI Model for Robot Vacuum Cleaners" @default.
- W4386484865 cites W2883318486 @default.
- W4386484865 cites W2963122961 @default.
- W4386484865 cites W2967357336 @default.
- W4386484865 cites W3015848146 @default.
- W4386484865 cites W3048828116 @default.
- W4386484865 cites W3109500059 @default.
- W4386484865 cites W3119036516 @default.
- W4386484865 cites W3123139907 @default.
- W4386484865 cites W3125496003 @default.
- W4386484865 cites W3133852244 @default.
- W4386484865 cites W3144696002 @default.
- W4386484865 cites W3199194340 @default.
- W4386484865 cites W4200182737 @default.
- W4386484865 cites W4214753187 @default.
- W4386484865 cites W4220847164 @default.
- W4386484865 cites W4229018275 @default.
- W4386484865 cites W4294691337 @default.
- W4386484865 cites W4319430529 @default.
- W4386484865 cites W4320016118 @default.
- W4386484865 cites W4362663195 @default.
- W4386484865 cites W4385348938 @default.
- W4386484865 doi "https://doi.org/10.3390/app131810031" @default.
- W4386484865 hasPublicationYear "2023" @default.
- W4386484865 type Work @default.
- W4386484865 citedByCount "0" @default.
- W4386484865 crossrefType "journal-article" @default.
- W4386484865 hasAuthorship W4386484865A5083824997 @default.
- W4386484865 hasBestOaLocation W43864848651 @default.
- W4386484865 hasConcept C119857082 @default.
- W4386484865 hasConcept C127413603 @default.
- W4386484865 hasConcept C154945302 @default.
- W4386484865 hasConcept C17511633 @default.
- W4386484865 hasConcept C23795335 @default.
- W4386484865 hasConcept C2776775011 @default.
- W4386484865 hasConcept C31972630 @default.
- W4386484865 hasConcept C41008148 @default.
- W4386484865 hasConcept C44154836 @default.
- W4386484865 hasConcept C78519656 @default.
- W4386484865 hasConcept C90509273 @default.
- W4386484865 hasConceptScore W4386484865C119857082 @default.
- W4386484865 hasConceptScore W4386484865C127413603 @default.
- W4386484865 hasConceptScore W4386484865C154945302 @default.
- W4386484865 hasConceptScore W4386484865C17511633 @default.
- W4386484865 hasConceptScore W4386484865C23795335 @default.
- W4386484865 hasConceptScore W4386484865C2776775011 @default.
- W4386484865 hasConceptScore W4386484865C31972630 @default.
- W4386484865 hasConceptScore W4386484865C41008148 @default.
- W4386484865 hasConceptScore W4386484865C44154836 @default.
- W4386484865 hasConceptScore W4386484865C78519656 @default.
- W4386484865 hasConceptScore W4386484865C90509273 @default.
- W4386484865 hasIssue "18" @default.
- W4386484865 hasLocation W43864848651 @default.
- W4386484865 hasOpenAccess W4386484865 @default.
- W4386484865 hasPrimaryLocation W43864848651 @default.
- W4386484865 hasRelatedWork W1891287906 @default.
- W4386484865 hasRelatedWork W2160851558 @default.
- W4386484865 hasRelatedWork W2587231196 @default.
- W4386484865 hasRelatedWork W2810362730 @default.
- W4386484865 hasRelatedWork W2961085424 @default.
- W4386484865 hasRelatedWork W3025458026 @default.
- W4386484865 hasRelatedWork W3045301645 @default.
- W4386484865 hasRelatedWork W3193008118 @default.
- W4386484865 hasRelatedWork W4306674287 @default.
- W4386484865 hasRelatedWork W4366994599 @default.
- W4386484865 hasVolume "13" @default.
- W4386484865 isParatext "false" @default.
- W4386484865 isRetracted "false" @default.
- W4386484865 workType "article" @default.