Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383503079> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4383503079 abstract "Nearly three-quarters of the total power used in the world is consumed by the built environment sector. Therefore, looking for viable methods to reduce building energy needs and decrease negative environmental repercussions is vital. By incorporating intelligence into applications, everyone in the current situation has become intelligent, which lessens the load of constant interruption or human control. By using Machine to Machine interactions, intelligence enables the ability to connect more real-time parameters and make moral judgments in perilous circumstances. The current study examined the framework, approach, and performance of currently available AI-based techniques. According to the research, choosing the best machine and deep learning model for a given task can be difficult. Among the primary areas of study in relation to the vast amounts of data collected is the viability in the practice of the used algorithms, both standard machine learning and the more recent branch known as deep learning. Present a quantitative analysis contrasting the effectiveness of conventional deep learning and machine learning strategies using the direction of human movement in detecting the applications based on the analogue pyroelectric infrared sensor (PIR) outputs. Here, Random Forest is used as the machine learning method because of its great prediction accuracy. Over deeper datasets, deeper CNNs outperform shallow models as a deep learning method. The study demonstrates that traditional Machine Learning performs with detecting values within the first few seconds, improving real-time detection. Additionally, it might be used on more smart buildings without upgrades." @default.
- W4383503079 created "2023-07-08" @default.
- W4383503079 creator A5045767970 @default.
- W4383503079 creator A5049246663 @default.
- W4383503079 creator A5051146250 @default.
- W4383503079 creator A5092072810 @default.
- W4383503079 date "2023-04-19" @default.
- W4383503079 modified "2023-09-25" @default.
- W4383503079 title "Enhanced Building Prediction for Smart City Surveillance" @default.
- W4383503079 cites W2070941356 @default.
- W4383503079 cites W2517724752 @default.
- W4383503079 cites W2551839599 @default.
- W4383503079 cites W2796394553 @default.
- W4383503079 cites W2907452654 @default.
- W4383503079 cites W2938520540 @default.
- W4383503079 cites W2945958815 @default.
- W4383503079 cites W2950981708 @default.
- W4383503079 cites W2952104003 @default.
- W4383503079 cites W2992270489 @default.
- W4383503079 cites W2992944009 @default.
- W4383503079 cites W2997876070 @default.
- W4383503079 cites W3016183705 @default.
- W4383503079 cites W3044032620 @default.
- W4383503079 cites W3082837347 @default.
- W4383503079 cites W3099146502 @default.
- W4383503079 cites W3106216373 @default.
- W4383503079 cites W3134378022 @default.
- W4383503079 cites W3135652008 @default.
- W4383503079 cites W3152576252 @default.
- W4383503079 cites W3159397852 @default.
- W4383503079 cites W3164343423 @default.
- W4383503079 cites W3167529752 @default.
- W4383503079 cites W4200404279 @default.
- W4383503079 cites W4290466955 @default.
- W4383503079 cites W4292551332 @default.
- W4383503079 cites W4292824450 @default.
- W4383503079 cites W4304092853 @default.
- W4383503079 cites W4311625830 @default.
- W4383503079 doi "https://doi.org/10.1109/icaecis58353.2023.10169956" @default.
- W4383503079 hasPublicationYear "2023" @default.
- W4383503079 type Work @default.
- W4383503079 citedByCount "0" @default.
- W4383503079 crossrefType "proceedings-article" @default.
- W4383503079 hasAuthorship W4383503079A5045767970 @default.
- W4383503079 hasAuthorship W4383503079A5049246663 @default.
- W4383503079 hasAuthorship W4383503079A5051146250 @default.
- W4383503079 hasAuthorship W4383503079A5092072810 @default.
- W4383503079 hasConcept C108583219 @default.
- W4383503079 hasConcept C119857082 @default.
- W4383503079 hasConcept C124101348 @default.
- W4383503079 hasConcept C127413603 @default.
- W4383503079 hasConcept C154945302 @default.
- W4383503079 hasConcept C169258074 @default.
- W4383503079 hasConcept C201995342 @default.
- W4383503079 hasConcept C25343380 @default.
- W4383503079 hasConcept C2780451532 @default.
- W4383503079 hasConcept C41008148 @default.
- W4383503079 hasConceptScore W4383503079C108583219 @default.
- W4383503079 hasConceptScore W4383503079C119857082 @default.
- W4383503079 hasConceptScore W4383503079C124101348 @default.
- W4383503079 hasConceptScore W4383503079C127413603 @default.
- W4383503079 hasConceptScore W4383503079C154945302 @default.
- W4383503079 hasConceptScore W4383503079C169258074 @default.
- W4383503079 hasConceptScore W4383503079C201995342 @default.
- W4383503079 hasConceptScore W4383503079C25343380 @default.
- W4383503079 hasConceptScore W4383503079C2780451532 @default.
- W4383503079 hasConceptScore W4383503079C41008148 @default.
- W4383503079 hasLocation W43835030791 @default.
- W4383503079 hasOpenAccess W4383503079 @default.
- W4383503079 hasPrimaryLocation W43835030791 @default.
- W4383503079 hasRelatedWork W2942650110 @default.
- W4383503079 hasRelatedWork W2968586400 @default.
- W4383503079 hasRelatedWork W3211546796 @default.
- W4383503079 hasRelatedWork W4223564025 @default.
- W4383503079 hasRelatedWork W4226246648 @default.
- W4383503079 hasRelatedWork W4281616679 @default.
- W4383503079 hasRelatedWork W4311106074 @default.
- W4383503079 hasRelatedWork W4312046277 @default.
- W4383503079 hasRelatedWork W4316087074 @default.
- W4383503079 hasRelatedWork W4322727400 @default.
- W4383503079 isParatext "false" @default.
- W4383503079 isRetracted "false" @default.
- W4383503079 workType "article" @default.