2026-10-07T08:47:52Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33987616 2026-09-24T17:28:31Z category_146 category_12 category_734 category_931 category_811 portal_5 item_type_3 month_year_09_2026

<p>Noise robustness under IoT sensor perturbation.</p> Sasmita Kumari Pradhan (25105024) Suryakanth V. Gangashetty (25105027) Space Science Cell Biology Biological Sciences not elsewhere classified Information Systems not elsewhere classified Mathematical Sciences not elsewhere classified supporting reliable automation robust temporal modeling deep learning models xlink "> iot signal preprocessing reduced performance privacy concerns jaccard index intelligent interpretation improved detection human behavior healthcare monitoring health assessment feature extraction enhance safety energy efficiency dice coefficient data imbalance continuous sensing constrained environments computational complexity complex activities based classifiers anomaly recognition anomaly classification ambient sensors accurate activity <div><p>IoT-enabled smart homes require accurate activity classification to enhance safety, healthcare monitoring, and energy efficiency through continuous sensing and intelligent interpretation of human behavior. Common approaches employ wearable or ambient sensors, signal preprocessing, feature extraction, and deep learning models such as CNNs, LSTMs, BiLSTM, and attention-based classifiers. These techniques generally achieve high classification accuracy, robust temporal modeling, and improved detection of complex activities, supporting reliable automation, health assessment, and anomaly recognition. Challenges include sensor noise, data imbalance, privacy concerns, limited generalization across homes, computational complexity, and reduced performance in real-time or resource-constrained environments. The proposed IoT framework integrates normalized sensor vectors with BiLSTM and attention mechanisms, achieving improved temporal feature learning and more accurate activity and anomaly classification. The proposed BiLSTM-Attention framework achieved 97.2% accuracy, 95.1% Dice coefficient, 90.6% Jaccard index, 96.5% sensitivity, and 98.1% specificity on the smart home activity dataset.</p></div> 2026-09-24T17:28:22Z Dataset Dataset 10.1371/journal.pone.0355599.t003 https://figshare.com/articles/dataset/_p_Noise_robustness_under_IoT_sensor_perturbation_p_/33987616 CC BY 4.0