A Two-Tier Approach for Fall Detection Systems

সংরক্ষণ করুন:

গ্রন্থ-পঞ্জীর বিবরন
প্রকাশিত:	Journal of Computer Science and Control Systems vol. 15, no. 2 (Oct 2022), p. 5
প্রধান লেখক:	Akintotimi, Akinyemi Omololu
অন্যান্য লেখক:	Oladele, Rufus Olalere
প্রকাশিত:	University of Oradea
বিষয়গুলি:	Datasets Fall detection Algorithms Smartphones Older people Machine learning Support vector machines False alarms Kernel functions Sensors Activities of daily living
অনলাইন ব্যবহার করুন:	Citation/Abstract Full Text Full Text - PDF
ট্যাগগুলো:	ট্যাগ যুক্ত করুন কোনো ট্যাগ নেই, প্রথমজন হিসাবে ট্যাগ করুন!

বিবরন
সার সংক্ষেপ:	- A critical performance drawback of most fall detection systems is high false alarms. These false alarms are due to the imbalanced mix of the "fall" and "non-fall" data contained in the processed datasets on one hand, and the inherent limitation of the processing algorithms, on the other hand. To tackle this false alarm problem, a two-tier solution approach which entails Synthetic Minority Over-Sampling Technique (SMOTE) and hybrid of two machine learning algorithms (Multiple-Kernel Support Vector Machine (MK-SVM) and Multinomial Naive Bayes (MNB), hereafter known as SMOTE-based MKSVM-MNB is proposed. The results of simulation experiments performed using two open-source datasets namely SisFall Dataset and UMAFall Dataset show that SMOTE-based MKSVM-MNB significantly outperforms MKSVM, MNB and MKSVM-MNB in terms of the number of False Negatives (FN) recorded. Also, MKSVM-MNB significantly outperforms MKSVM and MNB in terms of FN.
আইএসএসএন:	1844-6043 2067-2101 1841-7213
সম্পদ:	Advanced Technologies & Aerospace Database