Browsing by Subject
Showing results 1401 to 1420 of 21215
< previous
next >
- Abstract— On-device computing in biomedical sensors have become attractive towards developing wearable health monitoring systems. The challenge is to make a compromise between the latency and complexity in a resource constrained implementation. This paper describes an on-device implementation of multi-level signal quality aware and quality controlled compression (MSQQCC) that enhances the compression factor while preserving the clinical features in a wearable photoplethysmography (PPG) sensing application. The multi-level quality assessment (QA) provides three eligible PPG qualities, viz., ‘excellent’, ‘good’ and ‘average’, based on which corresponding upper limits are set for further compression using a discrete wavelet transform, while the ‘corrupted’ segments are discarded. A pretrained multilayer perceptron neural network provides the optimal quantization level of coefficients. The residual data is separately compressed using an autoencoder. MSQQCC was evaluated with 300 mins of PPG data from 3 public data sets and 110 mins of data collected at laboratory. The end-to-end pipeline was implemented in a standalone system with ARM Cortex A53 controller, requiring 35.51 KB of memory and 1.8s latency to process 4s PPG data. The on-device QA achieved 98.45 % overall accuracy (Ac), which outperforms published works on PPG QA. The mean deviation of PPG clinical features by 5 %, with overall CR and PRD were 40.85 and 2.52, which are superior than many published works. A real-time transmission over Bluetooth shows improvement of energy efficiency by a significant factor and 34% extended battery life for wearable PPG sensor. The results are encouraging for adoption of MSQQCC in wearable biomedical health monitoring. 1
- Abstract—Arrhythmia is the most fatal for human being among all cardiovascular diseases. Early detection of arrhythmia beats, from long term ECG record, is helpful to start treatment and saving life of patients. In this work, we presented a patient- adaptive scheme to discriminate normal and three classes of arrhythmia beats from ECG signal. Instead of conventional features, the proposed method uses a kernel based modeling technique of the ECG beats and the model coefficients are used as the features to characterize different types of beats. In this semi automatic scheme, a global training set is combined with a local learning set to form a patient adaptive training set to develop a patient specific classifier model. The results are validated on MIT-BIH arrhythmia database and the performance of the proposed technique is validated by three classifiers namely, support vector machine (SVM), vector valued regularized kernel function approximation (VVRKFA) technique and k-nearest neighbour (KNN) classifiers. Experimental results indicate that the proposed patient adaptive classification scheme increases the global accuracy by 12 to 16% than that of the accuracy obtained without using patient specific beats to global training set. The highest average accuracy obtained using this method is 96.63%, which is comparable and even better than most of the works available in the literature. 1
- ACADEMIC ACHIEVERS 1
- Academic Departments: HITK 1
- Academic Insights and Future Prospects of Soft Robotics: Architecture, Material, Control and Application 1
- Academic Programmes 1
- Academic Value-added Programmes (AVAP) 1
- ACADS: An Automatic Computer Aided Diagnostic System for Oil Spill Detection and Classification in SAR Images 1
- Accelerating 5G success in India / By Praveen Cherian 1
- Accelerating crop domestication through genome editing for sustainable agriculture 1
- Accelerating digital-led recovery to the next normal - Sanjay Kaul 1
- Accelerating Indigenous R&D and Intellectual Property (IP) – CDOT is taking Digital India into the Future 1
- Accelerating Learning Performance of Facial Expression Recognition using Convolution Neural Network Umesh Chauan, Dineen Kulkarni and Shioanand Hiremath 1
- Accelerating Sustainable Hydropower Development Around the World 1
- Accelerating Time-Current Curve Computation of Induction Motor from Manufacturer Data 1
- Accenture invests in hologram company Looking Glass Factory 1
- Access To Geospatial Data 1
- Accessible Cooperative Learning of Web Information Streams with Progressively Developed Classes 1
- Accidental Convergence Can Quash The most Secure Air-Gaps 1
- Accomplishing Secure Personal Health Records Using Attribute Based Encryption in Cloud Computing 1