Investigation of a Method for EEG Signal De-Noising Based on the DIVA Model

The DIVA (Directions Into Velocities of Articulators) model is an adaptive neural network model that is used to control the movement of the analog vocal tract to generate words, syllables, or phonemes. The input signal to the DIVA model is the EEG (electroencephalogram) signal acquired from the human brain. However, due to the influence of power frequency interference and other forms of noise, the input signal can be non-stationary and can also contain a variety of multi-form waveforms in its instantaneous structure. Input of such a signal into the DIVA model affects normal speech processing. Therefore, based on the concept of sparse decomposition, this paper applies and improves an adaptive sparse decomposition model for feature extraction of the general EEG signal structure and then uses the Matching Pursuit algorithm to compute the optimal atom. The original EEG signal can then be represented by atoms in a complete atomic library. This model removes noise from the EEG signal resulting in a better signal than the wavelet transform method. Finally, applies the EEG signal de-noised by this model to DIAV model. Simulation results show that the method improves phonetic pronunciation greatly.

Effectiveness of the Diagnose-Intervene- Verify-Adjust (DIVA) model for integrated primary healthcare planning and performance improvement: an embedded mixed methods evaluation in Kaduna state, Nigeria

ObjectivesThis study evaluates the real-world effectiveness of Diagnose-Intervene-Verify-Adjust (DIVA), an innovative quality improvement mode, in improving primary healthcare (PHC) bottlenecks impeding health system performance in Kaduna, a northern Nigerian state.DesignAn embedded mixed method study design involving participant observation.SettingPHCs in 23 local government areas of Kaduna state, Nigeria.Participants138 PHC managers across the state (PHC directors and programme managers in the 23 local governments).InterventionDIVA is a four-step improvement model in which ‘Diagnose’ identifies constraints to effective coverage, ‘Intervene’ develops/implements action plans addressing constraints, while ‘Verify/Adjust’ monitor performance and revise plans.Primary and secondary outcome measuresThe model, as adapted in Nigeria, is designed to evaluate and improve the availability of health commodities, human resources, geographical accessibility, acceptability, continuous utilisation and quality of four PHC interventions (immunisation, integrated management of childhood illnesses, antenatal care and skilled birth attendance).Results183 bottlenecks were identified by local government teams across all interventions in 2013. 41% of bottlenecks concern human resources. Geographical access and availability of commodities ranked least. Availability of commodities was the most improved determinant although among the least constrained, probably indicating skewed implementation of operational plans. 1562 activities were planned to address identified bottlenecks in the state, of which only 568 (36%) were completely implementedConclusionOur study demonstrates that PHC planning using the DIVA model can potentially improve health system performance. However, effective implementation is critical and may require some central government oversight.