Artificial intelligence proficient systems with neural network machine learning algorithms in nanoparticle size prediction application / 国际药学研究杂志

Artificial Intelligence (AI) indicates the usage of a computer to model intellectual performance with least human intercession. Modern progress in nanoparticle technology has facilitated the preparation of nanoparticle with a distinct size which in turn has expedited significant improvements in the field of nanomedicine. Predicting this characteristic would leap numerous preceding studies customarily needed to optimize formulations. This paper intends to develop Artificial Neural Network (ANN) for predicting the size of the silver nanoparticle (AgNP) with four input variables. Different algorithms were applied to train ANNs with several numbers of hidden layers, nodes and transfer functions by arbitrary selection. The estimation performance of the different model was evaluated, on training, validation and testing data sets in terms of Regression (R) and Mean Square Error (MSE). The optimized prediction model was proficient in predicting nanoparticle size for a broad range of conditions with better R and MSE values. The relative impact of each input variables on AgNP size was also determined. Results from this study contribute to design an effective green approach for obtaining nanoparticles, while the limited received materials are employed, and the merest size of nanoparticles will be achieved.

Study on the inverse problem of electrical impedance tomography based on self-diagnosis regularization / 生物医学工程学杂志

The inverse problem of electrical impedance tomography (EIT) is seriously ill-posed, which restricts the clinical application of EIT. Regularization is an important numerical method to improve the stability of the EIT inverse problem as well as the resolution of the imaging. This paper proposes a self-diagnosis regularization method based on Tikhonov regularization and diagonal weight regularization method (DWRM). Firstly, the ill-posedness of the inverse problem is analyzed by sensitivity. Then, the performance of the self-diagnosis regularization is analyzed through the singular value theory. Finally, some simulated experiments including simulations and flume experiment are carried out and verify that the self-diagnosis regularization has better image quality and anti-noise ability than those of traditional regularization methods. The self-diagnosis regularization method weakens the ill-posedness of inverse problem of EIT and can prompt the practical application of EIT.

Adaptive filtering method for EMG signal using bounded range artificial bee colony algorithm

In this paper, an adaptive artefact canceller is designed using the bounded range artificial bee colony (BR-ABC) optimization technique. The results of proposed method are compared with recursive least square and other evolutionary algorithms. The performance of these algorithms is evaluated in terms of signal-to-noise ratio (SNR), mean square error (MSE), maximum error (ME) mean, standard deviation (SD) and correlation factor (r). The noise attenuation capability is tested on EMG signal contaminated with power line and ECG noise at different SNR levels. A comparative study of various techniques reveals that the performance of BR-ABC algorithm is better in noisy environment. Our simulation results show that the ANC filter using BR-ABC technique provides 15 dB improvement in output average SNR, 63 and 83% reduction in MSE and ME, respectively as compared to ANC filter based on PSO technique. Further, the ANC filter designed using BR-ABC technique enhances the correlation between output and pure EMG signal.

Research on least square interpolation based fractional delay and mismatch for cochlear implant / 国际生物医学工程杂志

Objective The fractional realization of delayed parameters will occurs when using microphone array technology in cochlear implants. To study the design and mismatch feature of fractional delay filter so as to meet the requirement of fractional delay realization in cochlear implants. Methods According to the characteristics of small cochlear implants and delay requirements, a fractional delay filter was designed by least mean square method. Results The fractional delay filtering method based on least mean square interpolation can achieve fractional delay, and can minimize the average error and the mean square error of the whole frequency band. Conclusions The fractional delay filter based on least mean square interpolation has the features of mismatch and high-order flat error, which makes it have theoretical and engineering value and providing a parameter selection method for the design of fractional delay filter.

Application of multi-adaptive filter based on radial basis function neural network for real-time somatosensory evoked potential monitoring / 国际生物医学工程杂志

ObjectiveTo design multi-adaptive filter based on radial basis function (MAF-RBF) for efficiently extracting somatosensory evoked potential (SEP) in real-time SEP monitoring.MethodsWith the optimization of important parameters that influence the performance of radial basis function neural network,the performance of extracting SEP was compared to that of a multi-adaptive filter (MAF),which developed from the combination of well-developed adaptive noise canceller and adaptive signal enhancer.ResultsIn this simulation study,the outputs of MAF-RBF showed a similar waveform with SEP template signals,and a smoother waveform than the.output of MAF.ConclusionWith appropriate parameter values,MAF-RBFNN is able to extract the latency and amplitude of SEP from the extremely noisy background rapidly and reliably without averaging.