Biomedical Engineering / Biomedizinische Technik最新文献

Researchers have been working to magnify mental workload (MWL) modeling for a long time. An important aspect of its modeling is feature selection as it interprets bulky and high-dimensional EEG data and enhances the accuracy of the classification model. In this study, a feature selection technique is proposed to obtain an optimized feature set with multiple domain features that can contribute to classifying the MWL at three distinct levels. The brain signals from thirteen healthy subjects were examined while they attended an intrinsic MWL of spotting differences in a set of similar pictures. The Recursive Feature Elimination (RFE) technique selects the robust features from the feature matrix by eliminating all the least contributing features. Along with the Support Vector Machine (SVM), the overall classification accuracy with the proposed RFE reached 0.913 from 0.791 surpassing the other techniques mentioned. The results of the study also significantly display the variation in the mean values of the selected features at the three workload levels (p<0.05). This model can become the principle for defining the workload level quantification applicable to diverse fields like neuroergonomics study, intelligent assistive devices (ADs) development, blue-chip technology exploration, cognitive evaluation of students, power plant operators, traffic operators, etc.

Objectives: Electroencephalogram (EEG) is often used to detect mental fatigue because of its real-time characteristic and objective nature. However, because of the individual variability of EEG among different individuals, tedious and time-consuming calibration sessions are needed.

Methods: Therefore, we propose a multi-source domain adaptation network for inter-subject mental fatigue detection named FLDANN, which is short for focal loss based domain-adversarial training of neural network. As for mental state feature extraction, power spectrum density is extracted based on the Welch method from four sub-bands of EEG signals. The features of the source domain and target domain are fed into the FLDANN network. The contributions of FLDANN include: (1) It uses the idea of adversarial to reduce feature differences between the source and target domain. (2) A loss function named focal loss is used to assign weights to source and target domain samples.

Results: The experiment result shows that when the number of the source domains increases, the classification accuracy of domain-adversarial training of neural network (DANN) gradually decreases and finally tends to be stable. The proposed method achieves an accuracy of 84.10% ± 8.75% on the SEED-VIG dataset and 65.42% ± 7.47% on the self-designed dataset. In addition, the proposed method is compared with other domain adaptation methods and the results show that the proposed method outperforms those state-of-the-art methods.

Conclusions: The result proves that the proposed method is able to solve the problem of individual differences across subjects and to solve the problem of low classification performance of multi-source domain transfer learning.

Implant-associated infection is the main reasons for implant failure. Titanium and titanium alloy are currently the most widely used implant materials. However, they have limited antibacterial performance. Therefore, enhancing the antibacterial ability of implants by surface modification technology has become a trend of research. Tantalum is a potential implant coating material with good biological properties. With the development of surface modification technology, tantalum coating becomes more functional through improvement. In addition to improving osseointegration, its antibacterial performance has also become the focus of attention. In this review, we provide an overview of the latest strategies to improve tantalum antibacterial properties. We demonstrate the potential of the clinical application of tantalum in reducing implant infections by stressing its advantageous properties.

Objectives: Synchronisation of wireless inertial measurement units in human movement analysis is often achieved using event-based synchronisation techniques. However, these techniques lack precise event generation and accuracy. An inaccurate synchronisation could lead to large errors in motion estimation and reconstruction and therefore wrong analysis outputs.

Methods: We propose a novel event-based synchronisation technique based on a magnetic field, which allows sub-sample accuracy. A setup featuring Shimmer3 inertial measurement units is designed to test the approach.

Results: The proposed technique shows to be able to synchronise with a maximum offset of below 2.6 ms with sensors measuring at 100 Hz. The investigated parameters suggest a required synchronisation time of 8 s.

Conclusions: The results indicate a reliable event generation and detection for synchronisation of wireless inertial measurement units. Further research should investigate the temperature changes that the sensors are exposed to during human motion analysis and their influence on the internal time measurement of the sensors. In addition, the approach should be tested using inertial measurement units from different manufacturers to investigate an identified constant offset in the accuracy measurements.

Objectives: Denoising autoencoder (DAE) with a single hidden layer of neurons can recode a signal, i.e., converting the original signal into a noise-reduced signal. The DAE approach has shown a good performance in denoising bio-signals, like electrocardiograms (ECG). In this paper, we study the effect of correlated, uncorrelated and jittered datasets on the performance of the DAE model.

Methods: Vectors of multiple concatenated ECG segments of simultaneously recorded Einthoven recordings I, II, III are considered to establish the following dataset cases: (1) correlated, (2) uncorrelated, and (3) jittered. We consider our previous work in finding the optimal number of hidden neurons receiving the input signal with respect to signal quality and computational burden by applying Akaike's information criterion. To evaluate DAE, these datasets are corrupted with six types of noise, namely mix noise (MX), motion artifact noise (MA), electrode movement (EM), baseline wander (BW), Gaussian white noise (GWN) and high-frequency noise (HFN), to simulate real case scenario. Spectral analysis is used to study the effects of noise whose power spectrum may overlap with the power spectrum of the wanted signal on DAE performance.

Results: The simulation results show (a) that the number of hidden neurons to denoise multiple correlated ECG is much lower than for jittered signals, (b) QRS-complex based ECG alignment preferable, (c) noises with slightly overlapping power spectrum, like BW and HFN, can be easily removed with sufficient number of neurons, while the noise with completely overlapping spectrum, like GWN, requires a very low-dimensional and thus coarser reduction to recover the signal.

Conclusions: The performance of DAE model in terms of signal-to-noise ratio improvement and the required number of hidden neurons can be improved by utilizing the correlation among simultaneous Einthoven I, II, III records.

Heart diseases represent a serious medical condition that can be fatal. Therefore, it is critical to investigate the measures of its early prevention. The Mel-scale frequency cepstral coefficients (MFCC) feature has been widely used in the early diagnosis of heart abnormity and achieved promising results. During feature extraction, the Mel-scale triangular overlapping filter set is applied, which makes the frequency response more in line with the human auditory property. However, the frequency of the heart sound signals has no specific relationship with the human auditory system, which may not be suitable for processing of heart sound signals. To overcome this issue and obtain a more objective feature that can better adapt to practical use, in this work, we propose an equal scale frequency cepstral coefficients (EFCC) feature based on replacing the Mel-scale filter set with a set of equally spaced triangular overlapping filters. We further designed classifiers combining convolutional neural network (CNN), recurrent neural network (RNN) and random forest (RF) layers, which can extract both the spatial and temporal information of the input features. We evaluated the proposed algorithm on our database and the PhysioNet Computational Cardiology (CinC) 2016 Challenge Database. Results from ten-fold cross-validation reveal that the EFCC-based features show considerably better performance and robustness than the MFCC-based features on the task of classifying heart sounds from novel patients. Our algorithm can be further used in wearable medical devices to monitor the heart status of patients in real time with high precision, which is of great clinical importance.

A theoretical investigation of multi-layer Bragg Reflector (BR) structure to design highly sensitive temperature sensor is proposed to measure the temperature over a wide range. Characteristic-Matrix (CM) mathematical tool is used to design and analyse the proposed temperature sensor. A 1D Distributed Bragg Reflector multi-layer structure is used to design and analyse the sensing characteristics of the proposed sensor. Periodic modulation in the Refractive-Index (RI) of the two materials, high and low, forms DBR multi-layer structure. Germanium and air are used as the two alternate materials of BR for high and low dielectric layers respectively. Parameters of many semiconductor materials, including germanium, varies with temperature. Here we have considered RI variation of germanium with the temperature to model and design the proposed sensor. A defect layer is introduced at the center of multi-layer structure to obtain the resonating mode for an incident electromagnetic wave. The sensor can detect temperature over a wide range from 100 to 550 K. A resonating mode, shifting towards different wavelength region is observed for the temperature variations. The influence of increase in the DBR layers (N) and defect cavity geometrical length (l_D) is studied. The obtained results conclude that the cavity defect length and BR layers affects the sensing parameters of the designed sensor. The obtained RI sensitivity, Q-factor, temperature sensitivity and detection limit of the sensor are 2.323 μm/RIU, 115,000, 1.18 nm/K and 9.024 × 10^-6 RIU respectively. Theoretically obtained transmission spectrum was validated using Monte Carlo simulation.

Objectives: Although the use of short implants is becoming more common for patients with atrophic alveolar ridges, their use is still quite limited. This is due to the lack of data of long-term survival compared to standard-length implants. The aim of this study was to determine the load in the bone and implant system with different superstructures.

Methods: Three kinds of prosthetic restorations were created on short implants based on CT-Data. Two short implants with different macro-geometries were used. The implants were inserted in idealised posterior lower mandibular segments and afterwards restored with a crown, a double splinted crown, and a bridge.

Results: The analysis was performed under load of 300 N either divided between a mesial and distal point or as a point load on the pontic/mesial crown. The different design of the implant systems had a noticeable influence on the stress in the cortical bone, in the implant system, and the displacement of the superstructure as well.

Conclusions: Compared with implants of standard length, higher stresses were observed, which can lead early failure of the implant during the healing period or a late cervical bone resorption. Precise indications are essential for short implants to avoid the failure of short implants.

Objectives: The most crucial part in the diagnosis of cancer is severity grading. Gleason's score is a widely used grading system for prostate cancer. Manual examination of the microscopic images and grading them is tiresome and consumes a lot of time. Hence to automate the Gleason grading process, a novel deep learning network is proposed in this work.

Methods: In this work, a deep learning network for Gleason grading of prostate cancer is proposed based on EfficientNet architecture. It applies a compound scaling method to balance the dimensions of the underlying network. Also, an additional attention branch is added to EfficientNet-B7 for precise feature weighting.

Result: To the best of our knowledge, this is the first work that integrates an additional attention branch with EfficientNet architecture for Gleason grading. The proposed models were trained using H&E-stained samples from prostate cancer Tissue Microarrays (TMAs) in the Harvard Dataverse dataset.

Conclusions: The proposed network was able to outperform the existing methods and it achieved an Kappa score of 0.5775.