Volume 66, Issue 4

Sleep staging is an important basis for diagnosing sleep-related problems. In this paper, an attention based convolutional network for automatic sleep staging is proposed. The network takes time-frequency image as input and predict sleep stage for each 30-s epoch as output. For each CNN feature maps, our model generate attention maps along two separate dimensions, time and filter, and then multiplied to form the final attention map. Residual-like fusion structure is used to append the attention map to the input feature map for adaptive feature refinement. In addition, to get the global feature representation with less information loss, the generalized mean pooling is introduced. To prove the efficacy of the proposed method, we have compared with two baseline method on sleep-EDF data set with different setting of the framework and input channel type, the experimental results show that the paper model has achieved significant improvements in terms of overall accuracy, Cohen’s kappa, MF1, sensitivity and specificity. The performance of the proposed network is compared with that of the state-of-the-art algorithms with an overall accuracy of 83.4%, a macro F1-score of 77.3%, κ  = 0.77, sensitivity = 77.1% and specificity = 95.4%, respectively. The experimental results demonstrate the superiority of the proposed network.

The feasibility of using time–frequency (TF) ridges estimation is investigated on multi-channel electroencephalogram (EEG) signals for emotional recognition. Without decreasing accuracy rate of the valence/arousal recognition, the informative component extraction with low computational cost will be examined using multivariate ridge estimation. The advanced TF representation technique called multivariate synchrosqueezing transform (MSST) is used to obtain well-localized components of multi-channel EEG signals. Maximum-energy components in the 2D TF distribution are determined using TF-ridges estimation to extract instantaneous frequency and instantaneous amplitude, respectively. The statistical values of the estimated ridges are used as a feature vector to the inputs of machine learning algorithms. Thus, component information in multi-channel EEG signals can be captured and compressed into low dimensional space for emotion recognition. Mean and variance values of the five maximum-energy ridges in the MSST based TF distribution are adopted as feature vector. Properties of five TF-ridges in frequency and energy plane (e.g., mean frequency, frequency deviation, mean energy, and energy deviation over time) are computed to obtain 20-dimensional feature space. The proposed method is performed on the DEAP emotional EEG recordings for benchmarking, and the recognition rates are yielded up to 71.55, and 70.02% for high/low arousal, and high/low valence, respectively.

Emotion is one of the most complex and difficult expression to be predicted. Nowadays, many recognition systems that use classification methods have focused on different types of emotion recognition problems. In this paper, we aimed to propose a multimodal fusion method between electroencephalography (EEG) and electrooculography (EOG) signals for emotion recognition. Therefore, before the feature extraction stage, we applied different angle-amplitude transformations to EEG–EOG signals. These transformations take arbitrary time domain signals and convert them two-dimensional images named as Angle-Amplitude Graph (AAG). Then, we extracted image-based features using a scale invariant feature transform method, fused these features originates basically from EEG–EOG and lastly classified with support vector machines. To verify the validity of these proposed methods, we performed experiments on the multimodal DEAP dataset which is a benchmark dataset widely used for emotion analysis with physiological signals. In the experiments, we applied the proposed emotion recognition procedures on the arousal-valence dimensions. We achieved (91.53%) accuracy for the arousal space and (90.31%) for the valence space after fusion. Experimental results showed that the combination of AAG image features belonging to EEG–EOG signals in the baseline angle amplitude transformation approaches enhanced the classification performance on the DEAP dataset.

It is well known that many physiological phenomena are modeled accurately and effectively using fractional operators and systems. This type of modeling is due mainly to the dynamical link between fractional-order systems and the fractal structures of the physiological systems. The automatic characterization of the premature ventricular contraction (PVC) is very important for early diagnosis of patients with different life-threatening cardiac diseases. In this paper, a classification scheme of normal and PVC beats of the electrocardiogram (ECG) signal is proposed. The clustering features used for normal and PVC beats discrimination are the parameters of the commensurate order linear fractional model of the frequency content of the QRS complex of the ECG signal. A series of tests and comparisons have been performed to evaluate and validate the efficiency of the proposed PVC classification algorithm using the MIT-BIH arrhythmia database. The proposed PVC classification method has achieved an overall accuracy of 94.745%, a specificity of 95.178% and a sensitivity of 90.021% using all the 48 records of the database.

Blood pressure is a reliable indicator of many cardiac arrhythmias and rheological problems. This study proposes a clinical set-up using conventional monitoring systems to estimate systolic and diastolic blood pressures continuously based on two photoplethysmogram signals (PPG) taken from the earlobe and toe. Several amendments were applied to conventional clinical monitoring devices to construct our project plan. We used two monitors to acquire two PPGs, one ECG, and invasive blood pressure as the reference to evaluate the estimation accuracy. One of the most critical requirements was the synchronization of the acquired signals that was accomplished by using ECG as the time reference. Following data acquisition and preparation procedures, the performance of each PPG signal alone and together was investigated using deep convolutional neural networks. The proposed architecture was evaluated on 32 records acquired from 14 patients after cardiovascular surgery. The results showed a better performance for toe PPG in comparison with earlobe PPG. Moreover, they indicated the algorithm accuracy improves if both signals are applied together to the network. According to the British Hypertension Society standards, the results achieved grade A for both blood pressure measurements. The mean and standard deviation of estimation errors were +0.3 ± 4.9 and +0.1 ± 3.2 mmHg for systolic and diastolic BPs, respectively. Since the method is based on conventional monitoring equipment and provides a high estimation consistency, it can be considered as a possible alternative for inconvenient invasive BP monitoring in clinical environments.

Benign paroxysmal positional vertigo (BPPV) is a clinical condition. The existing diagnostic methods cannot determine the specific location of otolith on the short or long brachial sides. Thus, visual and quantitative evaluation of the existing clinical standard diagnostic modality Dix–Hallpike test is needed to improve medical efficiency. Our goal was to develop a real-time virtual simulation system to assess a BPPV treatment manipulation. In this study, we used the proposed simulation system to observe otolith movement during a posterior semicircular canal BPPV diagnostic test, and to analyze the diagnostic mechanisms and strategies. Through visual cluster analysis of otolith position and analysis of otolith movement time in the standard Dix–Hallpike test, we can find that the positions of otoliths are relatively scattered, especially on the z -axis ( z 1  = 10.67 ± 3.98), and the fall time of otoliths at different positions has relatively large changes ( t 1  = 22.21 ± 1.40). But in the modified experiment z 2  = 4.93 ± 0.32 and t 2  = 26.21 ± 0.28. The experimental results show that the simulation system could track the state and the movement of otolith in real-time, which is of great significance for understanding the diagnostic mechanisms of BPPV evaluations and improving the diagnostic method.

Rehabilitation at home is rapidly increasing. Although successful results are achieved with treatment methods applied in rehabilitation clinics, there are also some disadvantages in this process, such as dependence on an expert and high costs. Developments in mechatronic technologies have accelerated the development of assistive devices which are designed for use at home. One of the rehabilitation applications is on a hemiplegic hand. In previous studies, some useful devices have been developed for hand rehabilitation. In this study, we suggest a new, low-cost and wearable robotic glove for hand rehabilitation. The specific component of this device is the spring and cable driven system proposed for transmission of motion and force. The device was tested on both unimpaired participants and patients with the hemiplegic hand, and it was proven to be beneficial for hand rehabilitation. As a result of trials with unimpaired participants, the muscle activation of the extensor digitorum and the flexor carpi radialis were increased by 184.1 and 197.8% respectively. The weight of the device was less than 400 g, thanks to 3D printed parts.

The identification of gastrointestinal (GI) motility disorders requires the evaluation of regional GI transit, and the development of alternative methodologies in animals has a significant impact on translational approaches. Therefore, the purpose of this study was to validate an easy and low-cost methodology (alternate current biosusceptometry – ACB) for the assessment of regional GI transit in rats through images. Rats were fed a test meal containing magnetic tracer and phenol red, and GI segments (stomach, proximal, medial and distal small intestine, and cecum) were collected to assess tracer’s retention at distinct times after ingestion (0, 60, 120, 240, and 360 min). Images were obtained by scanning the segments, and phenol red concentration was determined by the sample’s absorbance. The temporal retention profile, geometric center, gastric emptying, and cecum arrival were evaluated. The correlation coefficient between methods was 0.802, and the temporal retention of each segment was successfully assessed. GI parameters yielded comparable results between methods, and ACB images presented advantages as the possibility to visualize intrasegmental tracer distribution and the automated scan of the segments. The imaging approach provided a reliable assessment of several parameters simultaneously and may serve as an accurate and sensitive approach for regional GI research in rats.

Uncontrolled movements of laparoscopic instruments can lead to inadvertent injury of adjacent structures. The risk becomes evident when the dissecting instrument is located outside the field of view of the laparoscopic camera. Technical solutions to ensure patient safety are appreciated. The present work evaluated the feasibility of an automated binary classification of laparoscopic image data using Convolutional Neural Networks (CNN) to determine whether the dissecting instrument is located within the laparoscopic image section. A unique record of images was generated from six laparoscopic cholecystectomies in a surgical training environment to configure and train the CNN. By using a temporary version of the neural network, the annotation of the training image files could be automated and accelerated. A combination of oversampling and selective data augmentation was used to enlarge the fully labeled image data set and prevent loss of accuracy due to imbalanced class volumes. Subsequently the same approach was applied to the comprehensive, fully annotated Cholec80 database. The described process led to the generation of extensive and balanced training image data sets. The performance of the CNN-based binary classifiers was evaluated on separate test records from both databases. On our recorded data, an accuracy of 0.88 with regard to the safety-relevant classification was achieved. The subsequent evaluation on the Cholec80 data set yielded an accuracy of 0.84. The presented results demonstrate the feasibility of a binary classification of laparoscopic image data for the detection of adverse events in a surgical training environment using a specifically configured CNN architecture.

Current test standards of osteosynthetic implants examine the bone plate and screw separately leading to unrealistic load scenarios and unknown performance of the system as a whole, which prevents the identification of characteristic failures in clinical use. A standardized static and dynamic four-point bending test (ASTM F382) was performed on a bone plate. Based on that standard, an advanced implant system test (IST) was designed and performed to test a mechanical construct consisting of a bone plate, screws and an artificial bone substitute out of Polyoxymethylene (POM). The test object was an osteosynthetic system to treat fractured ulna bones. Both results of the conventional and advanced test method were analyzed and compared to one another. The static results show a similar yield point (YP) relative to the bending moment with just 9% difference. Dynamic results show a bi-phasic behavior of the displacement vs. cycle data for the IST. The secondary phase can be defined as a constantly increasing plastic deflection or ratcheting effect quantified by its slope in mm per one million cycles, leading to a 10 times higher slope for the IST than the conventional test. The IST has a high impact on the test results and the resultant interpretation of the mechanical behavior of the osteosynthetic system. A constantly increasing plastic deflection might lead to fatigue failures and to a loss of the mechanical durability. The development of new standardizations referring to the whole system within reasonable boundary conditions of individual biomechanical applications is crucial for high quality mechanical analysis.

Materials used for dental crowns show a wide range of variety, and a dentist’s choice can depend on several factors such as patient desires, esthetics, tooth factors, etc. One of the most important issues for implant surgery is the primary stability and it should be provided to minimize the risks of screw loosening, failed osseointegration, or nonunion. The current study aims to present the Finite Element Analysis (FEA)-based material selection strategy for a dental crown in terms of reducing the aforementioned risks of dental implants. A virtual surgery mandible model obtained using MIMICS software was transferred to the ANSYS and material candidates determined using CES software were compared using FEA. The results indicated that Zr0 2 +Y 2 O 3 (zirconia) has shown a 12.79% worse performance compared to Au83-88/Pt4-12/Pd4.5-6 alloy in terms of abutment loosening. On the other hand, zirconia is the most promising material for dental crowns in terms of the stability of the bone-implant complex. Therefore, it may show the best overall performance for clinical use. Moreover, as suggested in this study, a better outcome and more accurate predictions can be achieved using a patient-specific FEA approach for the material selection process.