Subject-specific Case Research Articles

A rotary transformer cross-subject model for continuous estimation of finger joints kinematics and a transfer learning approach for new subjects.

Surface Electromyographic (sEMG) signals are widely utilized for estimating finger kinematics continuously in human-machine interfaces (HMI), and deep learning approaches are crucial in constructing the models. At present, most models are extracted on specific subjects and do not have cross-subject generalizability. Considering the erratic nature of sEMG signals, a model trained on a specific subject cannot be directly applied to other subjects. Therefore, in this study, we proposed a cross-subject model based on the Rotary Transformer (RoFormer) to extract features of multiple subjects for continuous estimation kinematics and extend it to new subjects by adversarial transfer learning (ATL) approach. We utilized the new subject's training data and an ATL approach to calibrate the cross-subject model. To improve the performance of the classic transformer network, we compare the impact of different position embeddings on model performance, including learnable absolute position embedding, Sinusoidal absolute position embedding, and Rotary Position Embedding (RoPE), and eventually selected RoPE. We conducted experiments on 10 randomly selected subjects from the NinaproDB2 dataset, using Pearson correlation coefficient (CC), normalized root mean square error (NRMSE), and coefficient of determination (R2) as performance metrics. The proposed model was compared with four other models including LSTM, TCN, Transformer, and CNN-Attention. The results demonstrated that both in cross-subject and subject-specific cases the performance of RoFormer was significantly better than the other four models. Additionally, the ATL approach improves the generalization performance of the cross-subject model better than the fine-tuning (FT) transfer learning approach. The findings indicate that the proposed RoFormer-based method with an ATL approach has the potential for practical applications in robot hand control and other HMI settings. The model's superior performance suggests its suitability for continuous estimation of finger kinematics across different subjects, addressing the limitations of subject-specific models.

A new height contouring method for severity prediction in cam-type hip joints: 20 subject-specific cases

Cam-type femoroacetabular impingement syndrome (FAIS) is characterised by a non-spherical continuation of the femoral head into the femoral head-neck junction and is associated with damage to the acetabular cartilage. Diagnostic methods based on cam shape are progressing from 2D radiographic measurements to 3D CT measures, providing greater insight. There is currently no consensus on how to describe the 3D cam lesion shape and subject-specific impingement mechanisms are difficult to determine.A novel 3D ‘contour’ method was used to describe the proximal femur of 20 cam-type hips. Five contours, analogous to height contours on a terrain map, were used to describe the femoral head-neck junction, capturing the progressive height of the cam lesion. From that description, the cam apex (a subject's largest alpha angle), cam extent (spread around the femoral head), cam location (position around the femoral head) and average acetabular coverage, were recorded. A previously developed hip impingement model was used to apply 126 activity-based motions to each subject-specific hip shape and predict impingement occurrence and depth of incursion past the acetabular rim. Correlations between shape measures and impingement occurrence were investigated.The two contours representing the lowest heights (close to the head best fit sphere and 1 mm greater than that) generated cam alpha angle and cam extent measurements which contained the typical clinical measures (Alpha: close to best fit 47°-98°, at 1 mm 45°–77°; Extent: close to best fit 0°–129°, at 1 mm 0°–100°). The remaining contours described the progressive height of the cam lesion up to 4 mm greater than the head radius. Impingement was predicted predominantly from the first 1 mm height of the cam, with only two subjects impinging at a cam height greater than 2 mm. Therefore, it is possible that adequate resection of the first 1 mm of cam height is the most critical in reducing a subject's impingement severity.Impingement occurrence was positively correlated with the cam apex (ρ = 0.84 close to best fit, ρ = 0.70 at 1 mm height), the cam extent (ρ = 0.68 close to best fit, ρ = 0.80 at 1 mm height) and the acetabular coverage (ρ = 0.50, at 1 mm height). However, in line with other work on cam impingement, correlations between any single shape measure and the risk of impingement were not strong enough to be used with confidence as predictive tools. This supports the further development of modelling tools which sufficiently capture the complex shape and can generate an impingement risk metric which accounts for joint motion.

Automated Seizure Detection Based on State-Space Model Identification.

In this study, we developed a machine learning model for automated seizure detection using system identification techniques on EEG recordings. System identification builds mathematical models from a time series signal and uses a small number of parameters to represent the entirety of time domain signal epochs. Such parameters were used as features for the classifiers in our study. We analyzed 69 seizure and 55 non-seizure recordings and an additional 10 continuous recordings from Thomas Jefferson University Hospital, alongside a larger dataset from the CHB-MIT database. By dividing EEGs into epochs (1 s, 2 s, 5 s, and 10 s) and employing fifth-order state-space dynamic systems for feature extraction, we tested various classifiers, with the decision tree and 1 s epochs achieving the highest performance: 96.0% accuracy, 92.7% sensitivity, and 97.6% specificity based on the Jefferson dataset. Moreover, as the epoch length increased, the accuracy dropped to 94.9%, with a decrease in sensitivity to 91.5% and specificity to 96.7%. Accuracy for the CHB-MIT dataset was 94.1%, with 87.6% sensitivity and 97.5% specificity. The subject-specific cases showed improved results, with an average of 98.3% accuracy, 97.4% sensitivity, and 98.4% specificity. The average false detection rate per hour was 0.5 ± 0.28 in the 10 continuous EEG recordings. This study suggests that using a system identification technique, specifically, state-space modeling, combined with machine learning classifiers, such as decision trees, is an effective and efficient approach to automated seizure detection.

Effect of number and placement of EEG electrodes on measurement of neural tracking of speech.

Measurement of neural tracking of natural running speech from the electroencephalogram (EEG) is an increasingly popular method in auditory neuroscience and has applications in audiology. The method involves decoding the envelope of the speech signal from the EEG signal, and calculating the correlation with the envelope of the audio stream that was presented to the subject. Typically EEG systems with 64 or more electrodes are used. However, in practical applications, set-ups with fewer electrodes are required. Here, we determine the optimal number of electrodes, and the best position to place a limited number of electrodes on the scalp. We propose a channel selection strategy based on an utility metric, which allows a quick quantitative assessment of the influence of a channel (or a group of channels) on the reconstruction error. We consider two use cases: a subject-specific case, where the optimal number and position of the electrodes is determined for each subject individually, and a subject-independent case, where the electrodes are placed at the same positions (in the 10-20 system) for all the subjects. We evaluated our approach using 64-channel EEG data from 90 subjects. In the subject-specific case we found that the correlation between actual and reconstructed envelope first increased with decreasing number of electrodes, with an optimum at around 20 electrodes, yielding 29% higher correlations using the optimal number of electrodes compared to all electrodes. This means that our strategy of removing electrodes can be used to improve the correlation metric in high-density EEG recordings. In the subject-independent case, we obtained a stable decoding performance when decreasing from 64 to 22 channels. When the number of channels was further decreased, the correlation decreased. For a maximal decrease in correlation of 10%, 32 well-placed electrodes were sufficient in 91% of the subjects.

Performance Enhancement of P300 Detection by Multiscale-CNN

The P300-based spelling system is one of the most popular brain–computer interface applications. Its success largely depends on performance, including the information transmission rate (ITR) and detection rate (i.e., accuracy). To achieve good performance, we proposed a multiscale convolutional neural network (MS-CNN) model that consists of seven layers. First, an upfront data set was used to train the MS-CNN, aiming to obtain a subject-unspecific model (universal model) for P300 detection. Second, this universal model was adapted by a portion of data derived from a subject to update the model to obtain a subject-specific model by incorporating a transfer learning technique. We applied the proposed model in the brain–computer interface (BCI) Controlled Robot Contest at the 2019 World Robot Conference, and our performance was the best among the teams in the contest. In the contest, ten healthy young subjects were randomly assigned by the contest committee to assess the model. Our model achieved the best P300 detection performance (higher accuracy with less repetition time). The ITR for the subject-unspecific case was 13.49 bits/min, while the ITR for the subject-specific case was 12.13 bits/min when the repetitions were fewer than six. It is believed that our method may pave a promising path for taking a further step toward efficient implementation of the P300-based spelling system.

Motor Imagery EEG Signals Decoding by Multivariate Empirical Wavelet Transform-Based Framework for Robust Brain–Computer Interfaces

The robustness and computational load are the key challenges in motor imagery (MI) based on electroencephalography (EEG) signals to decode for the development of practical brain-computer interface (BCI) systems. In this study, we propose a robust and simple automated multivariate empirical wavelet transform (MEWT) algorithm for the decoding of different MI tasks. The main contributions of this study are four-fold. First, the multiscale principal component analysis method is utilized in the preprocessing module to obtain robustness against noise. Second, a novel automated channel selection strategy is proposed and then is further verified with comprehensive comparisons among three different strategies for decoding channel combination selection. Third, a sub-band alignment method by utilizing MEWT is adopted to obtain joint instantaneous amplitude and frequency components for the first time in MI applications. Four, a robust correlation-based feature selection strategy is applied to largely reduce the system complexity and computational load. Extensive experiments for subject-specific and subject independent cases are conducted with the three-benchmark datasets from BCI competition III to evaluate the performances of the proposed method by employing typical machine-learning classifiers. For subject-specific case, experimental results show that an average sensitivity, specificity and classification accuracy of 98% was achieved by employing multilayer perceptron neural networks, logistic model tree and least-square support vector machine (LS-SVM) classifiers, respectively for three datasets, resulting in an improvement of upto 23.50% in classification accuracy as compared with other existing method. While an average sensitivity, specificity and classification accuracy of 93%, 92.1% and 91.4% was achieved for subject independent case by employing LS-SVM classifier for all datasets with an increase of up to 18.14% relative to other existing methods. Results also show that our proposed algorithm provides a classification accuracy of 100% for subjects with small training size in subject-specific case, and for subject independent case by employing a single source subject. Such satisfactory results demonstrate the great potential of the proposed MEWT algorithm for practical MI EEG signals classification.

GAIT ANALYSIS DRIVEN 2D FINITE ELEMENT MODEL OF THE NEUROPATHIC HINDFOOT

The diabetic foot is one of the most serious complications of diabetes mellitus and it can lead to foot ulcerations and amputations. Finite element analysis quantifies the loads developed in the different anatomical structures and describes how these affect foot tissue during foot–floor interaction. This approach for the diabetic subjects’ foot could provide valuable information in the process of plantar orthosis fabrication and fit. The purpose of this study was to develop two finite element models of the hindfoot, of healthy and diabetic neuropathic subjects. These models accounts for in vivo kinematics, kinetics, plantar pressure (PP) data and magnetic resonance images. These were acquired during gait analysis on 10 diabetic neuropathics and 10 healthy subjects. Validity of the models has been assessed through comparison between the peak PPs of simulated and experimental data: root mean square error (RMSE) in percentage of the experimental peak value was evaluated. Two different finite elements analysis were performed: subject-specific simulations in terms of both geometry and gait analysis, and by adopting the complete gait analysis dataset as boundary conditions. Model predicted plantar pressures were in good agreement with those experimentally measured. Best agreement was obtained in the subject-specific case (RMSE of 13%).

Optimisation of phase ratio in the triple jump using computer simulation

The triple jump is an athletic event comprising three phases in which the optimal proportion of each phase to the total distance jumped, termed the phase ratio, is unknown. This study used a whole-body torque-driven computer simulation model of all three phases of the triple jump to investigate optimal technique. The technique of the simulation model was optimised by varying torque generator activation parameters using a Genetic Algorithm in order to maximise total jump distance, resulting in a hop-dominated technique (35.7%:30.8%:33.6%) and a distance of 14.05m. Optimisations were then run with penalties forcing the model to adopt hop and jump phases of 33%, 34%, 35%, 36%, and 37% of the optimised distance, resulting in total distances of: 13.79m, 13.87m, 13.95m, 14.05m, and 14.02m; and 14.01m, 14.02m, 13.97m, 13.84m, and 13.67m respectively. These results indicate that in this subject-specific case there is a plateau in optimum technique encompassing balanced and hop-dominated techniques, but that a jump-dominated technique is associated with a decrease in performance. Hop-dominated techniques are associated with higher forces than jump-dominated techniques; therefore optimal phase ratio may be related to a combination of strength and approach velocity.

Building a Case-Based Curriculum to Enhance the Pedagogical Content Knowledge of Mathematics Teachers

Little attention has been given to research on cases in specific disciplines or on the development of an integrated case-based curriculum. In this article, I discuss how the cognitive flexibility and knowledge transfer theory proposed by Rand Spiro and his colleagues frames the design of a case-based curriculum for use in mathematics teacher education. The paper includes a sample mathematics teaching case and presents an analysis of four discussions based on that case. In the analysis, the dominant themes of those case discussions are identified and a framework for selecting and sequencing cases for an integrated curriculum is discussed. The analysis also shows the potential of subject-specific cases for enhancing mathematics teachers' pedagogical thinking and reasoning.