Volume 70, Issue 3

Objectives The actions and decisions of pilots are directly related to aviation safety. Therefore, understanding the neurological and cognitive processes of pilots during flight is essential. This study aims to investigate the EEG signals of pilots to understand the characteristic changes during the climb and descent stages of flight. Methods By performing wavelet packet decomposition on the EEG signals, we examined EEG maps during these critical phases and analyzed changes in signal intensity. To delve deeper, we calculated the log-transformed power of electroencephalograms to investigate the EEG responses under different flight conditions. Additionally, we conducted EEG spectral coherence analysis to evaluate the degree of synchronization between different electrodes during climb and descent. Results This analysis helps us understand the functional connectivity changes in various brain regions during these phases. Understanding these complex interactions is crucial, as it provides insights into the cognitive processes of pilots during the critical climb and descent stages of flight, contributing to enhanced aviation safety. Conclusions By identifying how brain activity fluctuates during these phases, we can better comprehend pilots’ decision-making processes, ultimately leading to the development of more effective training programs and safety protocols. This research underscores the importance of neurological studies in safety.

Objectives In recent years, significant progress has been made in the research of gesture recognition using surface electromyography (sEMG) signals based on machine learning and deep learning techniques. The main motivation for sEMG gesture recognition research is to provide more natural, convenient, and personalized human-computer interaction, which makes research in this field have considerable application prospects in rehabilitation technology. However, the existing gesture recognition algorithms still need to be further improved in terms of global feature capture, model computational complexity, and generalizability. Methods This paper proposes a fusion model of Squeeze-and-Excitation Networks (SE) and DenseNet, inserting attention mechanism between DenseBlock and Transition to focus on the most important information, improving feature representation ability, and effectively solving the problem of gradient vanishing. Results This proposed method was tested on the electromyographic gesture datasets NinaPro DB2 and DB4, achieving accuracies of 85.93 and 82.39 % respectively. Through ablation experiments, it was found that the method based on DenseNet-101 as the backbone model produced the best results. Conclusions Compared with existing models, this proposed method has better robustness and generalizability in gesture recognition, providing new ideas for the development of sEMG signal gesture recognition applications in the future.

Objectives Diabetic retinopathy (DR) is associated with long-term diabetes and is a leading cause of blindness if it is not diagnosed early. The rapid growth of deep learning eases the clinicians’ DR diagnosing procedure. It automatically extracts the features and performs the grading. However, training the image toward the majority of background pixels can impact the accuracy and efficiency of grading tasks. This paper proposes an auto-thresholding algorithm that reduces the negative impact of considering the background pixels for feature extraction which highly affects the grading process. Methods The PSO-based thresholding algorithm for retinal segmentation is proposed in this paper, and its efficacy is evaluated against the Otsu, histogram-based sigma, and entropy algorithms. In addition, the importance of retinal segmentation is analyzed using Explainable AI (XAI) to understand how each feature impacts the model’s performance. For evaluating the accuracy of the grading, ResNet50 was employed. Results The experiments were conducted using the IDRiD fundus dataset. Despite the limited data, the retinal segmentation approach provides significant accuracy than the non-segmented approach, with a substantial accuracy of 83.70 % on unseen data. Conclusions The result shows that the proposed PSO-based approach helps automatically determine the threshold value and improves the model’s accuracy.

Objectives The operating room is a fast-paced and demanding environment. Among the various factors involved in its optimization, predicting surgery duration is critical for scheduling and resource organization, ultimately resulting in improved quality of surgical care. Methods We design, implement and evaluate a semi-automated machine learning method that takes as input the current phase and tools employed and provides prediction of the Remain Surgery Duration (RSD) in laparoscopic cholecystectomy operations. We use the annotated information of tools and phases provided in the publicly available dataset Cholec80. The method is based on a Random Forest regression model that considers two data streams: the surgical phase and the type of tools employed, at each time-frame of the operation. The data were split into Training-, Validation- and Test-sets. The Mean Absolute Error (MAE) was used as the performance metric for the various models examined. Results Our approach managed to achieve a MAE=5.89 min across the overall duration of the surgeries in the test-set and MAE=4.61 min at 20 min before the end of the operation. Conclusions The employment of two separate regression models switched at a specific elapsed time threshold provides significant improvement in RSD prediction compared to other methods that process the video from the endoscope.

Objectives Dental caries is a prevalent oral health issue around the world that leads to tooth aches, root canal infections, and even tooth extractions. Existing dental caries diagnosis models may misdiagnose the disorder and take more time to segment the caries. This research work aims to provide an in-depth analysis of spatial and channel attention mechanism techniques used for semantic segmentation in an encoder-decoder network. For effective performance, the research implements novel techniques to segment the dental caries accurately. Methods Deep Fully Connected Residual Block (DFCR) is designed to provide relevant features without the loss of significant information. A novel Hybrid Spatial Channel Attention (HSCA) module is developed for combining significant features with the help of multi-scale spatial features and cross-dimensional channel features. Results The proposed methodology performs better than other cutting-edge algorithms by achieving 96.63 % accuracy, 95.77 % dice score, 96.28 % Intersection over Union (IOU) score for the caries dataset, and 96.93 % accuracy, 95.21 % dice value, and 96.1 % IOU for the Tufts dental dataset. Conclusions The developed model facilitates in detection of cavities precisely at an earlier stage with the help of dental images. The semantic segmentation of dental caries provides accurate diagnosis by assisting medical professionals.

Objectives The aim of this study was to clarify the applied initial forces and moments by different aligners of various materials and manufacturing methods. Methods The finite-element-method was used to analyze the forces and moments generated by the aligners on a maloccluded tooth. Plaster models of dental arches with a mesiorotated tooth 11 were fabricated, digitized and virtually analyzed. Four types of aligners with various layer thicknesses were selected: two splints with novel shape memory properties: a printable aligner made of the resin Tera Harz TC-85 DAC (Graphy Inc., South Korea) and a self-manufactured aligner consisting of the components polypropylene carbonate and thermoplastic polyurethane. The other two aligners were conventional, thermoformable aligners: CA ® Pro Clear Aligner (Scheu Dental GmbH, Germany) and Erkodur-al (Erkodent Erich Kopp GmbH, Germany). Results The force and moment analyses showed that the thermoformable CA ® Pro Clear Aligner exhibited the highest values. The thermoformed Erkodur-al aligner showed the lowest force loads for all layer thicknesses. The Graphy printed splint showed similar results compared to Erkodur-al at layer thicknesses of 0.40 mm and 0.50 mm. Conclusions To avoid periodontal overloading, aligners with lower force and moment delivery should be chosen for this type of tooth movement.

Objectives This study focuses on the effect of microstructural surface characteristics on metal-ceramic bond strength for SLM-fabricated titanium alloy. This research seeks to improve metal-ceramic adhesion in SLM-produced parts. Methods Inspired by the hydrophilic structure of Calathea zebrina, bioinspired microstructures were designed on titanium alloy surfaces. Samples were categorized into two groups: those with microstructured surfaces and those with smooth surfaces. Various microstructural parameters were implemented. Bending tests were conducted on all samples, which were subjected to the same porcelain-fused-to-metal sintering process. Scanning electron microscopy (SEM) and energy-dispersive X-ray spectroscopy (EDS) were employed to examine the bonding and separation surfaces of titanium alloy and porcelain. Results Metal-porcelain bonding strength is strongly influenced by the spacing and height of the bionic microstructure. Surfaces with the microstructure showed significantly higher bonding strength and distinctly different residue characteristics after peeling compared to surfaces without the microstructure. Conclusions Microstructured surfaces on titanium alloy substrates facilitate robust chemical and mechanical bonding between metal and porcelain, markedly enhancing the performance of SLM-produced metal-ceramic restorations.

Objectives In view of the gradual rejuvenation and acceleration of lumbar spondylosis, a wearable powered lumbar exoskeleton based on a 6-SPU/SP parallel mechanism is designed based on the rehabilitation treatment method of lumbar forward flexion/extension, left/right lateral flexion and rotation. Methods First, the changes in human lumbar muscles are analyzed based on human biomechanics, and then the prototype design of the powered lumbar exoskeleton is implemented, including the mechanical mechanism design, and hardware module design. Finally, the simulation experiment of muscle force and output sensitivity test in the resistive mode are conducted. Results The simulation results show that the external oblique muscle can be relieved about 20 % and the iliopsoas muscle can be decreased by 33 % when wearing the powered lumbar exoskeleton in the lateral flexion. The pressure sensors can measure the output force of each actuator in real-time when the resistance force reaches the set value of 15 N at the resistive model. Conclusions The results show that the powered lumbar exoskeleton can assist the human lumbar spine in rehabilitation training of traction, forward flexion and extension, left and right lateral flexion, and rotation. This research provides new ideas for future clinical research.

Objectives Nonenzymatic biosensor-based-conductive polymers like polyaniline are highly electrochemically stable, cheap, and easy to synthesize biosensors, which is the main objective of research as well as testing applied in different pH conditions to get optimum sensitivity. Methods A nonenzymatic glucose biosensor based on polyaniline was electrochemically deposited on a glassy carbon electrode; the cyclic voltammetry under range applied voltage −0.2 to 1.2 V vs. Ag/AgCl was employed to synthesize the biosensor electrode. Results The polyaniline biosensor electrode properties were characterized, and the morphology surface photographic confirmed mesoporous architecture with many accessible pores, while chemical bonding analysis confirmed the synthesis of polyaniline. The initial investigation examined the pH levels of phosphate-buffered saline, including 5, 5.5, 6, and 6.5. The cyclic voltammetry measurement revealed that the pH=5.5 provides excellent sensitivity toward glucose detection. The sensitivity of pH=5.5 is 68.7 μA mM −1  cm −2 , and the low detection limit is 1 µM. Conclusions The findings above indicate that the biosensor could be an excellent candidate for application in electrochemical glucose sensing under pH=5.5 conditions of phosphate-buffered saline.