The Impact of Various Cockpit Display Interfaces on Novice Pilots' Mental Workload and Situational Awareness: A Comparative Study.

Future airspace is expected to become more congested with additional in-service cargo and commercial flights. Pilots will face additional burdens in such an environment, given the increasing number of factors that they must simultaneously consider while completing their work activities. Therefore, care and attention must be paid to the mental workload (MWL) experienced by operating pilots. If left unaddressed, a state of mental overload could affect the pilot's ability to complete his or her work activities in a safe and correct manner. This study examines the impact of two different cockpit display interfaces (CDIs), the Steam Gauge panel and the G1000 Glass panel, on novice pilots' MWL and situational awareness (SA) in a flight simulator-based setting. A combination of objective (EEG and HRV) and subjective (NASA-TLX) assessments is used to assess novice pilots' cognitive states during this study. Our results indicate that the gauge design of the CDI affects novice pilots' SA and MWL, with the G1000 Glass panel being more effective in reducing the MWL and improving SA compared with the Steam Gauge panel. The results of this study have implications for the design of future flight deck interfaces and the training of future pilots.

Guidewire Endpoint Detection Based on Pixel Adjacent Relation in Robot-assisted Cardiovascular Interventions.

Visualization of endovascular tools like guidewire and catheter is essential for procedural success of endovascular interventions. This requires tracking the tool pixels and motion during catheterization; however, detecting the endpoints of the endovascular tools is challenging due to their small size, thin appearance, and flexibility. As this still limit the performances of existing methods used for endovascular tool segmentation, predicting correct object location could provide ways forward. In this paper, we proposed a neighborhood-based method for detecting guidewire endpoints in X-ray angiograms. Typically, it consists of pixel-level segmentation and a post-segmentation step that is based on adjacency relationships of pixels in a given neighborhood. The latter includes skeletonization to predict endpoint pixels of guidewire. The method is evaluated with proprietary guidewire dataset obtained during in-vivo study in six rabbits, and it shows a high segmentation performance characterized with precision of 87.87% and recall of 90.53%, and low detection error with a mean pixel error of 2.26±0.14 pixels. We compared our method with four state-of-the-art detection methods and found it to exhibit the best detection performance. This neighborhood-based detection method can be generalized for other surgical tool detection and in related computer vision tasks.Clinical Relevance- The proposed method can be provided with better tool tracking and visualization systems during robot-assisted intravascular interventional surgery.

Deep Learning Models for Stress Analysis in University Students: A Sudoku-Based Study.

Due to the phenomenon of "involution" in China, the current generation of college and university students are experiencing escalating levels of stress, both academically and within their families. Extensive research has shown a strong correlation between heightened stress levels and overall well-being decline. Therefore, monitoring students' stress levels is crucial for improving their well-being in educational institutions and at home. Previous studies have primarily focused on recognizing emotions and detecting stress using physiological signals like ECG and EEG. However, these studies often relied on video clips to induce various emotional states, which may not be suitable for university students who already face additional stress to excel academically. In this study, a series of experiments were conducted to evaluate students' stress levels by engaging them in playing Sudoku games under different distracting conditions. The collected physiological signals, including PPG, ECG, and EEG, were analyzed using enhanced models such as LRCN and self-supervised CNN to assess stress levels. The outcomes were compared with participants' self-reported stress levels after the experiments. The findings demonstrate that the enhanced models presented in this study exhibit a high level of proficiency in assessing stress levels. Notably, when subjects were presented with Sudoku-solving tasks accompanied by noisy or discordant audio, the models achieved an impressive accuracy rate of 95.13% and an F1-score of 93.72%. Additionally, when subjects engaged in Sudoku-solving activities with another individual monitoring the process, the models achieved a commendable accuracy rate of 97.76% and an F1-score of 96.67%. Finally, under comforting conditions, the models achieved an exceptional accuracy rate of 98.78% with an F1-score of 95.39%.

Monitoring and Analysis Solid Formulation Dissolution Phenomenon with Image Recognition Technologies.

The dissolution test has become the most important quality index in the research and development of solid formulation, especially the evaluation of drug bioequivalence. However, it had low operability, was tedious, and was always overlooked. The previously related studies required a fixed tablet and analysed the recorded video by disso GUARO PRO and Microsoft Paint™. Therefore, we have developed a novel image recognition system to automatically track the moving tablet and analyse the volume change at the same time. Image recognition technology is often used to monitor the dissolution process. The camera system with visible light and infrared camera functions was placed on the dissolution tester. The system collects the plate image for binary processing and then records and calculates its pixel area, which can automatically record the volume change of the tablet in the dissolution test, no matter disintegration or corrosion.

ScatterHough: Automatic Lane Detection from Noisy LiDAR Data.

Lane detection plays an essential role in autonomous driving. Using LiDAR data instead of RGB images makes lane detection a simple straight line, and curve fitting problem works for realtime applications even under poor weather or lighting conditions. Handling scatter distributed noisy data is a crucial step to reduce lane detection error from LiDAR data. Classic Hough Transform (HT) only allows points in a straight line to vote on the corresponding parameters, which is not suitable for data in scatter form. In this paper, a Scatter Hough algorithm is proposed for better lane detection on scatter data. Two additional operations, ρ neighbor voting and ρ neighbor vote-reduction, are introduced to HT to make points in the same curve vote and consider their neighbors' voting result as well. The evaluation of the proposed method shows that this method can adaptively fit both straight lines and curves with high accuracy, compared with benchmark and state-of-the-art methods.

TAFFIES: Tailored Automated Feedback Framework for Developing Integrated and Extensible Feedback Systems.

Delivering high-quality, timely and formative feedback for students' code-based coursework submissions is a problem faced by Computer Science (CS) educators. Automated Feedback Systems (AFSs) can provide immediate feedback on students' work, without requiring students to be physically present in the classroom-an increasingly important consideration for education in the context of COVID-19 lockdowns. There are concerns, however, surrounding the quality of the feedback provided by existing AFSs, with many systems simply presenting a score, a binary classification (pass/fail), or a basic error identification ("The program could not run"). Such feedback, with little guidance for how to rectify the problem, raises doubts as to whether or not these systems can stimulate deep engagement with the related knowledge or learning activities. In this paper, we propose TAFFIES, a framework to scaffold the development of AFSs that promote high-quality, tailored feedback for student's solutions. We tested our framework by applying it to develop an AFS to mark and provide feedback to 160 CS students in an introductory databases class. In contrast to most introductory-level coursework feedback and marking, which typically generate significant student reaction and change requests, our AFS deployment resulted in zero grade challenges. There were also no identified marking errors, or suggested inconsistencies or unfairness. Student feedback on the AFS was universally positive, with comments indicating an AFS-related increase in student motivation. The experience of designing, deploying, and evolving the AFS using TAFFIES is examined through reflective practice, student evaluation, and focus group (involving peer teachers) analysis.

Machine-Learning-Enabled Virtual Screening for Inhibitors of Lysine-Specific Histone Demethylase 1.

A machine learning approach has been applied to virtual screening for lysine specific demethylase 1 (LSD1) inhibitors. LSD1 is an important anti-cancer target. Machine learning models to predict activity were constructed using Morgan molecular fingerprints. The dataset, consisting of 931 molecules with LSD1 inhibition activity, was obtained from the ChEMBL database. An evaluation of several candidate algorithms on the main dataset revealed that the support vector regressor gave the best model, with a coefficient of determination (R2) of 0.703. Virtual screening, using this model, identified five predicted potent inhibitors from the ZINC database comprising more than 300,000 molecules. The virtual screening recovered a known inhibitor, RN1, as well as four compounds where activity against LSD1 had not previously been suggested. Thus, we performed a machine-learning-enabled virtual screening of LSD1 inhibitors using only the structural information of the molecules.

Smart Wearables with Sensor Fusion for Fall Detection in Firefighting.

During the past decade, falling has been one of the top three causes of death amongst firefighters in China. Even though there are many studies on fall-detection systems (FDSs), the majority use a single motion sensor. Furthermore, few existing studies have considered the impact sensor placement and positioning have on fall-detection performance; most are targeted toward fall detection of the elderly. Unfortunately, floor cracks and unstable building structures in the fireground increase the difficulty of detecting the fall of a firefighter. In particular, the movement activities of firefighters are more varied; hence, distinguishing fall-like activities from actual falls is a significant challenge. This study proposed a smart wearable FDS for firefighter fall detection by integrating motion sensors into the firefighter's personal protective clothing on the chest, elbows, wrists, thighs, and ankles. The firefighter's fall activities are detected by the proposed multisensory recurrent neural network, and the performances of different combinations of inertial measurement units (IMUs) on different body parts were also investigated. The results indicated that the sensor fusion of IMUs from all five proposed body parts achieved performances of 94.10%, 92.25%, and 94.59% in accuracy, sensitivity, and specificity, respectively.

Affective Computing on Machine Learning-Based Emotion Recognition Using a Self-Made EEG Device.

In this research, we develop an affective computing method based on machine learning for emotion recognition using a wireless protocol and a wearable electroencephalography (EEG) custom-designed device. The system collects EEG signals using an eight-electrode placement on the scalp; two of these electrodes were placed in the frontal lobe, and the other six electrodes were placed in the temporal lobe. We performed experiments on eight subjects while they watched emotive videos. Six entropy measures were employed for extracting suitable features from the EEG signals. Next, we evaluated our proposed models using three popular classifiers: a support vector machine (SVM), multi-layer perceptron (MLP), and one-dimensional convolutional neural network (1D-CNN) for emotion classification; both subject-dependent and subject-independent strategies were used. Our experiment results showed that the highest average accuracies achieved in the subject-dependent and subject-independent cases were 85.81% and 78.52%, respectively; these accuracies were achieved using a combination of the sample entropy measure and 1D-CNN. Moreover, our study investigates the T8 position (above the right ear) in the temporal lobe as the most critical channel among the proposed measurement positions for emotion classification through electrode selection. Our results prove the feasibility and efficiency of our proposed EEG-based affective computing method for emotion recognition in real-world applications.

Sensor Fusion of Motion-Based Sign Language Interpretation with Deep Learning.

Sign language was designed to allow hearing-impaired people to interact with others. Nonetheless, knowledge of sign language is uncommon in society, which leads to a communication barrier with the hearing-impaired community. Many studies of sign language recognition utilizing computer vision (CV) have been conducted worldwide to reduce such barriers. However, this approach is restricted by the visual angle and highly affected by environmental factors. In addition, CV usually involves the use of machine learning, which requires collaboration of a team of experts and utilization of high-cost hardware utilities; this increases the application cost in real-world situations. Thus, this study aims to design and implement a smart wearable American Sign Language (ASL) interpretation system using deep learning, which applies sensor fusion that "fuses" six inertial measurement units (IMUs). The IMUs are attached to all fingertips and the back of the hand to recognize sign language gestures; thus, the proposed method is not restricted by the field of view. The study reveals that this model achieves an average recognition rate of 99.81% for dynamic ASL gestures. Moreover, the proposed ASL recognition system can be further integrated with ICT and IoT technology to provide a feasible solution to assist hearing-impaired people in communicating with others and improve their quality of life.

American Sign Language Recognition Using Leap Motion Controller with Machine Learning Approach.

Sign language is intentionally designed to allow deaf and dumb communities to convey messages and to connect with society. Unfortunately, learning and practicing sign language is not common among society; hence, this study developed a sign language recognition prototype using the Leap Motion Controller (LMC). Many existing studies have proposed methods for incomplete sign language recognition, whereas this study aimed for full American Sign Language (ASL) recognition, which consists of 26 letters and 10 digits. Most of the ASL letters are static (no movement), but certain ASL letters are dynamic (they require certain movements). Thus, this study also aimed to extract features from finger and hand motions to differentiate between the static and dynamic gestures. The experimental results revealed that the sign language recognition rates for the 26 letters using a support vector machine (SVM) and a deep neural network (DNN) are 80.30% and 93.81%, respectively. Meanwhile, the recognition rates for a combination of 26 letters and 10 digits are slightly lower, approximately 72.79% for the SVM and 88.79% for the DNN. As a result, the sign language recognition system has great potential for reducing the gap between deaf and dumb communities and others. The proposed prototype could also serve as an interpreter for the deaf and dumb in everyday life in service sectors, such as at the bank or post office.

Smartwatch-based driver alertness monitoring with wearable motion and physiological sensor.

Studies have shown that a high precision driver alertness monitoring system is an essential and a monetary countermeasure to reduce the road accidents. This paper presents a novel approach to measure the driver alertness, evaluated by a smartwatch device based on fusion of direct and indirect method. The driver chronic physiological state is monitor by adopting a photoplethysmography sensor on the driver finger that is connected to a wrist-type wearable device. A Bluetooth Low Energy module connected to the wearable device transmits the PPG data to the smartwatch in real-time. Meanwhile, the indirect method, driver steering wheel movement can be derived by utilizing the motion sensors integrated in the smartwatch which include a tri-axis accelerometer and a gyroscope sensors. The respiration signals can be derived from the PPG time- and frequency-domains attributes. The data obtained from both methods aforementioned are subsequently decomposed into relevant features in time, spectral context and phase space domain, and thus computes the alertness index. Here, the correlations between the extracted features and the subjective Koralinska Sleepiness Scale are studied as well along with the recorded experimental videos. This study reveals that the alertness index prediction accuracy can be reached up to 96.3% based on the descriptive extracted features.

Mobile healthcare for automatic driving sleep-onset detection using wavelet-based EEG and respiration signals.

Driving drowsiness is a major cause of traffic accidents worldwide and has drawn the attention of researchers in recent decades. This paper presents an application for in-vehicle non-intrusive mobile-device-based automatic detection of driver sleep-onset in real time. The proposed application classifies the driving mental fatigue condition by analyzing the electroencephalogram (EEG) and respiration signals of a driver in the time and frequency domains. Our concept is heavily reliant on mobile technology, particularly remote physiological monitoring using Bluetooth. Respiratory events are gathered, and eight-channel EEG readings are captured from the frontal, central, and parietal (Fpz-Cz, Pz-Oz) regions. EEGs are preprocessed with a Butterworth bandpass filter, and features are subsequently extracted from the filtered EEG signals by employing the wavelet-packet-transform (WPT) method to categorize the signals into four frequency bands: α, ß, θ, and δ. A mutual information (MI) technique selects the most descriptive features for further classification. The reduction in the number of prominent features improves the sleep-onset classification speed in the support vector machine (SVM) and results in a high sleep-onset recognition rate. Test results reveal that the combined use of the EEG and respiration signals results in 98.6% recognition accuracy. Our proposed application explores the possibility of processing long-term multi-channel signals.

A smartphone-based driver safety monitoring system using data fusion.

This paper proposes a method for monitoring driver safety levels using a data fusion approach based on several discrete data types: eye features, bio-signal variation, in-vehicle temperature, and vehicle speed. The driver safety monitoring system was developed in practice in the form of an application for an Android-based smartphone device, where measuring safety-related data requires no extra monetary expenditure or equipment. Moreover, the system provides high resolution and flexibility. The safety monitoring process involves the fusion of attributes gathered from different sensors, including video, electrocardiography, photoplethysmography, temperature, and a three-axis accelerometer, that are assigned as input variables to an inference analysis framework. A Fuzzy Bayesian framework is designed to indicate the driver's capability level and is updated continuously in real-time. The sensory data are transmitted via Bluetooth communication to the smartphone device. A fake incoming call warning service alerts the driver if his or her safety level is suspiciously compromised. Realistic testing of the system demonstrates the practical benefits of multiple features and their fusion in providing a more authentic and effective driver safety monitoring.