GNSS performance enhancement using measurement estimation in harsh environment.

Global navigation satellite systems (GNSSs) are commonly used to measure the position and time globally. A GNSS is convenient owing to its ability to measure accurate position relatively without using assistive tools for navigation by comparing with other sensors. Based on these benefits, the applicable area is expanding to commercial and social uses (e.g., vehicle navigation, smart grids, and smartphone apps). In the future, various services and technologies (e.g., the use of autonomous vehicles, unmanned delivery, and industrial field robots), which make Internet of Things (IOT) more active, will be used in our society. Conversely, the performance of GNSS can degrade in harsh environments, such as urban areas, owing to the property of GNSS, which calculates position and time via satellite signal reception. However, buildings in a city can block navigation satellite signals and generate multi-path errors. The blocked signals exacerbate the dilution of precision (DOP), which indicates the accuracy of the navigation solution and increases the navigation solution error. This study proposes methods to improve navigation performance by leveraging various techniques (e.g., range differences, receiver clock error hold, and virtual satellites). The methods were validated in harsh environments where visible satellites were reduced. In the simulation, each proposed method improved the navigation performance by creating an environment similar to a normal situation, despite the receiver entering a harsh environment. The results confirmed that the navigation performance deteriorated compared to the normal situation where the number of visible satellites decreased. However, the navigation performance was recovered gradually by applying the proposed techniques. Using the proposed methods, navigation performance can be maintained continuously even in situations where satellite signals are blocked.

Deep learning model for the diagnosis of breast cancers smaller than 1 cm with ultrasonography: integration of ultrasonography and clinical factors.

Background: The aim of this study was to evaluate the diagnostic performance of a deep learning (DL) algorithm for breast masses smaller than 1 cm on ultrasonography (US). We also evaluated a hybrid model that combines the predictions of the DL algorithm from US images and a patient's clinical factors including age, family history of breast cancer, BRCA mutation, and mammographic breast density. Methods: A total of 1,041 US images (including 633 benign and 408 malignant masses) were obtained from 1,041 patients who underwent US between January 2014 and June 2021. All US images were randomly divided into training (513 benign and 288 malignant lesions), validation (60 benign and 60 malignant lesions), and test (60 benign and 60 malignant lesions) data sets. A mask region-based convolutional neural network (R-CNN) was used to generate a feature map of the input image with a CNN and a pre-trained ResNet101 structure. For the clinical model, the multilayer perceptron (MLP) structure was used to calculate the likelihood that the tumor was benign or malignant from the clinical risk factors. We compared the diagnostic performance of an image-based DL algorithm, a combined model with regression, and a combined model with the decision tree method. Results: Using the US images, the area under the receiver operating characteristics curve (AUROC) of the DL algorithm was 0.85 [95% confidence interval (CI), 0.78-0.92]. With the combined model using a regression model, the sensitivity was 78.3% (95% CI, 67.9-88.8%) and the specificity was 85% (95% CI, 76-94%). The sensitivity of the combined model using a regression model was significantly higher than that of the imaging model (P=0.003). The specificity values of the two models were not significantly different (P=0.083). The sensitivity and specificity of the combined model using a decision tree model were 75% (95% CI, 62.1-85.3%) and 91.7% (95% CI, 81.6-97.2%), respectively. The sensitivity of the combined model using the decision tree model was higher than that of the image model but the difference was not statistically significant (P=0.081). The specificity values of the two models were not significantly different (P=0.748). Conclusions: The DL model could feasibly be used to predict breast cancers smaller than 1 cm. The combined model using clinical factors outperformed the standalone US-based DL model.

Machine-learning-based coordination of powered ankle-foot orthosis and functional electrical stimulation for gait control.

This study proposes a novel gait rehabilitation method that uses a hybrid system comprising a powered ankle-foot orthosis (PAFO) and FES, and presents its coordination control. The developed system provides assistance to the ankle joint in accordance with the degree of volitional participation of patients with post-stroke hemiplegia. The PAFO adopts the desired joint angle and impedance profile obtained from biomechanical simulation. The FES patterns of the tibialis anterior and soleus muscles are derived from predetermined electromyogram patterns of healthy individuals during gait and personalized stimulation parameters. The CNN-based estimation model predicts the volitional joint torque from the electromyogram of the patient, which is used to coordinate the contributions of the PAFO and FES. The effectiveness of the developed hybrid system was tested on healthy individuals during treadmill walking with and without considering the volitional muscle activity of the individual. The results showed that consideration of the volitional muscle activity significantly lowers the energy consumption by the PAFO and FES while providing adaptively assisted ankle motion depending on the volitional muscle activities of the individual. The proposed system has potential use as an assist-as-needed rehabilitation system, where it can improve the outcome of gait rehabilitation by inducing active patient participation depending on the stage of rehabilitation.

Standing Balance Control of a Bipedal Robot Based on Behavior Cloning.

Bipedal robots have gained increasing attention for their human-like mobility which allows them to work in various human-scale environments. However, their inherent instability makes it difficult to control their balance while they are physically interacting with the environment. This study proposes a novel balance controller for bipedal robots based on a behavior cloning model as one of the machine learning techniques. The behavior cloning model employs two deep neural networks (DNNs) trained on human-operated balancing data, so that the trained model can predict the desired wrench required to maintain the balance of the bipedal robot. Based on the prediction of the desired wrench, the joint torques for both legs are calculated using robot dynamics. The performance of the developed balance controller was validated with a bipedal lower-body robotic system through simulation and experimental tests by providing random perturbations in the frontal plane. The developed balance controller demonstrated superior performance with respect to resistance to balance loss compared to the conventional balance control method, while generating a smoother balancing movement for the robot.

Development of a Novel Robotic Rehabilitation System With Muscle-to-Muscle Interface.

In this study, we developed a novel robotic system with a muscle-to-muscle interface to enhance rehabilitation of post-stroke patients. The developed robotic rehabilitation system was designed to provide patients with stage appropriate physical rehabilitation exercise and muscular stimulation. Unlike the position-based control of conventional bimanual robotic therapies, the developed system stimulates the activities of the target muscles, as well as the joint movements of the paretic limb. The robot-assisted motion and the electrical stimulation on the muscles of the paretic side are controlled by on-line comparison of the motion and the muscle activities between the paretic and unaffected sides. With the developed system, the rehabilitation exercise can be customized and modulated depending on the patient's stage of motor recovery after stroke. The system can be operated in three different modes allowing both passive and active exercises. The effectiveness of the developed system was verified with healthy human subjects, where the subjects were paired to serve as the unaffected side and the paretic side of a hemiplegic patient.

Endoscopic navigation system with extended field of view using augmented reality technology.

BACKGROUND: While endoscopic skull base surgery (ESBS) has emerged as an alternative surgical option, the limited field of view of the endoscope may lead to the surgeon's fatigue and discomfort. METHODS: The developed navigation system includes extended augmented reality (AR), which can provide an extended viewport to a conventional endoscopic view by overlaying 3D anatomical models generated from preoperative medical images onto endoscope images. To enhance the accuracy of the developed system, we adopted state-of-the-art endoscopic calibration and tracking techniques based on an optical tracking system. RESULTS: The mean spatial errors of AR was ~1 mm, which falls in the acceptable range of accuracy for ESBS. For the simulated surgical tasks with the developed system, the number and duration of error events were decreased. CONCLUSIONS: The results show that the human subject can perform the task more precisely and safely with the developed AR-based navigation system than with the conventional endoscopic system.

Prediction of Driver's Intention of Lane Change by Augmenting Sensor Information Using Machine Learning Techniques.

Driver assistance systems have become a major safety feature of modern passenger vehicles. The advanced driver assistance system (ADAS) is one of the active safety systems to improve the vehicle control performance and, thus, the safety of the driver and the passengers. To use the ADAS for lane change control, rapid and correct detection of the driver's intention is essential. This study proposes a novel preprocessing algorithm for the ADAS to improve the accuracy in classifying the driver's intention for lane change by augmenting basic measurements from conventional on-board sensors. The information on the vehicle states and the road surface condition is augmented by using an artificial neural network (ANN) models, and the augmented information is fed to a support vector machine (SVM) to detect the driver's intention with high accuracy. The feasibility of the developed algorithm was tested through driving simulator experiments. The results show that the classification accuracy for the driver's intention can be improved by providing an SVM model with sufficient driving information augmented by using ANN models of vehicle dynamics.

Acetoacetate protects neuronal cells from oxidative glutamate toxicity.

Glutamate cytotoxicity contributes to neuronal degeneration in many central nervous system (CNS) diseases, such as epilepsy and ischemia. We previously reported that a high-fat and low-carbohydrate diet, the ketogenic diet (KD), protects against kainic acid-induced hippocampal cell death in mice. We hypothesized based on these findings that ketosis resulting from KD might inhibit glutamate cytotoxicity, resulting in inhibition of hippocampal neuronal cell death. Therefore, we investigated the role of ketone bodies [acetoacetate (AA) and beta-hydroxybutyrate (beta-OHB)] both in a mouse hippocampal cell line (HT22) and in rat primary hippocampal neurons. As a result, we found that pretreatment with 5 mM lithium AA and 4 mM Na beta-OHB protected the HT22 hippocampal cell line and primary hippocampal neuronal culture against 5 mM glutamate toxicity and that up to 2 hr of pretreatment with 5 mM AA had a protective effect against 5 mM glutamate toxicity in the HT22 cell line. Pretreatment with 5 mM AA decreased ROS production of HT22 cell line at 2 and 8 hr exposure of glutamate, and it decreased the appearance of annexin V-positive HT22 cells, which are indicative of an early stage of apoptosis, and propidium iodide-positive HT22 cells, which are indicative of necrosis.