Gradient-Based Multi-Objective Feature Selection for Gait Mode Recognition of Transfemoral Amputees

Data-efficient human walking speed intent identification

The ability to accurately identify human gait intent is a challenge relevant to the success of many applications in robotics, including, but not limited to, assistive devices. Most existing intent identification approaches, however, are either sensor-specific or use a pattern-recognition approach that requires large amounts of training data. This paper introduces a real-time walking speed intent identification algorithm based on the Mahalanobis distance that requires minimal training data. This data efficiency is enabled by making the simplifying assumption that each time step of walking data is independent of all other time steps. The accuracy of the algorithm was analyzed through human-subject experiments that were conducted using controlled walking speed changes on a treadmill. Experimental results confirm that the model used for intent identification converges quickly (within 5 min of training data). On average, the algorithm successfully detected the change in desired walking speed within one gait cycle and had a maximum of 87% accuracy at responding with the correct intent category of speed up, slow down, or no change. The findings also show that the accuracy of the algorithm improves with the magnitude of the speed change, while speed increases were more easily detected than speed decreases.

Toward higher-performance bionic limbs for wider clinical use

Most prosthetic limbs can autonomously move with dexterity, yet they are not perceived by the user as belonging to their own body. Robotic limbs can convey information about the environment with higher precision than biological limbs, but their actual performance is substantially limited by current technologies for the interfacing of the robotic devices with the body and for transferring motor and sensory information bidirectionally between the prosthesis and the user. In this Perspective, we argue that direct skeletal attachment of bionic devices via osseointegration, the amplification of neural signals by targeted muscle innervation, improved prosthesis control via implanted muscle sensors and advanced algorithms, and the provision of sensory feedback by means of electrodes implanted in peripheral nerves, should all be leveraged towards the creation of a new generation of high-performance bionic limbs. These technologies have been clinically tested in humans, and alongside mechanical redesigns and adequate rehabilitation training should facilitate the wider clinical use of bionic limbs.

Deep Learning-Based CT Imaging for the Diagnosis of Liver Tumor

The objective of this research was to investigate the application value of deep learning-based computed tomography (CT) images in the diagnosis of liver tumors. Fifty-eight patients with liver tumors were selected, and their CT images were segmented using a convolutional neural network (CNN) algorithm. The segmentation results were quantitatively evaluated using the Dice similarity coefficient (DSC), precision, and recall. All the patients were examined and diagnosed by CT enhanced delayed scan technique, and the CT scan results were compared with the pathological findings. The results showed that the DSC, precision, and recall of the CNN algorithm reached 0.987, 0.967, and 0.954, respectively. The images segmented by the CNN were clearer. The diagnostic result of the examination on 56 cases by CT enhanced delay scanning was consistent with that of pathological diagnosis. According to the result of pathological diagnosis, there were 6 cases with hepatic cyst, 9 with hepatic hemangioma, 12 cases with liver metastasis, 10 cases with hepatoblastoma, 3 cases with focal nodular hyperplasia, and 18 cases with primary liver cancer. The result of CT enhanced delay scanning on 58 patients was consistent with that of pathological diagnosis, and the total diagnostic coincidence rate reached 96.55%. In conclusion, the CNN algorithm can perform accurate and efficient segmentation, with high resolution, providing a more scientific basis for the segmentation of liver tumors in CT images. CT enhanced scanning technology has a good effect on the diagnosis and differentiation of liver tumor patients, with high diagnostic coincidence rate. It has important value for the diagnosis of liver tumor and is worthy of clinical application.

A Survey of Human Gait-Based Artificial Intelligence Applications

We performed an electronic database search of published works from 2012 to mid-2021 that focus on human gait studies and apply machine learning techniques. We identified six key applications of machine learning using gait data: 1) Gait analysis where analyzing techniques and certain biomechanical analysis factors are improved by utilizing artificial intelligence algorithms, 2) Health and Wellness, with applications in gait monitoring for abnormal gait detection, recognition of human activities, fall detection and sports performance, 3) Human Pose Tracking using one-person or multi-person tracking and localization systems such as OpenPose, Simultaneous Localization and Mapping (SLAM), etc., 4) Gait-based biometrics with applications in person identification, authentication, and re-identification as well as gender and age recognition 5) “Smart gait” applications ranging from smart socks, shoes, and other wearables to smart homes and smart retail stores that incorporate continuous monitoring and control systems and 6) Animation that reconstructs human motion utilizing gait data, simulation and machine learning techniques. Our goal is to provide a single broad-based survey of the applications of machine learning technology in gait analysis and identify future areas of potential study and growth. We discuss the machine learning techniques that have been used with a focus on the tasks they perform, the problems they attempt to solve, and the trade-offs they navigate.

Toward Minimal-Sensing Locomotion Mode Recognition for a Powered Knee-Ankle Prosthesis

OBJECTIVE

Locomotion mode recognition (LMR) enables seamless and natural transitions between low-level control systems in a powered prosthesis. We present a new optimization framework for LMR that eliminates irrelevant or redundant features and measurement signals while still maintaining performance.

METHODS

We use multi-objective biogeography-based optimization to find a compromise solution between performance and the minimization of feature set size. Experimental data are collected from four transfemoral users walking with a powered knee-ankle prosthesis. We compare the performance of LMR systems trained with the optimal feature subsets and with the full feature set using a deep neural network classifier across six locomotion modes: standing, flat-ground walking, stair up/down, and ramp up/down.

RESULTS

Statistical tests indicate that classifier performance using the optimal feature subsets is statistically equal to that using the full feature set. The LMR trained with an optimal subset results in the 1.98% steady-state and 4.09% transitional error rates, while only using approximately 41% and 53% of the available features and sensors, respectively.

CONCLUSION

Results thus indicate the capability of the proposed framework to achieve simultaneously accurate and low-complex LMR systems for transfemoral individuals with powered prostheses.

SIGNIFICANCE

This framework would potentially lead to less frequent clinical visits needed for sensor replacement and calibrations, which may save health care costs and the prosthesis user's time and energy.

Subject- and Environment-Based Sensor Variability for Wearable Lower-Limb Assistive Devices

Significant research effort has gone towards the development of powered lower limb prostheses that control power during gait. These devices use forward prediction based on electromyography (EMG), kinetics and kinematics to command the prosthesis which locomotion activity is desired. Unfortunately these predictions can have substantial errors, which can potentially lead to trips or falls. It is hypothesized that one reason for the significant prediction errors in the current control systems for powered lower-limb prostheses is due to the inter- and intra-subject variability of the data sources used for prediction. Environmental data, recorded from a depth sensor worn on a belt, should have less variability across trials and subjects as compared to kinetics, kinematics and EMG data, and thus its addition is proposed. The variability of each data source was analyzed, once normalized, to determine the intra-activity and intra-subject variability for each sensor modality. Then measures of separability, repeatability, clustering and overall desirability were computed. Results showed that combining Vision, EMG, IMU (inertial measurement unit), and Goniometer features yielded the best separability, repeatability, clustering and desirability across subjects and activities. This will likely be useful for future application in a forward predictor, which will incorporate Vision-based environmental data into a forward predictor for powered lower-limb prosthesis and exoskeletons.

Gradient Descent-Based Optimization Method of a Four-Bar Mechanism Using Fully Cartesian Coordinates

Machine vibrations often occur due to dynamic unbalance inducing wear, fatigue, and noise that limit the potential of many machines. Dynamic balancing is a main concern in mechanism and machine theory as it allows designers to limit the transmission of vibrations to the frames and base of machines. This work introduces a novel method for representing a four-bar mechanism with the use of Fully Cartesian coordinates and a simple definition of the shaking force (ShF) and the shaking moment (ShM) equations. A simplified version of Projected Gradient Descent is used to minimize the ShF and ShM functions with the aim of balancing the system. The multi-objective optimization problem was solved using a linear combination of the objectives. A comprehensive analysis of the partial derivatives, volumes, and relations between area and thickness of the counterweights is used to define whether the allowed optimization boundaries should be changed in case the mechanical conditions of the mechanism permit it. A comparison between Pareto fronts is used to determine the impact that each counterweight has on the mechanism’s balancing. In this way, it is possible to determine which counterweights can be eliminated according to the importance of the static balance (ShF), dynamic balance (ShM), or both. The results of this methodology when using three counterweights reduces the ShF and ShM by 99.70% and 28.69%, respectively when importance is given to the static balancing and by 83.99% and 8.47%, respectively, when importance is focused on dynamic balancing. Even when further reducing the number of counterweights, the ShF and ShM can be decreased satisfactorily.