Freezing of gait (FoG) is a common motor dysfunction in individuals with Parkinson's disease. FoG impairs walking and is associated with increased fall risk. On-demand external cueing systems can detect FoG and provide stimuli to help individuals overcome freezing. Predicting FoG before onset enables preemptive cueing and may prevent FoG. However, detection and prediction remain challenging. If FoG data are not available for an individual, patient-independent models have been used to detect FoG, which have shown great sensitivity and poor specificity, or vice versa. In this study, we introduce a Deep Gait Anomaly Detector (DGAD) using a transfer learning-based approach to improve FoG detection accuracy. We also evaluate the effect of data augmentation and additional pre-FoG segments on prediction rate. Seven individuals with PD performed a series of daily walking tasks wearing inertial measurement units on their ankles. The DGAD algorithm demonstrated average sensitivity and specificity of 63.0% and 98.6% (3.2% improvement compared with the highest specificity in the literature). The target models identified 87.4% of FoG onsets, with 21.9% predicted. This study demonstrates our algorithm's potential for accurate identification of FoG and delivery of cues for patients for whom no FoG data is available for model training.

Freezing of gait (FoG) is a common type of motor impairment in Parkinson's disease (PD) associated with falls. Pharmacologic treatments have failed to prevent FoG, resulting in a need for the development of non-pharmaceutical interventions. This study aims to use the ADAptive SYNthetic (ADASYN) sampling algorithm to improve the automatic detection of FoG episodes in people with PD. Eighteen PD patients performed a series of daily walking tasks in a lab environment, with nine experiencing FoG. We trained and evaluated different classifiers using signals collected from wearable accelerometers placed on the patients' ankles. The low ratio of FoG labeled data compared with normal gait created an imbalanced dataset. The analysis of results revealed that the sensitivity of the SVM model to FoG could be improved from 91.9% to 96.5% by creating new synthesized FoG instances near the boundaries of two classes (normal gait and FoG). The SVM model can detect FoG events with an average sensitivity and specificity of 91.5% and 95.2% trained by the original dataset, and 95.8% and 95.0% trained by synthesized balanced dataset in patient-dependent models. Also, ADASYN slightly improved the average F-score of patient-dependent models from 90.6% to 91.2%, while reducing patient-independent model performance from 83.4% to 79.8%.

This paper presents an application of a socially assistive robotics (SAR) system to hands-off post-stroke rehabilitation. We validate the technical feasibility and efficacy of our system in guiding, motivating, and administering an upper extremity rehabilitation task. The robot, which consists of a humanoid torso on a mobile base, monitors user performance on a wire puzzle task through a wearable inertial measurement unit and signals from the puzzle. Smoothness of stroke-affected limb movement is used as the evaluation metric. Five adults of mild to moderate functional ability in the chronic phase of stroke recovery interacted with our SAR system over three separate days. The inertial data from the five participants were analyzed using frequency domain techniques. Subsequently, the amount of power in frequency bands corresponding to voluntary (0.1 to 2Hz) and involuntary motion/jerk (4 to 8Hz) was evaluated. We found that, in adults of mild severity (Upper Extremity Fugl-Meyer Assessment scores greater than 40), the motion becomes smoother (the amount of jerk is reduced) over 3 days of task practice. In adults of moderate motor severity (scores below 40), the motion became less smooth. This may indicate that the combination of our task and SAR system is better suited for individuals with higher functional ability, and needs augmentation in order to aid those of lower functional ability levels.

New approaches to rehabilitation and health care have developed due to advances in technology and human robot interaction (HRI). Socially assistive robotics (SAR) is a subcategory of HRI that focuses on providing assistance through hands-off interactions. We have developed a SAR architecture that facilitates multiple task-oriented interactions between a user and a robot agent. The architecture accommodates a variety of inputs, tasks, and interaction modalities that are used to provide relevant, real-time feedback to the participant. We have implemented the architecture and validated its technological feasibility in a small pilot study in which a SAR agent led three post-stroke individuals through an exercise scenario. In the following, we present our architecture design, and the results of the feasibility study.

In recent years, wearable sensing networks have been the focus of the biotechnology industry. A continuing the question is how best to integrate electronic components with the human body. The authors have devised a body area network that relies on two innovations; the use of conductive fabrics, and the use of DC powerline communication. By combining these innovations, we have created a truly wearable network that allows full generality of sensor location, spatial distribution of the medium to reduce overall bulk, and maintains sufficiently low line impedance for simultaneous power and data delivery over a single conductor. We have created a method for analysis of the transmission properties of conductive fabric garments. In addition, we evaluate the basic transmission line characteristics of the garment. Finally, we present a verification of our model and initial experimental results.

A wearable DC power line communication network is proposed for health sensing and rehabilitation. This system provides a network through which multiple sensors and actuators can send and receive both information and power. With such a network, sensors placed at many remote locations on the human body can send and receive information to a centralized power/data coordinator. This system consists of three main components: (1) the centralized power/data coordinator which coordinates communication among the nodes, (2) smart sensors and actuators, which have some localized data processing, and (3) the communications bus, which consists of two electrical conductors. The system operates using a two-tiered protocol, which relies on both polling and prioritization. During normal operation, the centralized coordinator constantly polls the sensors and actuators, obtaining biological information; When an emergency signal is generated by one of the nodes, it immediately notifies the central components, which in turn notify an Internet provider in order to alert a doctor, paramedic, or other safety personnel. First, a unique DC power line communication system is reviewed. Next, the details of our wearable DC power line communication network is discussed. Next, the design process for such a system is discussed in terms of the medium type and the number of sensor nodes in the network. Finally, a preliminary design of the proposed system is presented.

A novel material transport and handling system utilizing simultaneous information and power delivery is proposed. This system provides a convenient and unobtrusive method of sending documents, specimens, and material to multiple locations within a single building. It consists of a fixed track, central controller, central power supply, and multiple 'smart-carriers'. By using a fixed track, the system can be placed out of the way of normal ground level activity. The system allows for horizontal, as well as vertical travel. The 'smart-carriers' carry parcels along the tracks to and from various locations at the user's command. The 'smart-carriers' each have their own onboard micro-modem and controller. The track itself delivers the power and information signals to the smart-carriers. This design allows for a very simple and flexible system. Equation reduction was used to model a generic system with "n" smart carriers. Next, a powerline communication system was built and tested to evaluate the characteristics of the track. Protocols for communicating between the centralized controller and the carriers are introduced. Finally, a preliminary design of the proposed system is presented.

A system of networked smart motors is developed to reduce complex cable harnesses. Motor control signals are sent over the DC power bus line and receiver by motors with integrated power amplifiers and controller. Unlike traditional AC power line communication, the noise level and signal attenuation are much lower for the DC power bus communication. This allows for high fidelity, broadband communication among many smart motors without bulky, costly cables. A modem is designed to exploit the features of the DC power bus communication. Experimentation is done to verify that the DC bus line is indeed useful for communication. An experimental setup was developed to identify the noise spectrum and signal transmissibility of the consolidated power-signal line. Optimal carrier frequency and filter parameters are then obtained based on the experiments.

A system of multi-axis networked smart motors is developed to reduce complex cable harnesses. Motor control signals are sent over the DC power bus line and received by motors with integrated power amplifiers and controllers. The noise level and signal attenuation are low, allowing for high fidelity, broadband communication among many smart motors without bulky, costly cables. A modem is designed to exploit the features of the DC power bus communication. A power-signal coupling circuit with an impedance trap filter is designed for superimposing control signals over the DC power bus line with a maximum of signal transmissibility and reduced line noise. An experimental setup was developed to identify the noise spectrum and signal transmissibility of the consolidated power-signal line. Optimal carrier frequency and filter parameters are then obtained based on the experiments. A simple protocol for bi-directional communication between the motors and the central controller is designed and tested. Finally, the design of a joint undergoing continuous rotation is proposed utilizing the consolidated power-signal cable connected to endlessly spinning smart motors.

A servomotor design that is powered and controlled through only one wire is presented. A traditional servomotor needs both a power cable and a control cable connecting the motor to a control amplifier. Cables are bulky, heavy, and expensive and, more importantly, difficult to install and maintain in many applications. Particularly for multi-axis applications, like robots and machine tools, cable harnesses become thick and long, and are difficult to run through a stack of many axes, this is a major burden and bottleneck in electromechanical drives. The objective of this research is to eliminate such bulky cables by integrating and consolidating power cables and signal cables into a single wire, and transmitting control signals through the signal wire. Signals are coded by using a CDMA protocol and are superimposed on the single wire that supplies a DC voltage to each motor. In the paper first the principle of reduced-cable smart motors is described, followed by the architecture of the signal transmission system using direct sequence spread spectrum. A prototype system is designed, and the signal transmission line is simulated to verify the principle.