Yogendra Patil

Robust Cyber-Physical Systems

In this paper we comprehensively survey the concept and strategies for building a resilient and integrated cyber-physical system (CPS). Here resilience refers to a 3S-oriented design, that is, stability, security, and systematicness: Stability means the CPS can achieve a stable sensing-actuation close-loop control even though the inputs (sensing data) have noise or attacks; Security means that the system can overcome the cyber-physical interaction attacks; and Systematicness means that the system has a seamless integration of sensors and actuators. We will also explain the CPS modeling issues since they serve as the basics of 3S design. We will use two detailed examples from our achieved projects to explain how to achieve arobust, systematic CPS design: Case study 1 is on the design of a rehabilitation system with cyber (sensors) and physical (robots) integration. Case Study 2 is on the implantable medical device design. It illustrates the nature of CPS security principle. The dominant feature of this survey is that it has both principle discussions and practical cyber-physical coupling design. Comprehensive survey on entire CPS design process.Qualitative and quantitative descriptions on CPS resilience.From basic concepts to case studies.Point out the future research trends.

Monitoring of Cigarette Smoking Using Wearable Sensors and Support Vector Machines

Cigarette smoking is a serious risk factor for cancer, cardiovascular, and pulmonary diseases. Current methods of monitoring of cigarette smoking habits rely on various forms of self-report that are prone to errors and under reporting. This paper presents a first step in the development of a methodology for accurate and objective assessment of smoking using noninvasive wearable sensors (Personal Automatic Cigarette Tracker - PACT) by demonstrating feasibility of automatic recognition of smoke inhalations from signals arising from continuous monitoring of breathing and hand-to-mouth gestures by support vector machine classifiers. The performance of subject-dependent (individually calibrated) models was compared to performance of subject-independent (group) classification models. The models were trained and validated on a dataset collected from 20 subjects performing 12 different activities representative of everyday living (total duration 19.5 h or 21411 breath cycles). Precision and recall were used as the accuracy metrics. Group models obtained 87% and 80% of average precision and recall, respectively. Individual models resulted in 90% of average precision and recall, indicating a significant presence of individual traits in signal patterns. These results suggest the feasibility of monitoring cigarette smoking by means of a wearable and noninvasive sensor system in free living conditions.

Detection of Hand-to-Mouth Gestures Using a RF Operated Proximity Sensor for Monitoring Cigarette Smoking

Common methods for monitoring of cigarette smoking, such as portable puff-topography instruments or self-report questionnaires, tend to be biased due to conscious or unconscious underreporting. Additionally, these methods may change the natural smoking behavior of individuals. Our long term objective is the development of a wearable non-invasive monitoring system (Personal Automatic Cigarette Tracker – PACT) to reliably monitor cigarette smoking behavior under free living conditions. PACT monitors smoking by observing characteristic breathing patterns of smoke inhalations that follow a cigarette-to-mouth hand gesture. As envisioned, PACT does not rely on self-report or require any conscious effort from the user. A major element of the PACT is a proximity sensor that detects typical cigarette-to-mouth gesture during cigarette smoking. This study describes the design and validation of a prototype RF proximity sensor that captures hand-to-mouth gestures with a high sensitivity (0.90), and a methodology that can reject up to 68% of artifacts gestures originating from activities other than cigarette smoking.

Detection of cigarette smoke inhalations from respiratory signals using reduced feature set

A combination of wearable Respiratory Inductive Plethysmograph and a hand-to-mouth Proximity Sensor (PS) can be used to monitor smoking habits and smoke exposure in cigarette smokers. In our previous work, detection of smoke inhalations was achieved by using a Support Vector Machine (SVM) classifier applied to raw sensor signals with 1503-element feature vectors. This study uses empirically-defined 27 features computed from the sensor signals to reduce the length of vectors. Further reduction in the length of the feature vectors was achieved by a forward feature selection algorithm, identifying from 2 to 16 features most critical for smoke inhalations detection. For individual detection models, the 1503-element feature vectors, 27-element feature vectors and reduced feature vectors resulted in F-scores of 90.1%, 68.7% and 94% respectively. For the group models, F-scores were 81.3%, 65% and 67% respectively. These results demonstrate feasibility of detecting smoke inhalations with a computed feature set, but suggest high individuality of breathing patterns associated with smoking.

Cyberphysical System With Virtual Reality for Intelligent Motion Recognition and Training

In this paper, we propose to build a comprehensive cyberphysical system (CPS) with virtual reality (VR) and intelligent sensors for motion recognition and training. We use both wearable wireless sensors (such as electrocardiogram, motion sensors) and nonintrusive wireless sensors (such as gait sensors) to monitor the motion training status. We first provide our CPS architecture. Then we focus on motion training from three perspectives: 1) VR-first we introduce how we can use motion capture camera to trace the motions; 2) gait recognition-we have invented low-cost small wireless pyroelectric sensor, which can recognize different gaits through Bayesian pattern learning. It can automatically measure gait training effects; and 3) gesture recognition-to quickly tell what motions the subject is doing, we propose a low-cost, low-complexity motion recognition system with 3-axis accelerometers. We will provide hardware and software design. Our experimental results validate the efficiency and accuracy of our CPS design.

Home Oriented Virtual e-Rehabilitation

We present a collaborative framework to provide a simple solution for home-oriented rehabilitation of post-stroke patients. Our final aim is to build a system that will act like a therapist, giving sound advice to the patient and also improve patient’s confidence to perform their daily routine activities independently. In this study, we discuss our rehab system, with strong emphasis on techniques implemented for the integration of rehab robot with the virtual reality games. Experimental observations proves the feasibility of our system.

Exploring Incomplete Rating Designs With Mokken Scale Analysis

Recent research has explored the use of models adapted from Mokken scale analysis as a nonparametric approach to evaluating rating quality in educational performance assessments. A potential limiting factor to the widespread use of these techniques is the requirement for complete data, as practical constraints in operational assessment systems often limit the use of complete rating designs. In order to address this challenge, this study explores the use of missing data imputation techniques and their impact on Mokken-based rating quality indicators related to rater monotonicity, rater scalability, and invariant rater ordering. Simulated data and real data from a rater-mediated writing assessment were modified to reflect varying levels of missingness, and four imputation techniques were used to impute missing ratings. Overall, the results indicated that simple imputation techniques based on rater and student means result in generally accurate recovery of rater monotonicity indices and rater scalability coefficients. However, discrepancies between violations of invariant rater ordering in the original and imputed data are somewhat unpredictable across imputation methods. Implications for research and practice are discussed.

A Multi-interface VR Platform For Rehabilitation Research

With the introduction of new Virtual Reality (VR) devices such as Microsoft HoloLens, Oculus, HTC Vive etc., one cannot ignore the fact that research related to Human and VR interaction is bound to take a big leap. One of the main areas that has already gain momentum, is the area of VR based stroke rehabilitation research. Although many VR based research studies have been performed for lower and upper extremity training purposes, very few research studies are related to development of VR based research platforms. However, these platforms are usually single device dedicated, and therefore cannot be used to add another device. This study contributes to the field of HCI by achieving three major goals-- 1) explore the design aspects of VR based training research; 2) innovate the field of VR based training research by developing a multi-interface platform; and 3) inspire future researchers by providing an open source SDK so as to expand the horizon for human VR interaction. A pilot study was conducted in order to test the applicability of our platform, using 25 healthy subjects across four different interfaces. From the promising results achieved during the pilot study we are currently in the process of evaluating our platform using stroke patients at the Spain Rehabilitation Center at the University of Alabama, in Birmingham. Our findings and insights could inform future VR based rehabilitation system designs and help researchers and other stakeholders to assess the viability of using VR based scenarios for training purposes.