Search

With the pervasive use of smartphones, which contain numerous sensors, data for modeling human activity is readily available. Human activity recognition is an important area of research because it can be used in context-aware applications. It has significant influence in many other research areas and applications including healthcare, assisted living, personal fitness, and entertainment. There has been a widespread use of machine learning techniques in wearable and smartphone based human activity recognition. Despite being an active area of research for more than a decade, most of the existing approaches require extensive computation to extract feature, train model, and recognize activities. This study presents a computationally efficient smartphone based human activity recognizer, based on dynamical systems and chaos theory. A reconstructed phase space is formed from the accelerometer sensor data using time-delay embedding. A single accelerometer axis is used to reduce memory and computational complexity. A Gaussian mixture model is learned on the reconstructed phase space. A maximum likelihood classifier uses the Gaussian mixture model to classify ten different human activities and a baseline. One public and one collected dataset were used to validate the proposed approach. Data was collected from ten subjects. The public dataset contains data from 30 subjects. Out-of-sample experimental results show that the proposed approach is able to recognize human activities from smartphones’ one-axis raw accelerometer sensor data. The proposed approach achieved 100% accuracy for individual models across all activities and datasets. The proposed research requires 3 to 7 times less amount of data than the existing approaches to classify activities. It also requires 3 to 4 times less amount of time to build reconstructed phase space compare to time and frequency domain features. A comparative evaluation is also presented to compare proposed approach with the state-of-the-art works.

Objective To develop an educational mobile application (app) for expectant parents diagnosed with risk factors for premature birth. Methods Parent and medical advisory panels delineated the vision for the app. The app helps prepare for preterm birth. For pilot testing, obstetricians offered the app between 18–22 weeks gestational age to English speaking parents with risk factors for preterm birth. After 4 weeks of use, each participant completed a questionnaire. The software tracked topics accessed and duration of use. Results For pilot testing, 31 participants were recruited and 28 completed the questionnaire. After app utilization, participants reported heightened awareness of preterm birth (93%), more discussion of pregnancy or prematurity issues with partner (86%), increased questions at clinic visits (43%), and increased anxiety (21%). Participants reported receiving more prematurity information from the app than from their healthcare providers. The 15 participants for whom tracking data was available accessed the app for an average of 8 h. Conclusion Parents with increased risk for preterm birth may benefit from this mobile app educational program. Practice implications If the pregnancy results in preterm birth hospitalization, parents would have built a foundation of knowledge to make informed medical care choices.

The wide use of motor imagery as a paradigm for brain-computer interfacing (BCI) points to its characteristic ability to generate discriminatory signals for communication and control. In recent times, deep learning techniques have increasingly been explored, in motor imagery decoding. While deep learning techniques are promising, a major challenge limiting their wide adoption is the amount of data available for decoding. To combat this challenge, data augmentation can be performed, to enhance decoding performance. In this study, we performed data augmentation by synthesizing motor imagery (MI) electroencephalography (EEG) trials, following six approaches. Data generated using these methods were evaluated based on four criteria, namely - the accuracy of prediction, the Frechet Inception distance (FID), the t-distributed Stochastic Neighbour Embedding (t-SNE) plots and topographic head plots. We show, based on these, that the synthesized data exhibit similar characteristics with real data, gaining up to 3% and 12% increases in mean accuracies across two public datasets. Finally, we believe these approaches should be utilized in applying deep learning techniques, as they not only have the potential to improve prediction performances, but also to save time spent on subject data collection.

Research Objectives To Implement Human Computer Interface (HCI) with digital image processing for a new approach to control assistive robots. Design Experimental Study. Setting In UWM BioRobotics Lab. Participants Healthy participants. Interventions Assistive robot control for daily living activities(Eating, Picking/Placing Objects), Nose tracking cursor control, User interface. Main Outcome Measures #Control the computer cursor with nose movements. #App Interface is developed to control the robotic arm. #Control the interface using nose and teeth (showing teeth triggered the click events) to control the assistive robotic arm. Results Result contains the demonstration of the control of a robotic arm with nose tracking control through an user interface. External webcam was used to get the real-time video for tracking the nose for cursor movement. We conducted experiments on healthy subjects. The feedbacks are recorded in Tables. We compared the results with other two techniques which are eye tracking and camera mouse for cursor movement and clicking events in terms of error pixels and other factors. Conclusions The nose tracking cursor control is mainly for the disabled people who are struggling with or unable to do their basic day to day tasks for their motor dysfunctions. This method will help them to access and control over a computer as well as a robotic assistive arm to ease their lives. Author(s) Disclosures No Conflict

A centralized clinical data repository is essential for inspecting patients’ medical history, disease analysis, population-wide disease research, treatment decision support, and improving existing healthcare policies and services. Bangladesh, a rapidly developing country, poses several unusual challenges for developing such a centralized clinical data repository as the existing Electronic Health Records (EHR) are stored in unconnected, heterogeneous sources with no unique patient identifier and consistency. Data integration with secure record linkage, privacy preservation, quality control, and data standardization are the main challenges for developing a consistent and interoperable centralized clinical data repository. Based on the findings from our previous researches, we have designed an anonymous National Clinical Data Warehouse (NCDW) framework to reinforce research and analysis. The architecture of NCDW is divided into five stages to overcome the challenges: (1) Wrapper-based anonymous data acquisition; (2) Data loading and staging; (3) Transformation, standardization, and uploading to the data warehouse; (4) Management and monitoring; (5) Data Mart design, OLAP server, data mining, and applications. A prototype of NCDW has been developed with a complete pipeline from data collection to analytics by integrating three data sources. The proposed NCDW model facilitates regional and national decision support, intelligent disease analysis, knowledge discovery, and data-driven research. We have inspected the analytical efficacy of the framework by qualitative evaluation of the national decision support from two derived disease data marts. The experimental result based on the analysis is satisfactory to extend the NCDW on a large scale.

Non-invasive methods in the assessment of health parameters are important for various kinds of patient, but only few expensive and inconvenient solutions are available. Investigations of non-invasive methods beginning with simple red-green-blue (RGB) imaging extending to hyperspectral camera-based image have encountered portability, usability, and reliability issues. This paper presents a smartphone-based non-invasive hemoglobin level prediction model that addresses portability, accuracy and ease-of-use problems by taking advantage of the built-in high-resolution camera, significant computation ability, storage, and communication facility of current smartphones. In this research work, RGB information of a 10-second fingertip videois used to convert into different color spaces including hue (H), saturation (S), value (V), lightness (L), a, b (a and b for the color dimensions) and gray (g). Later, features are extracted from all the combinations of ten different colors and applied to a Partial Least Squares (PLS) algorithm. We have evaluated the best color combination to generate a prediction model with the data collected from American and Bangladeshi patients. Our model with a specific pixel color combination achieves a reliable accuracy.

Research Objectives To provide a reliable and easy to Joystick controlled transportation/manipulation system for individuals with restricted mobility for their daily tasks. Design Experimental study. Setting In UWM BioRobotics Lab. Participants Healthy and young participants. Interventions Collaborative Robotic Arm for Activities of Daily Living assistance (picking objects from a desk, the floor, opening doors, drawers and eating), finger/Chin Joystick Control. Main Outcome Measures * Control robotics arm with finger and chin while keeping control of the wheelchair's mobility. * A lightweight software capable of controlling a robotic arm with generic/commercial joysticks. * Intuitive and easy to learn operability of the robotic arm with its multiple control modes. Results The system is composed by a power wheelchair (in this case a Permobil M3 Corpus), a robotic arm (a 6 Degree of Freedom arm with its control box) and the two user joysticks (finger and chin). Some circuitry was developed in order to communicate with the wheelchair electrical system. The experiments were performed by healthy personal in order to measure the operability and ease to use of this controller. The experiment's mean time as well as its difficulty seen by the participants were some of the variables to compare. A 3D trajectory of the robot arm end effector was recorded for the 4 different Activities in the Daily Living using the two different control devices. Each experiment had a fixed position for the wheelchair and the same initial position for the robotic arm. Conclusions The finger/chin joystick control is meant for individuals with restricted mobility, to allow them to perform their activities of daily living that were previously impossible to. This method will allow the to integrate a robotic arm in their power wheelchair system and expand its capabilities. Author(s) Disclosures No conflict.

RFID (Radio Frequency IDentification) is anticipated to be a core technology that will be used in many practical applications of our life in near future. It has received considerable attention within the healthcare for almost a decade now. The technology’s promise to efficiently track hospital supplies, medical equipment, medications and patients is an attractive proposition to the healthcare industry. However, the prospect of wide spread use of RFID tags in the healthcare area has also triggered discussions regarding privacy, particularly because RFID data in transit may easily be intercepted and can be send to track its user (owner). In a nutshell, this technology has not really seen its true potential in healthcare industry since privacy concerns raised by the tag bearers are not properly addressed by existing identification techniques. There are two major types of privacy preservation techniques that are required in an RFID based healthcare system—(1) a privacy preserving authentication protocol is required while sensing RFID tags for different identification and monitoring purposes, and (2) a privacy preserving access control mechanism is required to restrict unauthorized access of private information while providing healthcare services using the tag ID. In this paper, we propose a framework (PriSens-HSAC) that makes an effort to address the above mentioned two privacy issues. To the best of our knowledge, it is the first framework to provide increased privacy in RFID based healthcare systems, using RFID authentication along with access control technique.

Privacy preservation in RFID systems is a very important issue in modern day world. Privacy activists have been worried about the invasion of user privacy while using various RFID systems and services. Hence, significant efforts have been made to design RFID systems that preserve users' privacy. Majority of the privacy preserving protocols for RFID systems require the reader to search all tags in the system in order to identify a single RFID tag which not efficient for large scale systems. In order to achieve high-speed authentication in large-scale RFID systems, researchers propose tree-based approaches, in which any pair of tags share a number of key components. Another technique is to perform group-based authentication that improves the tradeoff between scalability and privacy by dividing the tags into a number of groups. This novel authentication scheme ensures privacy of the tags. However, the level of privacy provided by the scheme decreases as more and more tags are compromised. To address this issue, in this paper, we propose a group based anonymous private authentication protocol (AnonPri) that provides higher level of privacy than the above mentioned group based scheme and achieves better efficiency (in terms of providing privacy) than the approaches that prompt the reader to perform an exhaustive search. Our protocol guarantees that the adversary cannot link the tag responses even if she can learn the identifier of the tags. Our evaluation results demonstrates that the level of privacy provided by AnonPri is higher than that of the group based authentication technique.

The current SARS-CoV-2, better know as COVID-19, has emerged as a serious pandemic with life-threatening clinical manifestations and a high mortality rate. One of the major complications of this disease is the rapid and dangerous pulmonary deterioration that can lead to critical pneumonia conditions, resulting in death. The current healthcare system around the world faces the potential problem of lacking resources to assist a large number of patients at the same time; then, the non-critical patients are mostly referred to perform self-isolation/quarantine at home. This pandemic has placed new demands on the health systems world, asking for novel, rapid and secure ways to monitor patients in order to detect and quickly report patient’s symptoms to the healthcare provider, even if they are not in the hospital. While tremendous efforts have been done to develop technologies to detect the virus, create the vaccine, and stop the spread of the disease, it is also important to develop IoT technologies that can help track and monitor diagnosed COVID-19 patients from their homes. In this paper, we explore the possibility of monitoring respiration rates (RR) of COVID-19 patients using a widely-available technology at home – WiFi. Using the at-home WiFi signals, we propose Wi-COVID, a non-invasive and non-wearable technology to monitor the patient and track RR for the healthcare provider. We first introduce the currently available applications that can be done using WiFi signals. Then, we propose the framework scheme for an end-to-end non-invasive monitoring platform of the COVID-19 patients using WiFi. Finally, we present some preliminary results of the proposed framework. We envision the proposed platform as a life-changing technology that leverages WiFi technology as a non-wearable and non-invasive way to monitor COVID-19 patients at home.

This randomized controlled trial feasibility study tested the effectiveness of an iPad® application (app) social script intervention for children with autism spectrum disorder (ASD) going to imaging and their parent (n=32 parent/child dyads). Parents of the children exposed to the app (n=16) had lower state anxiety compared to the parents whose children were not exposed to the app (n=16) (effect size 0.33). Children exposed to the app had fewer externalized challenging behaviors than the control group (effect size 0.56). The results demonstrate feasibility and efficacy of the intervention. Further study of the iPad app is warranted.

As climate change is becoming an important global issue, more and more people are beginning to pay attention to reducing greenhouse gas emissions. To measure personal or household carbon dioxide emission, there are already plenty of carbon footprint calculators available on the web. Most of these calculators use quantitative models to estimate carbon emission caused by a user's activities. Although these calculators can promote public awareness regarding carbon emission due to an individual's behavior, there are concerns about the consistency and transparency of these existing CO 2 calculators. Apart from a small group of smart phone based carbon footprint calculator applications, most of the existing CO 2 calculators require users to input data manually. This not only provides a poor user experience but also makes the calculation less accurate. The use of a standard framework for various carbon footprint application developments can increase the accuracy of overall calculations, which in turn may increase energy awareness at the individual human level. We aim for developing a carbon footprint calculation framework that can serve as a platform for various carbon footprint calculator applications. Therefore, in this paper, we propose a platform-agnostic Open Carbon Footprint Framework ( OCFF ) that will provide the necessary interfaces for software developers to incorporate the latest scientific knowledge regarding climate change into their applications. OCFF will maintain a clouded knowledge base that will give developers access to a dynamic source of computational information that can be brought to bear on real-time sensor data. Based on the OCFF platform, we developed a Ubiquitous Carbon Footprint Calculator application ( UCFC ) that allows the user to be aware of their personal carbon footprint based on their ubiquitous activity and act accordingly. The major contribution of this paper is the presentation of the quantitative model of the platform along with the entire design and implementation of UCFC application. We also present the results, analysis, and findings of an extensive survey that has been conducted to find users’ awareness of increased carbon footprint, feature requirements, and expectations and desires to alleviate CO 2 emissions by using a footprint calculator. The design of UCFC application incorporates the analysis and inferences of the survey results. We are also developing a fuel efficient mobile GPS application for iPhone suggesting the greenest/most fuel efficient route to the user. In this paper, we also point out some important features of such an application.

The rapid decrease in the size of mobile devices, coupled with an increase in capability, has enabled a swift proliferation of small and very capable devices into our daily lives. With such a prevalence of pervasive computing, the interaction among portable devices needs to be continuous and invisible to device users. As these devices become better connected, collaboration among them will play a vital role in sharing resources in an ad-hoc manner. The sharing of resources works as a facilitator for pervasive devices. However, this ad hoc interaction among devices provides the potential for security breaches. Trust can fight against such security violations by restricting malicious nodes from participating in interactions. Therefore, we need a unified trust relationship model between entities, which captures both the needs of the traditional computing world and the world of pervasive computing where the continuum of trust is based on identity, physical context or a combination of both. Here, we present a context specific and reputation-based trust model along with a brief survey of trust models suitable for peer-to-peer and ad-hoc environments. This paper presents a multi-hop recommendation protocol and a flexible behavioral model to handle interactions. One other contribution of this paper is the integration of an initial trust model; this model categorizes services or contexts in different security levels based on their security needs, and these security needs are considered in trust bootstrapping. The other major contribution of this paper is a simple method of handling malicious recommendations. This paper also illustrates the implementation and evaluation of our proposed formal trust model.

As portable devices have become a part of our everyday life, more people are unknowingly participating in a pervasive computing environment. People engage with not a single device for a specific purpose but many devices interacting with each other in the course of ordinary activity. With such prevalence of pervasive technology, the interaction between portable devices needs to be continuous and imperceptible to device users. Pervasive computing requires a small, scalable and robust network which relies heavily on the middleware to resolve communication and security issues. In this paper, we present the design and implementation of S-MARKS which incorporates device validation, resource discovery and a privacy module.

To cope with the challenges posed by device capacity and capability, and also the nature of ad hoc networks, a Service discovery model is needed that can resolve security and privacy issues with simple solutions. The use of complex algorithms and powerful fixed infrastructure is infeasible due to the volatile nature of pervasive environment and tiny pervasive devices. In this paper, we present a trust-based secure Service discovery model, TSSD (trust-based secure service discovery) for a truly pervasive environment. Our model is a hybrid one that allows both secure and non-secure discovery of services. This model allows Service discovery and sharing based on mutual trust. The security model handles the communication and service sharing security issues. TSSD also incorporates a trust mode for sharing Services with unknown devices.

One of the major problems in industrial security management is that most organizations or enterprises do not provide adequate guidelines or well-defined policy with respect to trust management, and trust is still an afterthought in most security engineering projects. With the increase of handheld devices, managers of business organizations tend to use handheld devices to access the information systems. However, the connection or access to an information system requires appropriate level of trust. In this paper, we present a flexible, manageable, and configurable software-based trust framework for the handheld devices of mangers to access distributed information systems. The presented framework minimizes the effects of malicious recommendations related to the trust from other devices or infrastructures. The framework allows managers to customize trust-related settings depending on network environments in an effort to create a more secure and functional network. To cope with the organizational structure of a large enterprise, within this framework, handheld devices of managers are broken down into different categories based upon available resources and desired security functionalities. The framework is implemented and applied to build a number of trust sensitive applications such as health care.