Devasena Inupakutika

The biggest challenge of using fiber Bragg grating (FBG) based sensors is the cross-sensitivity between the strain and temperature effects on FBG. In this letter, we demonstrate the ability of machine learning (ML) methods to discriminate between the strain and temperature effects on FBG sensors on a single measurement of change in the Bragg wavelength. Spectral data are collected using an FBG interrogation system at various strain and temperature conditions and are applied to different ML… Show more

The biggest challenge of using fiber Bragg grating (FBG) based sensors is the cross-sensitivity between the strain and temperature effects on FBG. In this letter, we demonstrate the ability of machine learning (ML) methods to discriminate between the strain and temperature effects on FBG sensors on a single measurement of change in the Bragg wavelength. Spectral data are collected using an FBG interrogation system at various strain and temperature conditions and are applied to different ML methods to determine the strain and temperature effects. We further simulate FBG with the same strain and temperature conditions using VPIphotonics. For comparison, the same ML methods are applied to both simulated and experimentally collected data. The experimental results reveal that our proposed model can predict strain and temperature with 90% accuracy on a single measurement of Bragg wavelength. We also demonstrate the stability of the model by comparing the testing and training errors of the applied ML methods. Therefore, our proposed technique reduces the cost and complexity associated with the existing FBG-based sensor system. Show less

With the evolving artificial intelligence technology, the chatbots are becoming smarter and faster lately. Chatbots are typically available round the clock providing continuous support and services. A chatbot or a conversational agent is a program or software that can communicate using natural language with humans. The challenge of developing an intelligent chatbot still exists ever since the onset of artificial intelligence. The functionality of chatbots can range from business oriented short… Show more

With the evolving artificial intelligence technology, the chatbots are becoming smarter and faster lately. Chatbots are typically available round the clock providing continuous support and services. A chatbot or a conversational agent is a program or software that can communicate using natural language with humans. The challenge of developing an intelligent chatbot still exists ever since the onset of artificial intelligence. The functionality of chatbots can range from business oriented short conversations to healthcare intervention based longer conversations. However, the primary role that the chatbots have to play is in understanding human utterances in order to respond appropriately. To that end, there is an increased emergence of Natural Language Understanding (NLU) engines by popular cloud service providers. The NLU services identify entities and intents from the user utterances provided as input. Thus, in order to integrate such understanding to a chatbot, this paper presents a study on existing major NLU platforms. Then, we present a case study chatbot integrated with Google DialogFlow and IBM Watson NLU services and discuss their intent recognition performance. Show less

We demonstrate the ability of machine learning methods to discriminate between the strain and the temperature effects on Fiber Bragg grating (FBG) sensor on a single measurement of Bragg wavelength change. This technique will reduce the cost and complexity of FBG-based sensor system.

Mobile Health (mHealth) apps are being widely used to monitor the health of patients with chronic medical conditions with the proliferation and the increasing use of smartphones. Mobile devices have limited computation power and energy supply which may lead to either delayed alarms, shorter battery life or excessive memory usage limiting their ability to execute resource-intensive functionality and inhibit proper medical monitoring. This paper presents a methodology for measurement-based… Show more

Mobile Health (mHealth) apps are being widely used to monitor the health of patients with chronic medical conditions with the proliferation and the increasing use of smartphones. Mobile devices have limited computation power and energy supply which may lead to either delayed alarms, shorter battery life or excessive memory usage limiting their ability to execute resource-intensive functionality and inhibit proper medical monitoring. This paper presents a methodology for measurement-based performance assessment of cloud backend and mobile networks that support mHealth services. The methodology targets the assessment of a prototype mHealth app developed for breast cancer patients undergoing Endocrine Hormone Therapy (EHT). It models third-party cloud backend services to examine the performance in a representative testing scenario for end-users accessing the app. Experimental results are reported and compared for native Android and iOS implementations. The analysis further reflects the impact of the network and device battery conditions on response times and end-user quality of experience. The contribution of this work is twofold: (a) First, it presents a performance methodology and analysis of a fully functional medication adherence management mHealth app implemented on major duopoly of mobile platforms (android and iOS) and (b) Second, based on the performance analysis, conclusions are drawn that serve as the recommendation pathway for the development of similar medical reference mobile apps. Show less

Mobile health (mHealth) apps have received increasing attention, due to their abilities to support patients who suffer from various conditions. mHealth apps may be especially helpful for patients with chronic diseases, by providing pertinent information, tracking symptoms, and inspiring adherence to medication regimens. To achieve these objectives, researchers need to prototype mHealth apps with dedicated software architectures. In this paper, a cloud-based mHealth application development… Show more

Mobile health (mHealth) apps have received increasing attention, due to their abilities to support patients who suffer from various conditions. mHealth apps may be especially helpful for patients with chronic diseases, by providing pertinent information, tracking symptoms, and inspiring adherence to medication regimens. To achieve these objectives, researchers need to prototype mHealth apps with dedicated software architectures. In this paper, a cloud-based mHealth application development concept is presented for chronic patient supportive care apps. The concept integrates existing software platforms and services for simplified app development that can be reused for other target applications. This developmental method also facilitates app portability, through the use of common components found across multiple mobile platforms, and scalability, through the loose coupling of services. The results are demonstrated by the development of native Android and cross-platform web apps, in a case study that presents an mHealth solution for endocrine hormone therapy (EHT). A performance analysis methodology, an app usability evaluation, based on focus group responses, and alpha and pre-beta testing results are provided. Show less

Wi-Fi fingerprinting-based indoor localization has received increased attention due to its proven accuracy and global availability. The common received-signal-strength-based (RSS) fingerprinting presents performance degradation due to well-known signal fluctuations, but more recently, the more stable channel state information (CSI) has gained popularity. In this paper, we present SDR-Fi, the first reported Wi-Fi software-defined radio (SDR) receiver for indoor positioning using CSI measurements… Show more

Wi-Fi fingerprinting-based indoor localization has received increased attention due to its proven accuracy and global availability. The common received-signal-strength-based (RSS) fingerprinting presents performance degradation due to well-known signal fluctuations, but more recently, the more stable channel state information (CSI) has gained popularity. In this paper, we present SDR-Fi, the first reported Wi-Fi software-defined radio (SDR) receiver for indoor positioning using CSI measurements as features for deep learning (DL) classification. The CSI measurements are obtained from a fast-prototyping LabVIEW-based 802.11n SDR receiver platform. SDR-Fi measures CSI data passively from pilot beacon frames from a single access point (AP) at almost 10 Hz rate. A feed-forward neural network and a 1D convolutional neural network are examined to estimate location accuracy in representative testing scenarios for an indoor cluttered laboratory area, and an adjacent, covered outdoor area. The proposed DL classification methods leverage CSI-based fingerprinting for low AP scenarios, as opposed to traditional RSS-based systems, which require many APs for reliable positioning. Demonstration results are threefold: (a) A fast-prototyping SDR platform that passively extracts CSI measurements from Wi-Fi beacon frames, providing a genuine possibility for vendor network cards to provide such measurements, (b) two state-of-the-art DL classification methods outperforming traditional RSS-based methods for low AP scenarios, (c) a testing methodology for performance evaluation of the proposed indoor positioning system. Show less

It has been a decade since smartphone application stores started allowing developers to post their own applications. This paper presents a narrative review on the state-of-the-art and the future of technology used by researchers in the field of mobile health promotion. Researchers build high cost, complex systems with the purpose of promoting health and collecting data. These systems promote health by using a feedback component that ''educates'' the subject. Other researchers instead use… Show more

It has been a decade since smartphone application stores started allowing developers to post their own applications. This paper presents a narrative review on the state-of-the-art and the future of technology used by researchers in the field of mobile health promotion. Researchers build high cost, complex systems with the purpose of promoting health and collecting data. These systems promote health by using a feedback component that ''educates'' the subject. Other researchers instead use platforms which provide them with data collected by others, which allows for no communication with subjects, but may be cheaper than building a system to collect the data. This second type of systems cannot be used directly for health promotion. However, both types of systems are relevant to the field of health promotion, because they are precursors to a third type of systems that are emerging, the gig economy systems for mobile health data collection, which are low cost, globally available, and provide limited communication with subjects. If such systems evolve to include more channels for communication with the data-generating subjects, and also bring developers into the economy, they may eventually revolutionize the field of mobile health promotion and data collection by giving researchers new capabilities, such as the ability to replicate existing health promotion campaigns with the click of a button and the appropriate licenses. In this paper we present a review of state-of-the-art systems for mobile health promotion and data collection and a model for what these systems may look like in the future. Show less

Adjuvant endocrine hormonal therapy (EHT) is highly effective and appropriate for nearly all breast cancer patients with hormone receptor-positive tumors, which represent 75% of all breast cancer diagnoses. Long-term use of EHT reduces recurrence rates and nearly halves the risk of death during the second decade after diagnosis. Despite the proven benefits, about 33% of women receiving EHT do not take their medication as prescribed. This causes an increase in the risk for recurrence and… Show more

Adjuvant endocrine hormonal therapy (EHT) is highly effective and appropriate for nearly all breast cancer patients with hormone receptor-positive tumors, which represent 75% of all breast cancer diagnoses. Long-term use of EHT reduces recurrence rates and nearly halves the risk of death during the second decade after diagnosis. Despite the proven benefits, about 33% of women receiving EHT do not take their medication as prescribed. This causes an increase in the risk for recurrence and death.

To promote adherence to EHT among breast cancer patients, this study will develop and pilot-test an intervention consisting of 1) a bilingual, culturally tailored, personalized, interactive smartphone application (app); and 2) support from a patient navigator. The control group will receive usual care. This 2-group randomized control trial will recruit 120 breast cancer patients receiving EHT at the Mays Cancer Center at UT Health San Antonio. The two-year study will have 3-time assessments (baseline, 3 and 6 months).

This theory-based intervention will empower patients' self-monitoring and management. It will facilitate patient education, identification/reporting of side effects, delivery of self-care advice, and simplify communication between the patient and the oncology team. The ultimate goal of this innovative multi-communication intervention is to improve overall survival and life expectancy, enhance quality of life, reduce recurrence, and decrease healthcare cost. The anticipated outcome is a scalable, evidence-based, and easily disseminated intervention with potentially broad use to patients using EHT and other oral anticancer agents. Show less

Rapidly evolving technologies like data analysis, smartphone and web-based applications, and the Internet of things have been increasingly used for healthy living, fitness and well-being. These technologies are being utilized by various research studies to reduce obesity. This paper demonstrates design and development of a dataflow protocol that integrates several applications. After registration of a user, activity, nutrition and other lifestyle data from participants are retrieved in a… Show more

Rapidly evolving technologies like data analysis, smartphone and web-based applications, and the Internet of things have been increasingly used for healthy living, fitness and well-being. These technologies are being utilized by various research studies to reduce obesity. This paper demonstrates design and development of a dataflow protocol that integrates several applications. After registration of a user, activity, nutrition and other lifestyle data from participants are retrieved in a centralized cloud dedicated for health promotion. In addition, users are provided accounts in an e-Learning environment from which learning outcomes can be retrieved. Using the proposed system, health promotion campaigners have the ability to provide feedback to the participants using a dedicated messaging system. Participants authorize the system to use their activity data for the program participation. The implemented system and servicing protocol minimize personnel overhead of large-scale health promotion campaigns and are scalable to assist automated interventions, from automated data retrieval to automated messaging feedback. This paper describes end-to-end workflow of the proposed system. The case study tests are carried with Fitbit Flex2 activity trackers, Withings Scale, Verizon Android-based tablets, Moodle learning management system, and Articulate RISE for learning content development. Show less

The use of mobile and web tools in health care has greatly improved interactions between doctors, patients and healthcare professionals in the past few years. According to the University of Texas Health Science Center at San Antonio (UTHSCSA) almost 75% of the 296,980 women in the United States that are diagnosed with breast cancer will have hormone receptor-positive breast cancers. Endocrine hormonal therapy (EHT) is very effective for nearly all women with hormone-receptive positive tumours… Show more

The use of mobile and web tools in health care has greatly improved interactions between doctors, patients and healthcare professionals in the past few years. According to the University of Texas Health Science Center at San Antonio (UTHSCSA) almost 75% of the 296,980 women in the United States that are diagnosed with breast cancer will have hormone receptor-positive breast cancers. Endocrine hormonal therapy (EHT) is very effective for nearly all women with hormone-receptive positive tumours and is the most widely prescribed one. The dedicated use and adherence to this therapy for 5 years has also shown larger reduction in recurrence [6]. However, even with such proven benefits, the adherence is limited to just 33% of all the women who are prescribed. In such cases, the use of interactive easy-to-use apps would promote and improve adherence [2]. Such apps should enable fast responses to patient queries, guide patients through treatment, help them understand symptoms, motivate them through educational content, and prompt interaction with their peers. In this paper, we describe an approach for accelerating app prototyping using the existing Google Android platform and converting it to a cross-platform web application thereafter. Google Firebase [1] is used as a database server to assist in monitoring and sending notifications to users without compromising the safety and security of patients' data. The proposed system and approach can also be further tailored for similar technology-assisted health promotion and intervention studies. The effectiveness of the approach is evaluated through a randomized controlled study with breast cancer patients conducted by the UTHSCSA research team. Show less