Rohit Chaudhri

BALANCE: towards a usable pervasive wellness application with accurate activity inference

Technology offers the potential to objectively monitor peoples eating and activity behaviors and encourage healthier lifestyles. BALANCE is a mobile phone-based system for long term wellness management. The BALANCE system automatically detects the users caloric expenditure via sensor data from a Mobile Sensing Platform unit worn on the hip. Users manually enter information on foods eaten via an interface on an N95 mobile phone. Initial validation experiments measuring oxygen consumption during treadmill walking and jogging show that the systems estimate of caloric output is within 87% of the actual value. Future work will refine and continue to evaluate the systems efficacy and develop more robust data input and activity inference methods.

Open data kit 2.0: expanding and refining information services for developing regions

Open Data Kit (ODK) is an open-source, modular toolkit that enables organizations to build application-specific information services for use in resource-constrained environments. ODK is one of the leading data collection solutions available and has been deployed by a wide variety of organizations in dozens of countries around the world. This paper discusses how recent feedback from users and developers led us to redesign the ODK system architecture. Specifically, the design principles for ODK 2.0 focus on: 1) favoring runtime languages over compile time languages to make customizations easier for individuals with limited programming experience; 2) implementing basic data structures as single rows within a table of data; 3) storing that data in a database that is accessible across applications and client devices; and 4) increasing the diversity of input types by enabling new data input methods from sensors. We discuss how these principles have led to the refinement of the existing ODK tools, and the creation of several new tools that aim to improve the toolkit, expand its range of applications, and make it more customizable by users.

Open data kit sensors: a sensor integration framework for android at the application-level

Smartphones can now connect to a variety of external sensors over wired and wireless channels. However, ensuring proper device interaction can be burdensome, especially when a single application needs to integrate with a number of sensors using different communication channels and data formats. This paper presents a framework to simplify the interface between a variety of external sensors and consumer Android devices. The framework simplifies both application and driver development with abstractions that separate responsibilities between the user application, sensor framework, and device driver. These abstractions facilitate a componentized framework that allows developers to focus on writing minimal pieces of sensor-specific code enabling an ecosystem of reusable sensor drivers. The paper explores three alternative architectures for application-level drivers to understand trade-offs in performance, device portability, simplicity, and deployment ease. We explore these tradeoffs in the context of four sensing applications designed to support our work in the developing world. They highlight a range of sensor usage models for our application-level driver framework that vary data types, configuration methods, communication channels, and sampling rates to demonstrate the frameworks effectiveness.

Open data kit sensors: mobile data collection with wired and wireless sensors

Sensing data is important to a variety of data collection and monitoring applications. This paper presents the ODK Sensors framework designed to simplify the process of integrating sensors into mobile data collection tasks for both programmers and data collectors. Current mobile platforms (e.g., smartphones, tablets) can connect to a variety of external sensors over wired (USB) and wireless (Bluetooth) channels. However, the proper implementation can be burdensome, especially when a single application needs to support a variety of sensors with different communication channels and data formats. Our goal is to provide a high level framework that allows for customization and flexibility of applications that interface with external sensors, and thus support a variety of information services that rely on sensordata. We use four application examples to highlight the range of usage models and the ease with which the applications can be developed.

FoneAstra: making mobile phones smarter

FoneAstra is a low-cost, programmable device that extends capabilities of mobile phones. We show how our device extends the functionality of non-programmable, low-tier mobile phones that are most prevalent amongst people from low-income groups in developing regions. FoneAstra enables interesting mobile applications in a variety of domains ranging from participatory sensing to remote monitoring to healthcare. The paper describes several applications that we are currently developing. As a first sample application, we demonstrate location tracking capability on low-tier mobile phones that are not programmable and do not have GPS capability. In prototype quantities, FoneAstra costs only

An RFID based system for monitoring free weight exercises

15.

Monitoring Vaccine Cold Chains in Developing Countries

In this paper we present preliminary results and future directions of work for a project in which we are building an RFID based system to sense and monitor free weight exercises.

Sensors and Smartphones: Tracking Water Collection in Rural Ethiopia

FoneAstra is a low-cost mobile-phone-based sensing system for monitoring national vaccine cold chains. In its first pilot deployment, the system successfully diagnosed several issues.

Demonstrating the efficacy of the FoneAstra pasteurization monitor for human milk pasteurization in resource-limited settings.

In rural areas, residents often venture far distances to collect water for everyday use. A low-power wireless system records motion and leverages Bluetooth-enabled smartphones, retrieving data from sensors attached to household water containers, to help researchers understand the effects of water policies and water-source locations.

A system for safe flash-heat pasteurization of human breast milk

UNLABELLED Human milk provides crucial nutrition and immunologic protection for infants. When a mothers own milk is unavailable, donated human milk, pasteurized to destroy bacteria and viruses, is a lifesaving replacement. Flash-heat pasteurization is a simple, low-cost, and commonly used method to make milk safe, but currently there is no system to monitor milk temperature, which challenges quality control. FoneAstra, a smartphone-based mobile pasteurization monitor, removes this barrier by guiding users through pasteurization and documenting consistent and safe practice. This study evaluated FoneAstras efficacy as a quality control system, particularly in resource-limited settings, by comparing bacterial growth in donor milk flash-heated with and without the device at a neonatal intensive care unit in Durban, South Africa. MATERIALS AND METHODS For 100 samples of donor milk, one aliquot each of prepasteurized milk, milk flash-heated without FoneAstra, and milk pasteurized with FoneAstra was cultured on routine agar for bacterial growth. Isolated bacteria were identified and enumerated. RESULTS In total, 300 samples (three from each donor sample) were analyzed. Bacterial growth was found in 86 of the 100 samples before any pasteurization and one of the 100 postpasteurized samples without FoneAstra. None of the samples pasteurized using FoneAstra showed bacterial growth. CONCLUSIONS Both pasteurization methods were safe and effective. FoneAstra, however, provides the additional benefits of user-guided temperature monitoring and data tracking. By improving quality assurance and standardizing the pasteurization process, FoneAstra can support wide-scale implementation of human milk banks in resource-limited settings, increasing access and saving lives.