Cheng-Kang Hsieh

Ohmage: A General and Extensible End-to-End Participatory Sensing Platform

Participatory sensing (PS) is a distributed data collection and analysis approach where individuals, acting alone or in groups, use their personal mobile devices to systematically explore interesting aspects of their lives and communities [Burke et al. 2006]. These mobile devices can be used to capture diverse spatiotemporal data through both intermittent self-report and continuous recording from on-board sensors and applications. Ohmage (http://ohmage.org) is a modular and extensible open-source, mobile to Web PS platform that records, stores, analyzes, and visualizes data from both prompted self-report and continuous data streams. These data streams are authorable and can dynamically be deployed in diverse settings. Feedback from hundreds of behavioral and technology researchers, focus group participants, and end users has been integrated into ohmage through an iterative participatory design process. Ohmage has been used as an enabling platform in more than 20 independent projects in many disciplines. We summarize the PS requirements, challenges and key design objectives learned through our design process, and ohmage system architecture to achieve those objectives. The flexibility, modularity, and extensibility of ohmage in supporting diverse deployment settings are presented through three distinct case studies in education, health, and clinical research.

Yum-Me: A Personalized Nutrient-Based Meal Recommender System

Nutrient-based meal recommendations have the potential to help individuals prevent or manage conditions such as diabetes and obesity. However, learning people’s food preferences and making recommendations that simultaneously appeal to their palate and satisfy nutritional expectations are challenging. Existing approaches either only learn high-level preferences or require a prolonged learning period. We propose Yum-me, a personalized nutrient-based meal recommender system designed to meet individuals’ nutritional expectations, dietary restrictions, and fine-grained food preferences. Yum-me enables a simple and accurate food preference profiling procedure via a visual quiz-based user interface and projects the learned profile into the domain of nutritionally appropriate food options to find ones that will appeal to the user. We present the design and implementation of Yum-me and further describe and evaluate two innovative contributions. The first contriution is an open source state-of-the-art food image analysis model, named FoodDist. We demonstrate FoodDist’s superior performance through careful benchmarking and discuss its applicability across a wide array of dietary applications. The second contribution is a novel online learning framework that learns food preference from itemwise and pairwise image comparisons. We evaluate the framework in a field study of 227 anonymous users and demonstrate that it outperforms other baselines by a significant margin. We further conducted an end-to-end validation of the feasibility and effectiveness of Yum-me through a 60-person user study, in which Yum-me improves the recommendation acceptance rate by 42.63%.

Leveraging Multi-Modal Sensing for Mobile Health: A Case Review in Chronic Pain

Active and passive mobile sensing has garnered much attention in recent years. In this paper, we focus on chronic pain measurement and management as a case application to exemplify the state of the art. We present a consolidated discussion on the leveraging of various sensing modalities along with modular server-side and on-device architectures required for this task. Modalities included are: activity monitoring from accelerometry and location sensing, audio analysis of speech, image processing for facial expressions as well as modern methods for effective patient self-reporting. We review examples that deliver actionable information to clinicians and patients while addressing privacy, usability, and computational constraints. We also discuss open challenges in the higher level inferencing of patient state and effective feedback with potential directions to address them. The methods and challenges presented here are also generalizable and relevant to a broad range of other applications in mobile sensing.

Performance evaluation of android IPC for continuous sensing applications

Sensor-rich smartphones are enabling a new class of applications and systems with significant potential to improve users’ daily lives. These applications, referred to as continuous sensing applications, continuously collect sensor data from on-board and external sensors and apply machine learning techniques to extract meaningful information about users’ behaviour and environment[1, 2, 6]. To collect the required sensor data, a continuous sensing application needs to communicate with different software entities on the phone including a) system services that interface with on-board sensors; b) drivers of off-board sensors, which are often proprietary applications developed by sensor manufacturers; and c) other sensing applications to obtain relevant user and context information. For enhanced security and privacy on modern smartphone platforms, each application runs within its own process. Therefore, Inter-Process Communication (IPC) mechanisms are crucial to continuous sensing applications. Current sensing sampling rates range from 32 bytes/sec for accelerometer and location data [5]; 63 bytes/sec for user and system context information, such as CPU, memory, and phone call, SMS records[3]; 88 KB/sec for acoustic data; and 232 KB/sec for image documentation [4]. Different sensing applications require IPC that can support a transfer of few bytes to hundreds of kilobytes, and frequencies of 0.1Hz to 1Hz. Ideal inter-process communication for continuous sensing applications must therefore meet the following performance requirements: 1) Low latency since the IPC transactions are on the critical path of the data collecting process; 2) Resource efficiency to minimize interference with device interactivity, performance, and availability; 3) Variable Bandwidth to accommodate a wide range of application demands from a few bytes to several hundreds of kilobytes per second as described earlier. We study the performance of three Android IPC mechanisms: 1) Binder, a remote-procedure-call (RPC) mechanism that enables a process to remotely invoke functions running on another process; Binder adopts a direct-message-copy scheme to transfer the IPC payload with only single data copy. 2) Intent, a flexible message passing system, implemented using two Binder RPC calls, allowing applications to send messages to each other; and 3) Content Provider, a data storehouse mechanism that implements various SQL-like IPC interfaces, in which the query operation uniquely incorporates a shared memory region to facilitate the transmission of possibly large query results.

OpenRec: A Modular Framework for Extensible and Adaptable Recommendation Algorithms

With the increasing demand for deeper understanding of users» preferences, recommender systems have gone beyond simple user-item filtering and are increasingly sophisticated, comprised of multiple components for analyzing and fusing diverse information. Unfortunately, existing frameworks do not adequately support extensibility and adaptability and consequently pose significant challenges to rapid, iterative, and systematic, experimentation. In this work, we propose OpenRec, an open and modular Python framework that supports extensible and adaptable research in recommender systems. Each recommender is modeled as a computational graph that consists of a structured ensemble of reusable modules connected through a set of well-defined interfaces. We present the architecture of OpenRec and demonstrate that OpenRec provides adaptability, modularity and reusability while maintaining training efficiency and recommendation accuracy. Our case study illustrates how OpenRec can support an efficient design process to prototype and benchmark alternative approaches with inter-changeable modules and enable development and evaluation of new algorithms.