CS 682: AI: Case-Based Reasoning
Current Research
The 4 Diabetes Support System Project
The 4 Diabetes Support System (4DSS) project
is a collaborative effort with the Appalachian Rural
Health Institute Diabetes and Endocrine Center. To avoid serious
complications of diabetes, patients must maintain good blood glucose
control. This involves managing insulin intake, diet, and exercise,
as well as accounting for lifestyle changes, such as travel,
shift work, or pregnancy. Advanced technologies provide patients
and their physicians with ever increasing quantities of data,
but interpreting this data and translating it into better care
still requires time-consuming, manual effort. The goal of this
project is to provide automated intelligent decision support to
diabetes patients and their professional care providers.
You can watch a brief
Ohio Update video
or read an
Ohio University Medicine news article
about this project.
The paper
"Case-Based Decision Support for Patients with Type 1 Diabetes on
Insulin Pump Therapy",
from the European Conference on Case-Based Reasoning (ECCBR-08), is
available online.
Additional information is available on
The Appalachian Rural Health Institute and
Diabetes.
Machine Learning Models for Blood Glucose Prediction in Diabetes Management
This SmartHealth Lab project enhances and extends the work begun on the 4DSS project.
Machine learning models that predict blood glucose levels would enable or facilitate
new applications of direct benefit to patients, including: alerts to immediately notify
patients of impending problems; real-time recommendations enabling patients to prevent impending
problems; and educational simulations showing the effects of different treatment choices
or lifestyle options on blood glucose levels.
Additional information is available here.
Prior Research
The Auguste Project
The Auguste Project was a collaborative effort with the
University Memory and Aging Center of Case Western Reserve University.
Case-Based Reasoning (CBR) and Multimodal Reasoning (MMR) were
explored in the context of planning the ongoing care of
Alzheimer's Disease patients. This is a difficult task marked
by cases that change over time, the multiple perspectives of
professionals from different health care disciplines, and
ethical considerations. The goals of the Auguste Project
were to better understand the reasoning processes used
in this task and to provide practical decision support
tools for health care professionals.
The papers
"Case-Based Reasoning in the Care of Alzheimer's Disease Patients",
from the International Conference on Case-Based Reasoning (ICCBR-01), and
"Can a Computer Be a Caregiver?",
from the AAAI-02 Workshop on Automation as Caregiver,
are available online.
Additional information is available on
The Auguste Project
and
Alzheimer's Disease.
The RoboCats
RoboCup is an interdisciplinary effort to
build a team of humanoid robots
capable of beating human soccer teams in the World Cup by the year 2050.
Intense international competition between now and then is expected to lead
to numerous unforeseen scientific breakthroughs, commercial spinoffs and
societal benefits. Ohio University researchers from the School of
Electrical Engineering and Computer Science and the Department of
Mechanical Engineering collaborated to build the RoboCats.
AI approaches, including CBR and MMR, were used to give the
robots brains, allowing them to cooperate with teammates
while thwarting the game strategies of their opponents. The RoboCats
competed in
RoboCup 2002, in Japan, RoboCup 2003, in Italy, and RoboCup 2004, in
Portugal.
The paper
"Case-Based Reasoning for Planning and World Modeling in the
RoboCup Small-Size League", from the IJCAI-03 Workshop on Issues in
Designing Physical Agents for Dynamic Real-Time Environments: World Modeling,
Planning, Learning, and Communicating, is available online. The
paper
"RoboCup for the Mechanically, Athletically and Culturally Challenged,"
from the AAAI-08 Workshop on What Went Wrong and Why, provides another
perspective.
Additional information is available on
RoboCup .
CAMPER
The Case-Based Menu Planner Enhanced by Rules (CAMPER) combines
CBR with rule-based reasoning (RBR) to plan nutritional menus.
It was built as part of the dissertation, Integrating
Case-Based and Rule-Based Reasoning in Knowledge-Based Systems,
which was completed at Case Western Reserve University.
The paper
"Integrating Case-Based and Rule-Based Reasoning
to Meet Multiple Design Constraints",
by C.R. Marling, G.J. Petot and L.S. Sterling (1999),
Computational Intelligence, 15(3):308-332,
is available online.
