SlideShare a Scribd company logo
1 of 24
Handling Class Overlap and Imbalance
to Detect Prompt Situations in
Smart Homes
Barnan Das, Narayanan C. Krishnan, Diane J. Cook

Barnan Das
School of Electrical Engineering and Computer Science
Washington State University
***Self-portraits by William Utermohlen, an American artist living in London, after he was diagnosed with Alzheimer’s disease in 1995. Utermohlen died from the
consequences of Alzheimer’s disease in March 2007.
36
million

Worldwide Dementia
population

13.2m

Actual and expected
number of Americans >=65
year with Alzheimer’s

7.7m
5.1m

2010

2030

2050

$200

Payment for care in 2012

billion

15

Unpaid caregivers

million
2
Source: World Health Organization and Alzheimer’s Association.
3
Automated
Prompting
Help with Activities of Daily Living (ADLs)

4
Existing Work
• Rule-based (temporal or contextual)
• Activity initiation
• RFID and video-input based prompts for
activity steps

Our Contribution
• Learning-based
• Sub-activity level prompts
• No audio/video input

5
Architectural Overview

6
Data
Raw Data

8

daily
activities

300

Sweeping
Cooking
Medication
Watering Plants
Etc.

elderly
participants

Prompts issued
when errors were
committed

Clean Data

1

activity
step

17

1

data
point

engineered features

0/1

Binary class
{no-prompt, prompt}

Length of activity step
Location in apartment
# sensors involves
# distribution of sensor events
Etc.

7
Class Distribution

149

Total number
of data points

3980
3831

8
Overlapping Classes
9
Overlapping Classes in Prompting Data

3D PCA Plot of prompting data
10
Existing Approaches
• Discard data of the overlapping region

• Treat overlapping region as a separate class
• Polynomial combination of existing features

• Using kernel methods

11
Tomek Links

12
Cluster-Based Under-Sampling(ClusBUS)

Form clusters

Under-sampling
candidate clusters
13
Two Critical Components
Choice of

Determining

Clustering Algorithm

Candidate Clusters

DBSCAN

Empirically Determined

•
•
•

•

Density-based
Non-spherical clusters
No need to predetermine
number of clusters

•

Based on minority class
dominance (r) in clusters
Threshold determined by qquantile values of r

14
Empirically Determined Threshold

15
Experimental Setup

Alternative Sampling Method SMOTE

Classifiers

•
•
•
•

Performance Metric

TP Rate, G-mean, AUC

C4.5 Decision Tree
Naïve Bayes
k-Nearest Neighbor
SVM

16
Results (1)
Original

SMOTE

ClusBUS

Original

0.8

0.7

0.7

G-mean

0.9

0.8

ClusBUS

1

0.9

TP Rate

1

SMOTE

0.6
0.5
0.4

0.6
0.5
0.4

0.3

0.3

0.2

0.2

0.1

0.1

0

0

C4.5

Naïve Bayes

IBk

TP Rate

SMO

C4.5

Naïve Bayes

IBk

SMO

G-mean
17
Results (2)
Original

SMOTE

ClusBUS

1
0.9
0.8
0.7
0.6
0.5

AUC

0.4
0.3
0.2
0.1
0

C4.5

Naïve
Bayes

IBk

SMO

Area Under ROC Curve

18
Conclusion

• Automated prompting as a classification problem
• Proposed ClusBUS: under-sampling-based preprocessing
• Solution to class overlap helps address imbalance classes

19
Contact Us

Barnan Das
barnandas@wsu.edu
Dr. Diane Cook
cook@eecs.wsu.edu

http://casas.wsu.edu
20
21
Backup Slides

22
Activities
Sweeping
Cooking
Taking Medication
Watering Plants
Watching DVD

Selecting Outfit
Taking Phone Call
Writing Birthday Card
23
Feature Generation
Feature # Feature Name

Description

1

stepLength

Length of the step in time (seconds)

2

numSensors

Number of unique sensors involved with the step

3

numEvents

Number of sensor events associated with the step

4

prevStep

Previous step

5

nextStep

Next step

6

timeActBegin

Time (seconds) elapsed since the beginning of the activity

7

timePrevStep

Time (seconds) difference between the last event of the
previous step and the first event of the current step

8

stepsActBegin Number of steps visited since the start of the activity

9

activityID

10

stepID

11

location

12

Class

Activity ID
Step ID
Set of features representing sensor frequencies in kitchen,
dining room, living room, etc. when the activity was
performed

Binary class. 1-”Prompt”, 0-”No-Prompt”

24

More Related Content

What's hot

What's hot (20)

xtremes
xtremesxtremes
xtremes
 
research publication
research publicationresearch publication
research publication
 
IRJET- Leaf Disease Detecting using CNN Technique
IRJET- Leaf Disease Detecting using CNN TechniqueIRJET- Leaf Disease Detecting using CNN Technique
IRJET- Leaf Disease Detecting using CNN Technique
 
An Exploration on the Identification of Plant Leaf Diseases using Image Proce...
An Exploration on the Identification of Plant Leaf Diseases using Image Proce...An Exploration on the Identification of Plant Leaf Diseases using Image Proce...
An Exploration on the Identification of Plant Leaf Diseases using Image Proce...
 
Plant Leaf Disease Analysis using Image Processing Technique with Modified SV...
Plant Leaf Disease Analysis using Image Processing Technique with Modified SV...Plant Leaf Disease Analysis using Image Processing Technique with Modified SV...
Plant Leaf Disease Analysis using Image Processing Technique with Modified SV...
 
Kapil dikshit ppt
Kapil dikshit pptKapil dikshit ppt
Kapil dikshit ppt
 
IRJET - A Review on Identification and Disease Detection in Plants using Mach...
IRJET - A Review on Identification and Disease Detection in Plants using Mach...IRJET - A Review on Identification and Disease Detection in Plants using Mach...
IRJET - A Review on Identification and Disease Detection in Plants using Mach...
 
LEAF DISEASE DETECTION USING IMAGE PROCESSING AND SUPPORT VECTOR MACHINE (SVM)
LEAF DISEASE DETECTION USING IMAGE PROCESSING AND SUPPORT VECTOR MACHINE (SVM)LEAF DISEASE DETECTION USING IMAGE PROCESSING AND SUPPORT VECTOR MACHINE (SVM)
LEAF DISEASE DETECTION USING IMAGE PROCESSING AND SUPPORT VECTOR MACHINE (SVM)
 
IRJET - Disease Detection in Plant using Machine Learning
IRJET -  	  Disease Detection in Plant using Machine LearningIRJET -  	  Disease Detection in Plant using Machine Learning
IRJET - Disease Detection in Plant using Machine Learning
 
Smart Fruit Classification using Neural Networks
Smart Fruit Classification using Neural NetworksSmart Fruit Classification using Neural Networks
Smart Fruit Classification using Neural Networks
 
IRJET- Detection and Classification of Leaf Diseases
IRJET-  	  Detection and Classification of Leaf DiseasesIRJET-  	  Detection and Classification of Leaf Diseases
IRJET- Detection and Classification of Leaf Diseases
 
Wheat leaf disease detection using image processing
Wheat leaf disease detection using image processingWheat leaf disease detection using image processing
Wheat leaf disease detection using image processing
 
Identification of Disease in Leaves using Genetic Algorithm
Identification of Disease in Leaves using Genetic AlgorithmIdentification of Disease in Leaves using Genetic Algorithm
Identification of Disease in Leaves using Genetic Algorithm
 
QI Tools Vietnam
QI Tools VietnamQI Tools Vietnam
QI Tools Vietnam
 
IRJET- Plant Leaf Disease Detection using Image Processing
IRJET- Plant Leaf Disease Detection using Image ProcessingIRJET- Plant Leaf Disease Detection using Image Processing
IRJET- Plant Leaf Disease Detection using Image Processing
 
The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)
 
Fruit Disease Detection and Classification
Fruit Disease Detection and ClassificationFruit Disease Detection and Classification
Fruit Disease Detection and Classification
 
Shot-Net: A Convolutional Neural Network for Classifying Different Cricket Shots
Shot-Net: A Convolutional Neural Network for Classifying Different Cricket ShotsShot-Net: A Convolutional Neural Network for Classifying Different Cricket Shots
Shot-Net: A Convolutional Neural Network for Classifying Different Cricket Shots
 
Imageprocessing
ImageprocessingImageprocessing
Imageprocessing
 
INTERNET OF THINGS IMPLEMENTATION FOR WIRELESS MONITORING OF AGRICULTURAL...
INTERNET OF THINGS IMPLEMENTATION FOR WIRELESS MONITORING     OF AGRICULTURAL...INTERNET OF THINGS IMPLEMENTATION FOR WIRELESS MONITORING     OF AGRICULTURAL...
INTERNET OF THINGS IMPLEMENTATION FOR WIRELESS MONITORING OF AGRICULTURAL...
 

Similar to Handling Class Overlap and Imbalance to Detect Prompt Situations in Smart Homes

Barnan Das PhD Preliminary Exam
Barnan Das PhD Preliminary ExamBarnan Das PhD Preliminary Exam
Barnan Das PhD Preliminary Exam
Barnan Das
 
Cluster analysis using Rapidminer and Sas
Cluster analysis using Rapidminer and SasCluster analysis using Rapidminer and Sas
Cluster analysis using Rapidminer and Sas
Madhumita Ghosh
 
Association mapping, GWAS, Mapping, natural population mapping
Association mapping, GWAS, Mapping, natural population mappingAssociation mapping, GWAS, Mapping, natural population mapping
Association mapping, GWAS, Mapping, natural population mapping
Mahesh Biradar
 
From ensembles to computer networks
From ensembles to computer networksFrom ensembles to computer networks
From ensembles to computer networks
CSIRO
 
4.1 network analysis basic
4.1 network analysis basic4.1 network analysis basic
4.1 network analysis basic
jilung hsieh
 
CMU Trecvid sed11
CMU Trecvid sed11CMU Trecvid sed11
CMU Trecvid sed11
Lu Jiang
 

Similar to Handling Class Overlap and Imbalance to Detect Prompt Situations in Smart Homes (18)

Barnan Das PhD Preliminary Exam
Barnan Das PhD Preliminary ExamBarnan Das PhD Preliminary Exam
Barnan Das PhD Preliminary Exam
 
Cluster analysis using Rapidminer and Sas
Cluster analysis using Rapidminer and SasCluster analysis using Rapidminer and Sas
Cluster analysis using Rapidminer and Sas
 
Anomaly detection (Unsupervised Learning) in Machine Learning
Anomaly detection (Unsupervised Learning) in Machine LearningAnomaly detection (Unsupervised Learning) in Machine Learning
Anomaly detection (Unsupervised Learning) in Machine Learning
 
ADAPT: Analysis of Dynamic Adaptations in Parameter Trajectories
ADAPT: Analysis of Dynamic Adaptations in Parameter Trajectories ADAPT: Analysis of Dynamic Adaptations in Parameter Trajectories
ADAPT: Analysis of Dynamic Adaptations in Parameter Trajectories
 
Association mapping, GWAS, Mapping, natural population mapping
Association mapping, GWAS, Mapping, natural population mappingAssociation mapping, GWAS, Mapping, natural population mapping
Association mapping, GWAS, Mapping, natural population mapping
 
MLSEV Virtual. Searching for Anomalies
MLSEV Virtual. Searching for AnomaliesMLSEV Virtual. Searching for Anomalies
MLSEV Virtual. Searching for Anomalies
 
From ensembles to computer networks
From ensembles to computer networksFrom ensembles to computer networks
From ensembles to computer networks
 
Resume
ResumeResume
Resume
 
Optimizing SPARQL Query Processing On Dynamic and Static Data Based on Query ...
Optimizing SPARQL Query Processing On Dynamic and Static Data Based on Query ...Optimizing SPARQL Query Processing On Dynamic and Static Data Based on Query ...
Optimizing SPARQL Query Processing On Dynamic and Static Data Based on Query ...
 
Golden Rules of Bioinformatics
Golden Rules of BioinformaticsGolden Rules of Bioinformatics
Golden Rules of Bioinformatics
 
Detecting STR Peaks in Degraded DNA samples
Detecting STR Peaks in Degraded DNA samplesDetecting STR Peaks in Degraded DNA samples
Detecting STR Peaks in Degraded DNA samples
 
DutchMLSchool 2022 - History and Developments in ML
DutchMLSchool 2022 - History and Developments in MLDutchMLSchool 2022 - History and Developments in ML
DutchMLSchool 2022 - History and Developments in ML
 
FallThesisFinal
FallThesisFinalFallThesisFinal
FallThesisFinal
 
ODVSML_Presentation
ODVSML_PresentationODVSML_Presentation
ODVSML_Presentation
 
Machine learning algorithm for classification of activity of daily life’s
Machine learning algorithm for classification of activity of daily life’sMachine learning algorithm for classification of activity of daily life’s
Machine learning algorithm for classification of activity of daily life’s
 
4.1 network analysis basic
4.1 network analysis basic4.1 network analysis basic
4.1 network analysis basic
 
CMU Trecvid sed11
CMU Trecvid sed11CMU Trecvid sed11
CMU Trecvid sed11
 
ESEM_2023.pdf
ESEM_2023.pdfESEM_2023.pdf
ESEM_2023.pdf
 

Recently uploaded

👉 Chennai Sexy Aunty’s WhatsApp Number 👉📞 7427069034 👉📞 Just📲 Call Ruhi Colle...
👉 Chennai Sexy Aunty’s WhatsApp Number 👉📞 7427069034 👉📞 Just📲 Call Ruhi Colle...👉 Chennai Sexy Aunty’s WhatsApp Number 👉📞 7427069034 👉📞 Just📲 Call Ruhi Colle...
👉 Chennai Sexy Aunty’s WhatsApp Number 👉📞 7427069034 👉📞 Just📲 Call Ruhi Colle...
rajnisinghkjn
 
Cara Menggugurkan Kandungan Dengan Cepat Selesai Dalam 24 Jam Secara Alami Bu...
Cara Menggugurkan Kandungan Dengan Cepat Selesai Dalam 24 Jam Secara Alami Bu...Cara Menggugurkan Kandungan Dengan Cepat Selesai Dalam 24 Jam Secara Alami Bu...
Cara Menggugurkan Kandungan Dengan Cepat Selesai Dalam 24 Jam Secara Alami Bu...
Cara Menggugurkan Kandungan 087776558899
 
Difference Between Skeletal Smooth and Cardiac Muscles
Difference Between Skeletal Smooth and Cardiac MusclesDifference Between Skeletal Smooth and Cardiac Muscles
Difference Between Skeletal Smooth and Cardiac Muscles
MedicoseAcademics
 
Call Girl in Chennai | Whatsapp No 📞 7427069034 📞 VIP Escorts Service Availab...
Call Girl in Chennai | Whatsapp No 📞 7427069034 📞 VIP Escorts Service Availab...Call Girl in Chennai | Whatsapp No 📞 7427069034 📞 VIP Escorts Service Availab...
Call Girl in Chennai | Whatsapp No 📞 7427069034 📞 VIP Escorts Service Availab...
amritaverma53
 
Russian Call Girls In Pune 👉 Just CALL ME: 9352988975 ✅❤️💯low cost unlimited ...
Russian Call Girls In Pune 👉 Just CALL ME: 9352988975 ✅❤️💯low cost unlimited ...Russian Call Girls In Pune 👉 Just CALL ME: 9352988975 ✅❤️💯low cost unlimited ...
Russian Call Girls In Pune 👉 Just CALL ME: 9352988975 ✅❤️💯low cost unlimited ...
chanderprakash5506
 

Recently uploaded (20)

7 steps How to prevent Thalassemia : Dr Sharda Jain & Vandana Gupta
7 steps How to prevent Thalassemia : Dr Sharda Jain & Vandana Gupta7 steps How to prevent Thalassemia : Dr Sharda Jain & Vandana Gupta
7 steps How to prevent Thalassemia : Dr Sharda Jain & Vandana Gupta
 
💞 Safe And Secure Call Girls Coimbatore🧿 6378878445 🧿 High Class Coimbatore C...
💞 Safe And Secure Call Girls Coimbatore🧿 6378878445 🧿 High Class Coimbatore C...💞 Safe And Secure Call Girls Coimbatore🧿 6378878445 🧿 High Class Coimbatore C...
💞 Safe And Secure Call Girls Coimbatore🧿 6378878445 🧿 High Class Coimbatore C...
 
👉 Chennai Sexy Aunty’s WhatsApp Number 👉📞 7427069034 👉📞 Just📲 Call Ruhi Colle...
👉 Chennai Sexy Aunty’s WhatsApp Number 👉📞 7427069034 👉📞 Just📲 Call Ruhi Colle...👉 Chennai Sexy Aunty’s WhatsApp Number 👉📞 7427069034 👉📞 Just📲 Call Ruhi Colle...
👉 Chennai Sexy Aunty’s WhatsApp Number 👉📞 7427069034 👉📞 Just📲 Call Ruhi Colle...
 
ANATOMY AND PHYSIOLOGY OF RESPIRATORY SYSTEM.pptx
ANATOMY AND PHYSIOLOGY OF RESPIRATORY SYSTEM.pptxANATOMY AND PHYSIOLOGY OF RESPIRATORY SYSTEM.pptx
ANATOMY AND PHYSIOLOGY OF RESPIRATORY SYSTEM.pptx
 
Cara Menggugurkan Kandungan Dengan Cepat Selesai Dalam 24 Jam Secara Alami Bu...
Cara Menggugurkan Kandungan Dengan Cepat Selesai Dalam 24 Jam Secara Alami Bu...Cara Menggugurkan Kandungan Dengan Cepat Selesai Dalam 24 Jam Secara Alami Bu...
Cara Menggugurkan Kandungan Dengan Cepat Selesai Dalam 24 Jam Secara Alami Bu...
 
💰Call Girl In Bangalore☎️63788-78445💰 Call Girl service in Bangalore☎️Bangalo...
💰Call Girl In Bangalore☎️63788-78445💰 Call Girl service in Bangalore☎️Bangalo...💰Call Girl In Bangalore☎️63788-78445💰 Call Girl service in Bangalore☎️Bangalo...
💰Call Girl In Bangalore☎️63788-78445💰 Call Girl service in Bangalore☎️Bangalo...
 
Difference Between Skeletal Smooth and Cardiac Muscles
Difference Between Skeletal Smooth and Cardiac MusclesDifference Between Skeletal Smooth and Cardiac Muscles
Difference Between Skeletal Smooth and Cardiac Muscles
 
Call Girl in Chennai | Whatsapp No 📞 7427069034 📞 VIP Escorts Service Availab...
Call Girl in Chennai | Whatsapp No 📞 7427069034 📞 VIP Escorts Service Availab...Call Girl in Chennai | Whatsapp No 📞 7427069034 📞 VIP Escorts Service Availab...
Call Girl in Chennai | Whatsapp No 📞 7427069034 📞 VIP Escorts Service Availab...
 
Race Course Road } Book Call Girls in Bangalore | Whatsapp No 6378878445 VIP ...
Race Course Road } Book Call Girls in Bangalore | Whatsapp No 6378878445 VIP ...Race Course Road } Book Call Girls in Bangalore | Whatsapp No 6378878445 VIP ...
Race Course Road } Book Call Girls in Bangalore | Whatsapp No 6378878445 VIP ...
 
Russian Call Girls In Pune 👉 Just CALL ME: 9352988975 ✅❤️💯low cost unlimited ...
Russian Call Girls In Pune 👉 Just CALL ME: 9352988975 ✅❤️💯low cost unlimited ...Russian Call Girls In Pune 👉 Just CALL ME: 9352988975 ✅❤️💯low cost unlimited ...
Russian Call Girls In Pune 👉 Just CALL ME: 9352988975 ✅❤️💯low cost unlimited ...
 
ANATOMY AND PHYSIOLOGY OF REPRODUCTIVE SYSTEM.pptx
ANATOMY AND PHYSIOLOGY OF REPRODUCTIVE SYSTEM.pptxANATOMY AND PHYSIOLOGY OF REPRODUCTIVE SYSTEM.pptx
ANATOMY AND PHYSIOLOGY OF REPRODUCTIVE SYSTEM.pptx
 
Circulatory Shock, types and stages, compensatory mechanisms
Circulatory Shock, types and stages, compensatory mechanismsCirculatory Shock, types and stages, compensatory mechanisms
Circulatory Shock, types and stages, compensatory mechanisms
 
Call girls Service Phullen / 9332606886 Genuine Call girls with real Photos a...
Call girls Service Phullen / 9332606886 Genuine Call girls with real Photos a...Call girls Service Phullen / 9332606886 Genuine Call girls with real Photos a...
Call girls Service Phullen / 9332606886 Genuine Call girls with real Photos a...
 
Call Girls Kathua Just Call 8250077686 Top Class Call Girl Service Available
Call Girls Kathua Just Call 8250077686 Top Class Call Girl Service AvailableCall Girls Kathua Just Call 8250077686 Top Class Call Girl Service Available
Call Girls Kathua Just Call 8250077686 Top Class Call Girl Service Available
 
Call Girls Rishikesh Just Call 9667172968 Top Class Call Girl Service Available
Call Girls Rishikesh Just Call 9667172968 Top Class Call Girl Service AvailableCall Girls Rishikesh Just Call 9667172968 Top Class Call Girl Service Available
Call Girls Rishikesh Just Call 9667172968 Top Class Call Girl Service Available
 
Call Girls Wayanad Just Call 8250077686 Top Class Call Girl Service Available
Call Girls Wayanad Just Call 8250077686 Top Class Call Girl Service AvailableCall Girls Wayanad Just Call 8250077686 Top Class Call Girl Service Available
Call Girls Wayanad Just Call 8250077686 Top Class Call Girl Service Available
 
Call 8250092165 Patna Call Girls ₹4.5k Cash Payment With Room Delivery
Call 8250092165 Patna Call Girls ₹4.5k Cash Payment With Room DeliveryCall 8250092165 Patna Call Girls ₹4.5k Cash Payment With Room Delivery
Call 8250092165 Patna Call Girls ₹4.5k Cash Payment With Room Delivery
 
Cardiac Output, Venous Return, and Their Regulation
Cardiac Output, Venous Return, and Their RegulationCardiac Output, Venous Return, and Their Regulation
Cardiac Output, Venous Return, and Their Regulation
 
Call Girls Mussoorie Just Call 8854095900 Top Class Call Girl Service Available
Call Girls Mussoorie Just Call 8854095900 Top Class Call Girl Service AvailableCall Girls Mussoorie Just Call 8854095900 Top Class Call Girl Service Available
Call Girls Mussoorie Just Call 8854095900 Top Class Call Girl Service Available
 
Call Girls in Lucknow Just Call 👉👉8630512678 Top Class Call Girl Service Avai...
Call Girls in Lucknow Just Call 👉👉8630512678 Top Class Call Girl Service Avai...Call Girls in Lucknow Just Call 👉👉8630512678 Top Class Call Girl Service Avai...
Call Girls in Lucknow Just Call 👉👉8630512678 Top Class Call Girl Service Avai...
 

Handling Class Overlap and Imbalance to Detect Prompt Situations in Smart Homes

Editor's Notes

  1. The background image that you see is a collection of self-portraits by William Utermohlen, an American artist/painter living in London. When diagnosed with Alzheimer’s in 1995 he decided to document his experiences in the form of self portraits as his life progresses with the disease. Utermohlen later dies from the consequences of Alzheimer’s in 2007.
  2. Fewnumbers and stats from World Health Organization and the Alzheimer’s Association that highlights the philosophical motivation of this work:There are currently 36 million people in the world who are suffering from Dementia. In US alone, there were over 5 million Alzheimer’s patients in the year 2010. By 2050, this number has been projected to be as high as 13.2 million. Caring for these Alzheimer’s patients has cost America $200 billion in 2012.Moreover, there are currently 15 million unpaid caregivers, who are usually family members, taking care of these patients. As 45% of the unpaid caregivers are 55 and older, caring for their dear ones causes high levels of emotional stress and depression.
  3. Therefore, there is a growing need for developing assistive living technologies to reduce the burden on the caregivers and help the elderly age in place. Help with Activities of Daily Living is one of the primary objectives and research directions in the area of Smart Environment research.
  4. In my research, I am trying to address Automated Prompting Challenge to help older adults with their daily activities. Specifically, I am addressing the machine learning challenges associated with tracking activity steps from in-home sensor data and predicting potential prompt situations when an elderly performs an activity.
  5. The existing work in the area of automated prompting mainly deals with rule-based prompts for activity initiation. However, there are other works which can handle prompt situations for activity steps by using either RFID tags or video-input.The contribution of the current work is mainly in proposing a machine learning-based prompting system by tracking activity steps and predicting potential prompt situation using the current infrastructure of the group which involves neither RFID tags nor video-input.
  6. A brief architectural overview before we dig deep into the algorithmic challenges:We collect daily human activity data from on-campus and off-campus smart homes which are equipped with a diverse sensor suite which includes motion, object, door, light and power sensors. We also exploit the sensors available on smart phones. The raw sensor data collected from the experiments conducted with human participants are passed along to the human annotators who label the data with daily activities and corresponding steps. These activity labels act as ground truth for evaluating our proposed learning models. Also, the ground-truth information is used to generate distinguishable features on activities and activity steps which are fed into machine learning models to predict prompt situation. And ultimately the predicted prompts could be issued to a smart home inhabitant through a prompting device.My contribution is in engineeringdistinguishable activity features and building machine learning models to predict potential prompt situations for ADLs.
  7. So lets see what the data represents and what is that we are trying to achieve. We are using the sensor data collected from 300 older-adult participants who performed 8 different activities of daily living in our on-campus smart home. An experimenter monitored the participants and issued prompts wherever necessary. For example, in the cooking activity prompts were issued when the participant forgot to heat the water in the microwave which was going to be used to cook a cup of noodles.The raw sensor data are labeled with activities, predefined activity steps and also if a prompt was issued with any specific activity step for a participant. Thus, after the primary preprocessing, a unique activity step for a participant corresponds to one data point. I have engineered 17 different attributes for these activity steps such as frequency of sensor triggering for specific locations, duration of activity step, time elapsed between activity initiation and current step, etc. The goal is thus to classify these steps into prompt and no prompt classes based on ground truth information collected from the experimenter and the annotator. So as you can tell, it is a binary classification problem.
  8. With the features that we generate on the raw data, it sometimes becomes impossible for a classifier to determine if a data point belongs to the prompt class or the no-prompt class. It turns out that, if overlapping classes problem occurs in the presence of imbalanced class distribution, getting rid of class overlap actually reduces the adverse effects of class imbalance to some extent. This problem also exists in other domains such as character recognition, credit card fraud detection, drug design, etc.
  9. The class overlap problem become clear from a 3D PCA plot of the prompting data.
  10. Solutions in the literature either talk about discarding the data points of the overlapping region or treating the overlapping region as a separate class. However, in the prompting domain neither of these approaches is going to work. First, the prompting data has absolute rarity of minority class instances and therefore throwing away data points will make the problem even worse. Secondly, treating the overlapping region as a separate class is not going to solve our purpose of accurate classification of prompt and no-prompt activity steps. Now, you might think if we use a parametric machine learning method and generate new features by some polynomial combination of existing features, it might solve this issue. However, it appears that it doesn’t. So, we take a preprocessing approach to solve overlapping classes
  11. Our solution is motivated from the concept of Tomek links which are defined as pairs of minimally distant minority and majority class data points. This means that Tomek links either represent noise or lie on the boundary of the two classes. And thus removing the majority class instances from the Tomek links can help in better learning the minority class.
  12. Our proposed approach is very similar. However, instead of identifying the overlapping region by finding Tomek links we use clustering. Cluster-Based Under-Sampling or ClusBUS, first identifies the overlapping region in the data by performing clustering. The clusters which have a good mix of both minority and majority class samples are considered for under-sampling. From these clusters, the majority class samples are removed. This creates a void around the minority class samples and thus helps in learning them better.