Barnan Das

Simple and Complex Activity Recognition through Smart Phones

Due to an increased popularity of assistive healthcare technologies activity recognition has become one of the most widely studied problems in technology-driven assistive healthcare domain. Current approaches for smart-phone based activity recognition focus only on simple activities such as locomotion. In this paper, in addition to recognizing simple activities, we investigate the ability to recognize complex activities, such as cooking, cleaning, etc. through a smart phone. Features extracted from the raw inertial sensor data of the smart phone corresponding to the users activities, are used to train and test supervised machine learning algorithms. The results from the experiments conducted on ten participants indicate that, in isolation, while simple activities can be easily recognized, the performance of the prediction models on complex activities is poor. However, the prediction model is robust enough to recognize simple activities even in the presence of complex activities.

Conditional random fields for activity recognition in smart environments

One of the most common functions of smart environments is to monitor and assist older adults with their activities of daily living. Activity recognition is a key component in this application. It is essentially a temporal classification problem which has been modeled in the past by naïve Bayes classifiers and hidden Markov models (HMMs). In this paper, we describe the use of another probabilistic model: Conditional Random Fields (CRFs), which is currently gaining popularity for its remarkable performance for activity recognition. Our focus is on using CRFs to recognize activities performed by an inhabitant in a smart home environment and our goal is to validate the claim of its higher or similar performance by comparing CRFs with HMMs using data collected in a real smart home.

Application of Cognitive Rehabilitation Theory to the Development of Smart Prompting Technologies

Older adults with cognitive impairments often have difficulty performing instrumental activities of daily living (IADLs). Prompting technologies have gained popularity over the last decade and have the potential to assist these individuals with IADLs in order to live independently. Although prompting techniques are routinely used by caregivers and health care providers to aid individuals with cognitive impairment in maintaining their independence with everyday activities, there is no clear consensus or gold standard regarding prompt content, method of instruction, timing of delivery, or interface of prompt delivery in the gerontology or technology literatures. In this paper, we demonstrate how cognitive rehabilitation principles can inform and advance the development of more effective assistive prompting technologies that could be employed in smart environments. We first describe cognitive rehabilitation theory (CRT) and show how it provides a useful theoretical foundation for guiding the development of assistive technologies for IADL completion. We then use the CRT framework to critically review existing smart prompting technologies to answer questions that will be integral to advancing development of effective smart prompting technologies. Finally, we raise questions for future exploration as well as challenges and suggestions for future directions in this area of research.

RACOG and wRACOG: Two Probabilistic Oversampling Techniques

As machine learning techniques mature and are used to tackle complex scientific problems, challenges arise such as the imbalanced class distribution problem, where one of the target class labels is under-represented in comparison with other classes. Existing oversampling approaches for addressing this problem typically do not consider the probability distribution of the minority class while synthetically generating new samples. As a result, the minority class is not represented well which leads to high misclassification error. We introduce two probabilistic oversampling approaches, namely RACOG and wRACOG, to synthetically generating and strategically selecting new minority class samples. The proposed approaches use the joint probability distribution of data attributes and Gibbs sampling to generate new minority class samples. While RACOG selects samples produced by the Gibbs sampler based on a predefined lag, wRACOG selects those samples that have the highest probability of being misclassified by the existing learning model. We validate our approach using nine UCI data sets that were carefully modified to exhibit class imbalance and one new application domain data set with inherent extreme class imbalance. In addition, we compare the classification performance of the proposed methods with three other existing resampling techniques.

PUCK: an automated prompting system for smart environments: toward achieving automated prompting--challenges involved

The growth in popularity of smart environments has been quite steep in the last decade and so has the demand for smart health assistance systems. A smart home-based prompting system can enhance these technologies to deliver in-home interventions to users for timely reminders or brief instructions describing the way a task should be carried out for successful completion. This technology is in high demand given the desire of people who have physical or cognitive limitations to live independently in their homes. In this paper, with the introduction of the “PUCK” prompting system, we take an approach to automate prompting-based interventions without any predefined rule sets or user feedback. Unlike other approaches, we use simple off-the-shelf sensors and learn the timing for prompts based on real data that are collected with volunteer participants in our smart home test bed. The data mining approaches taken to solve this problem come with the challenge of an imbalanced class distribution that occurs naturally in the data. We propose a variant of an existing sampling technique, SMOTE, to deal with the class imbalance problem. To validate the approach, a comparative analysis with cost-sensitive learning is performed.

Using smart phones for context-aware prompting in smart environments

Individuals with cognitive impairment have difficulty successfully performing activities of daily living, which can lead to decreased independence. In order to help these individuals age in place and decrease caregiver burden, technologies for assistive living have gained popularity over the last decade. In this work, a context-aware prompting system is implemented, augmented by a smart phone to determine prompt situations in a smart home environment. While context-aware systems use temporal and environmental information to determine context, we additionally use ambulatory information from accelerometer data of a phone which also acts as a mobile prompting device. A pilot study with healthy young adults is conducted to examine the feasibility of using a smart phone interface for prompt delivery during activity completion in a smart home environment.

An automated prompting system for smart environments

The growth in popularity of smart environments has been quite steep in the last decade and so has the demand for smart health assistance systems. A smart home-based prompting system can enhance these technologies to deliver in-home interventions to a user for timely reminders or a brief instruction describing the way a task should be done for successful completion. This technology is in high demand with the desire for people who have physical or cognitive limitations to live independently in their homes. In this paper, we take the approach to fully automating a prompting system without any predefined rule set or user feedback. Unlike other approaches, we use simple off-the-shelf sensors and learn the timing for prompts based on real data that is collected with volunteer participants in our smart home testbed.

Handling Imbalanced and Overlapping Classes in Smart Environments Prompting Dataset

The area of supervised machine learning often encounters imbalanced class distribution problem where one class is under represented as compared to other classes. Additionally, in many real-life problem domains, data with an imbalanced class distribution contains ambiguous regions in the data space where the prior probability of two or more classes are approximately equal. This problem, known as overlapping classes, thus makes it difficult for the learners in classification task. In this chapter, intersection between the problems of imbalanced class and overlapping classes is explored from the perspective of Smart Environments as the application domain. In smart environments, the task of delivering in-home interventions to residents for timely reminders or brief instructions to ensure successful completion of daily activities, is an ideal scenario for the problem. As a solution to the aforementioned problem, a novel clustering-based under-sampling (ClusBUS) technique is proposed. Density-based clustering technique, DBSCAN, is used to identify “interesting” clusters in the instance space on which under-sampling is performed on the basis of a threshold value for degree of minority class dominance in the clusters.

Context-aware prompting from your smart phone

Individuals with cognitive impairment have difficulty successfully performing activities of daily living, which can lead to decreased independence. In order to help these individuals age in place and decrease caregiver burden, technologies for assistive living have gained popularity over the last decade. This demo illustrates the implementation of a context-aware prompting system augmented by a smart phone to determine prompt situations in a smart home environment. While context-aware systems use temporal and environmental information to determine context, we additionally use ambulatory information from accelerometer data of a phone which also acts as a mobile prompting device.

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

The class imbalance problem is a well-known classification challenge in machine learning that has vexed researchers for over a decade. Under-representation of one or more of the target classes (minority class(es)) as compared to others (majority class(es)) can restrict the application of conventional classifiers directly on the data. In addition, emerging challenges such as overlapping classes, make class imbalance even harder to solve. Class overlap is caused due to ambiguous regions in the data where the prior probability of two or more classes are approximately equal. We are motivated to address the challenge of class overlap in the presence of imbalanced classes by a problem in pervasive computing. Specifically, we are designing smart environments that perform health monitoring and assistance. Our solution, ClusBUS, is a clustering-based under sampling technique that identifies data regions where minority class samples are embedded deep inside majority class. By removing majority class samples from these regions, ClusBUS preprocesses the data in order to give more importance to the minority class during classification. Experiments show that ClusBUS achieves improved performance over an existing method for handling class imbalance.