Narayanan Chatapuram Krishnan

Activity recognition on streaming sensor data

Many real-world applications that focus on addressing needs of a human, require information about the activities being performed by the human in real-time. While advances in pervasive computing have lead to the development of wireless and non-intrusive sensors that can capture the necessary activity information, current activity recognition approaches have so far experimented on either a scripted or pre-segmented sequence of sensor events related to activities. In this paper we propose and evaluate a sliding window based approach to perform activity recognition in an on line or streaming fashion; recognizing activities as and when new sensor events are recorded. To account for the fact that different activities can be best characterized by different window lengths of sensor events, we incorporate the time decay and mutual information based weighting of sensor events within a window. Additional contextual information in the form of the previous activity and the activity of the previous window is also appended to the feature describing a sensor window. The experiments conducted to evaluate these techniques on real-world smart home datasets suggests that combining mutual information based weighting of sensor events and adding past contextual information into the feature leads to best performance for streaming activity recognition.

CASAS: A Smart Home in a Box

The CASAS architecture facilitates the development and implementation of future smart home technologies by offering an easy-to-install lightweight design that provides smart home capabilities out of the box with no customization or training.

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.

Activity Discovery and Activity Recognition: A New Partnership

Activity recognition has received increasing attention from the machine learning community. Of particular interest is the ability to recognize activities in real time from streaming data, but this presents a number of challenges not faced by traditional offline approaches. Among these challenges is handling the large amount of data that does not belong to a predefined class. In this paper, we describe a method by which activity discovery can be used to identify behavioral patterns in observational data. Discovering patterns in the data that does not belong to a predefined class aids in understanding this data and segmenting it into learnable classes. We demonstrate that activity discovery not only sheds light on behavioral patterns, but it can also boost the performance of recognition algorithms. We introduce this partnership between activity discovery and online activity recognition in the context of the CASAS smart home project and validate our approach using CASAS data sets.

Transfer learning for activity recognition: a survey

Many intelligent systems that focus on the needs of a human require information about the activities being performed by the human. At the core of this capability is activity recognition, which is a challenging and well-researched problem. Activity recognition algorithms require substantial amounts of labeled training data yet need to perform well under very diverse circumstances. As a result, researchers have been designing methods to identify and utilize subtle connections between activity recognition datasets, or to perform transfer-based activity recognition. In this paper, we survey the literature to highlight recent advances in transfer learning for activity recognition. We characterize existing approaches to transfer-based activity recognition by sensor modality, by differences between source and target environments, by data availability, and by type of information that is transferred. Finally, we present some grand challenges for the community to consider as this field is further developed.

Analysis of low resolution accelerometer data for continuous human activity recognition

The advent of wearable sensors like accelerometers has opened a plethora of opportunities to recognize human activities from other low resolution sensory streams. In this paper we formulate recognizing activities from accelerometer data as a classification problem. In addition to the statistical and spectral features extracted from the acceleration data, we propose to extract features that characterize the variations in the first order derivative of the acceleration signal. We evaluate the performance of different state of the art discriminative classifiers like, boosted decision stumps (AdaBoost), support vector machines (SVM) and regularized logistic regression (RLogReg) under three different evaluation scenarios (namely subject independent, subject adaptive and subject dependent). We propose a novel computationally inexpensive methodology for incorporating smoothing classification temporally, that can be coupled with any classifier with minimal training for classifying continuous sequences. While a 3% increase in the classification accuracy was observed on adding the new features, the proposed technique for continuous recognition showed a 2.5 - 3% improvement in the performance.

Recognition of hand movements using wearable accelerometers

Accelerometer based activity recognition systems have typically focused on recognizing simple ambulatory activities of daily life, such as walking, sitting, standing, climbing stairs, etc. In this work, we developed and evaluated algorithms for detecting and recognizing short duration hand movements (lift to mouth, scoop, stir, pour, unscrew cap). These actions are a part of the larger and complex Instrumental Activities of Daily Life (IADL) making a drink and drinking. We collected data using small wireless tri-axial accelerometers worn simultaneously on different parts of the hand. Acceleration data for training was collected from 5 subjects, who also performed the two IADLs without being given specific instructions on how to complete them. Feature vectors (mean, variance, correlation, spectral entropy and spectral energy) were calculated and tested on three classifiers (AdaBoost, HMM, k-NN). AdaBoost showed the best performance, with an overall accuracy of 86% for detecting each of these hand actions. The results show that although some actions are recognized well with the generalized classifer trained on the subject-independent data, other actions require some amount of subject-specific training. We also observed an improvement in the performance of the system when multiple accelerometers placed on the right hand were used.

Measuring movement expertise in surgical tasks

Surgical movement is composed of discrete gestures that are combined to perform complex surgical procedures. A promising approach to objective surgical skill evaluation systems is kinematics and kinetic analysis of hand movement that yields a gesture level analysis of proficiency of a performed movement. In this paper, we propose a novel system that combines surgical gesture segmentation, surgical gesture recognition, and expertise analysis of surgical profiles in minimally invasive surgery (MIS). Kinematic analysis was used to segment gestures from a continuous motion stream. Human anatomy driven Hidden Markov Models (HMMs) are adopted for gesture recognition and expertise identification. When the proposed system was tested on a library of 200 samples for every basic surgical gesture, the gesture recognition module reported a perfect accuracy rate for the basic gestures, while the expertise identification module showed 94.7% accuracy.

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.

Mining the home environment

Individuals spend a majority of their time in their home or workplace and for many, these places are our sanctuaries. As society and technology advance there is a growing interest in improving the intelligence of the environments in which we live and work. By filling home environments with sensors and collecting data during daily routines, researchers can gain insights on human daily behavior and the impact of behavior on the residents and their environments. In this article we provide an overview of the data mining opportunities and challenges that smart environments provide for researchers and offer some suggestions for future work in this area.