Urinary tract infection (UTI) flare-ups pose a significant health risk for older adults with chronic conditions. These infections often go unnoticed until they become severe, making early detection through innovative smart home technologies crucial. Traditional machine learning (ML) approaches relying on simple binary classification for UTI detection offer limited utility to nurses and practitioners as they lack insight into prediction uncertainty, hindering informed clinical decision-making. This paper presents a clinician-in-the-loop (CIL) smart home system that leverages ambient sensor data to extract meaningful behavioral markers, train robust predictive ML models, and calibrate them to enable uncertainty-aware decision support. The system incorporates a statistically valid uncertainty quantification method called Conformal-Calibrated Interval (CCI), which quantifies uncertainty and abstains from making predictions ("I don’t know") when the ML model's confidence is low. Evaluated on real-world data from eight smart homes, our method outperforms baseline methods in recall and other classification metrics while maintaining the lowest abstention proportion and interval width. A survey of 42 nurses confirms that our system's outputs are valuable for guiding clinical decision-making, underscoring their practical utility in improving informed decisions and effectively managing UTIs and other condition flare-ups in older adults.

Machine Learning (ML) algorithms play an increasingly critical role in remote health monitoring, automating health assessments, and extending medical professionals’ reach in caring for an aging population. However, ML models often provide predictions without quantifying uncertainty, which is essential for safe deployment in healthcare. This article presents a novel method referred to as Uncertainty Regions via Importance-Weighted Calibration (URIC) for automating the uncertainty-based prediction of multiple clinical cognitive health measures from continuous smartwatch sensor data. URIC leverages Conformal Prediction (CP), a rigorous Uncertainty Quantification (UQ) framework that guarantees user-defined coverage (e.g., ground truth is in the predicted region with 95% probability). The key innovation of URIC is constructing smaller, more interpretable prediction regions by assigning importance weights to calibration examples. It forms prediction regions by using the most relevant calibration examples, ensuring tight regions without sacrificing coverage. We evaluate URIC for predicting the cognitive health measures of 157 adults who were either cognitively healthy or experienced Mild Cognitive Impairment (MCI). Compared to other UQ methods, our method constructs smaller prediction regions across all multi-target combinations while maintaining the user-specified coverage. This approach can be integrated into human-ML collaborative systems to improve diagnostic accuracy and interpretability in sensitive multi-target healthcare tasks.

Human activity recognition (HAR) from wearable sensor data traditionally identifies atomic movements (e.g., sit, stand, walk). However, many medical fields require recognizing functional activities-higher-level, goal-directed behaviors (e.g., errands, socialize, work). Functional activity recognition is critical for cognitive health assessment, rehabilitation, post-surgical recovery, and chronic disease management, yet remains largely unexplored due to its inherent complexity and variability for in-the-wild settings. This work addresses these challenges by investigating methods for functional HAR and introducing a novel approach that augments feature representations with feature token-transformer embeddings to improve classification performance. We compare a range of machine learning and deep learning methods, analyzing their ability to generalize across a diverse population. Additionally, we present ArWISE, a large-scale functional activity dataset collected longitudinally from n = 503 participants, consisting of over 32 million labeled points. Our experiments demonstrate the advantages of incorporating feature embeddings into functional HAR models, particularly in handling real-world variability and data sparsity. By bridging the gap between atomic movement recognition and functional behavior modeling, this work lays the foundation for more advanced, behavior-aware applications in digital health and human-centered AI.

Forecasting future health status is beneficial for understanding health patterns and providing anticipatory support for cognitive and physical health difficulties. In recent years, generative Large Language Models (LLMs) have shown promise as forecasters. Though not traditionally considered strong candidates for numeric tasks, LLMs demonstrate emerging abilities to address various forecasting problems. They also provide the ability to incorporate unstructured information and explain their reasoning process. In this article, we explore whether LLMs can effectively forecast future self-reported health state. To do this, we utilized in-the-moment assessments of mental sharpness, fatigue, and stress from multiple studies, utilizing daily responses ( N = 106 participants) and responses that are accompanied by text descriptions of activities ( N = 32 participants). With these data, we constructed prompt/response pairs to predict a participant’s next answer. We fine-tuned several LLMs and applied chain-of-thought prompting evaluating forecasting accuracy and prediction explainability. Notably, we found that LLMs achieved the lowest Mean Absolute Error (MAE) overall (0.851), while gradient boosting achieved the lowest overall RMSE (1.356). When additional text context was provided, LLM forecasts achieved the lowest MAE for predicting mental sharpness (0.862), fatigue (1.000), and stress (0.414). These multimodal LLMs further outperformed the numeric baselines in terms of RMSE when predicting stress (0.947), although numeric algorithms achieved the best RMSE results for mental sharpness (1.246) and fatigue (1.587). This study offers valuable insights for future applications of LLMs in health-based forecasting. The findings suggest that LLMs, when supplemented with additional text information, can be effective tools for improving health forecasting accuracy.

Generative adversarial networks have become a de facto approach to generate synthetic data points that resemble their real counterparts. We tackle the situation where the realism of individual samples is not the sole criterion for synthetic data generation. Additional constraints such as privacy preservation, distribution realism, and diversity promotion may also be essential to optimize. To address this challenge, we introduce HydraGAN, a multi-agent network that performs multi-objective synthetic data generation. We theoretically verify that training the HydraGAN system, containing a single generator and an arbitrary number of discriminators, leads to a Nash equilibrium. Experimental results for six datasets indicate that HydraGAN consistently outperforms prior methods in maximizing the Area under the Radar Curve (AuRC), balancing a combination of cooperative or competitive data generation goals.

Unsupervised domain adaptation (UDA) provides a strategy for improving machine learning performance in data-rich (target) domains where ground truth labels are inaccessible but can be found in related (source) domains. In cases where meta-domain information such as label distributions is available, weak supervision can further boost performance. We propose a novel framework, CALDA, to tackle these two problems. CALDA synergistically combines the principles of contrastive learning and adversarial learning to robustly support multi-source UDA (MS-UDA) for time series data. Similar to prior methods, CALDA utilizes adversarial learning to align source and target feature representations. Unlike prior approaches, CALDA additionally leverages cross-source label information across domains. CALDA pulls examples with the same label close to each other, while pushing apart examples with different labels, reshaping the space through contrastive learning. Unlike prior contrastive adaptation methods, CALDA requires neither data augmentation nor pseudo labeling, which may be more challenging for time series. We empirically validate our proposed approach. Based on results from human activity recognition, electromyography, and synthetic datasets, we find utilizing cross-source information improves performance over prior time series and contrastive methods. Weak supervision further improves performance, even in the presence of noise, allowing CALDA to offer generalizable strategies for MS-UDA.

In this study, we introduce and validate a computational method to detect lifestyle change that occurs in response to a multi-domain healthy brain aging intervention. To detect behavior change, digital behavior markers (DM) are extracted from smartwatch sensor data and a Permutation-based Change Detection (PCD) algorithm quantifies the change in marker-based behavior from a pre-intervention, one-week baseline. To validate the method, we verify that changes are successfully detected from synthetic data with known pattern differences. Next, we employ this method to detect overall behavior change for n=28 BHI subjects and n=17 age-matched control subjects. For these individuals, we observe a monotonic increase in behavior change from the baseline week with a slope of 0.7460 for the intervention group and a slope of 0.0230 for the control group. Finally, we utilize a random forest algorithm to perform leave-one-subject-out prediction of intervention versus control subjects based on digital marker delta values. The random forest predicts whether the subject is in the intervention or control group with an accuracy of 0.87. This work has implications for capturing objective, continuous data to inform our understanding of intervention adoption and impact.

New modes of technology are offering unprecedented opportunities to unobtrusively collect data about people's behavior. While there are many use cases for such information, we explore its utility for predicting multiple clinical assessment scores. Because clinical assessments are typically used as screening tools for impairment and disease, such as mild cognitive impairment (MCI), automatically mapping behavioral data to assessment scores can help detect changes in health and behavior across time. In this article, we aim to extract behavior markers from two modalities, a smart home environment and a custom digital memory notebook app, for mapping to 10 clinical assessments that are relevant for monitoring MCI onset and changes in cognitive health. Smart-home-based behavior markers reflect hourly, daily, and weekly activity patterns, while app-based behavior markers reflect app usage and writing content/style derived from free-form journal entries. We describe machine learning techniques for fusing these multimodal behavior markers and utilizing joint prediction. We evaluate our approach using three regression algorithms and data from 14 participants with MCI living in a smart-home environment. We observed moderate to large correlations between predicted and ground-truth assessment scores, ranging from r = 0.601 to r = 0.871 for each clinical assessment.

We propose a novel active learning framework for activity recognition using wearable sensors. Our work is unique in that it takes limitations of the oracle into account when selecting sensor data for annotation by the oracle. Our approach is inspired by human-beings’ limited capacity to respond to prompts on their mobile device. This capacity constraint is manifested not only in the number of queries that a person can respond to in a given time-frame but also in the time lag between the query issuance and the oracle response. We introduce the notion ofmindful active learningand propose a computational framework, calledEMMA, to maximize the active learning performance taking informativeness of sensor data, query budget, and human memory into account. We formulate this optimization problem, propose an approach to model memory retention, discuss the complexity of the problem, and propose a greedy heuristic to solve the optimization problem. Additionally, we design an approach to perform mindful active learning in batch where multiple sensor observations are selected simultaneously for querying the oracle. We demonstrate the effectiveness of our approach using three publicly available activity datasets and by simulating oracles with various memory strengths. We show that the activity recognition accuracy ranges from 21 to 97 percent depending on memory strength, query budget, and difficulty of the machine learning task. Our results also indicate that EMMA achieves an accuracy level that is, on average, 13.5 percent higher than the case when only informativeness of the sensor data is considered for active learning. Moreover, we show that the performance of our approach is at most 20 percent less than the experimental upper-bound and up to 80 percent higher than the experimental lower-bound. To evaluate the performance of EMMA for batch active learning, we design two instantiations of EMMA to perform active learning in batch mode. We show that these algorithms improve the algorithm training time at the cost of a reduced accuracy in performance. Another finding in our work is that integrating clustering into the process of selecting sensor observations for batch active learning improves the activity learning performance by 11.1 percent on average, mainly due to reducing the redundancy among the selected sensor observations. We observe that mindful active learning is most beneficial when the query budget is small and/or the oracle’s memory is weak. This observation emphasizes advantages of utilizing mindful active learning strategies in mobile health settings that involve interaction with older adults and other populations with cognitive impairments.

Smart homes equipped with anonymous binary sensors offer a low-cost, unobtrusive solution that powers activity-aware applications, such as building automation, health monitoring, behavioral intervention, and home security. However, when multiple residents are living in a smart home, associating sensor events with the corresponding residents can pose a major challenge. Previous approaches to multi-resident tracking in smart homes rely on extra information, such as sensor layouts, floor plans, and annotated data, which may not be available or inconvenient to obtain in practice. To address those challenges in real-life deployment, we introduce the sMRT algorithm that simultaneously tracks the location of each resident and estimates the number of residents in the smart home, without relying on ground-truth annotated sensor data or other additional information. We evaluate the performance of our approach using two smart home datasets recorded in real-life settings and compare sMRT with two other methods that rely on sensor layout and ground truth-labeled sensor data.

Anomaly detection techniques can extract a wealth of information about unusual events. Unfortunately, these methods yield an abundance of findings that are not of interest, obscuring relevant anomalies. In this work, we improve upon traditional anomaly detection methods by introducing Isudra, an Indirectly-Supervised Detector of Relevant Anomalies from time series data. Isudra employs Bayesian optimization to select time scales, features, base detector algorithms, and algorithm hyperparameters that increase true positive and decrease false positive detection. This optimization is driven by a small amount of example anomalies, driving an indirectly-supervised approach to anomaly detection. Additionally, we enhance the approach by introducing a warm start method that reduces optimization time between similar problems. We validate the feasibility of Isudra to detect clinically-relevant behavior anomalies from over 2 million sensor readings collected in 5 smart homes, reflecting 26 health events. Results indicate that indirectly-supervised anomaly detection outperforms both supervised and unsupervised algorithms at detecting instances of health-related anomalies such as falls, nocturia, depression, and weakness.

With the arrival of the internet of things, smart environments are becoming increasingly ubiquitous in our everyday lives. Sensor data collected from smart home environments can provide unobtrusive, longitudinal time series data that are representative of the smart home resident's routine behavior and how this behavior changes over time. When longitudinal behavioral data are available from multiple smart home residents, differences between groups of subjects can be investigated. Group-level discrepancies may help isolate behaviors that manifest in daily routines due to a health concern or major lifestyle change. To acquire such insights, we propose an algorithmic framework based on change point detection called Behavior Change Detection for Groups (BCD-G). We hypothesize that, using BCD-G, we can quantify and characterize differences in behavior between groups of individual smart home residents. We evaluate our BCD-G framework using one month of continuous sensor data for each of fourteen smart home residents, divided into two groups. All subjects in the first group are diagnosed with cognitive impairment. The second group consists of cognitively healthy, age-matched controls. Using BCD-G, we identify differences between these two groups, such as how impairment affects patterns of performing activities of daily living and how clinically-relevant behavioral features, such as in-home walking speed, differ for cognitively-impaired individuals. With the unobtrusive monitoring of smart home environments, clinicians can use BCD-G for remote identification of behavior changes that are early indicators of health concerns.

Domain adaptation (DA) offers a valuable means to reuse data and models for new problem domains. However, robust techniques have not yet been considered for time series data with varying amounts of data availability. In this paper, we make three main contributions to fill this gap. First, we propose a novel Convolutional deep Domain Adaptation model for Time Series data (CoDATS) that significantly improves accuracy and training time over state-of-the-art DA strategies on real-world sensor data benchmarks. By utilizing data from multiple source domains, we increase the usefulness of CoDATS to further improve accuracy over prior single-source methods, particularly on complex time series datasets that have high variability between domains. Second, we propose a novel Domain Adaptation with Weak Supervision (DA-WS) method by utilizing weak supervision in the form of target-domain label distributions, which may be easier to collect than additional data labels. Third, we perform comprehensive experiments on diverse real-world datasets to evaluate the effectiveness of our domain adaptation and weak supervision methods. Results show that CoDATS for single-source DA significantly improves over the state-of-the-art methods, and we achieve additional improvements in accuracy using data from multiple source domains and weakly supervised signals.

Researchers and practitioners in numerous fields yearn to understand human behavior and use that knowledge to improve the quality of life for individuals and populations. Until recently, theories of behavior and its relationship with genetics, health, and the environment have been based on selfreport or human-observed information. Given the meteoric rise of pervasive and machine learning technologies, researchers now have the necessary tools to map a personalized human behaviorome.Despite these recent technology advances, we still face numerous challenges that limit our current ability to learn reliable, complete personal profiles. The ability to perform machine learning-based behavior observation and analysis in uncontrolled environments, where the physical twin lives, is a fundamental requirement. This capability is not only a key to understanding the relationship between behavior and its influences, but also represents an unmet need.In this talk, we highlight methods that have been designed at the WSU CASAS lab to lay the foundation for digitally mapping a human behaviorome. We mention hurdles that were faced along the way, which unexpectedly created new research opportunities. We also tour some of the applications of the human behaviorome that the group is exploring, specifically to impact health and quality of life for adults as they age.

This article introduces RAS, a cyber-physical system that supports individuals with memory limitations to perform daily activities in their own homes. RAS represents a partnership between a smart home, a robot, and software agents. When smart home residents perform activities, RAS senses their movement in the space and identifies the current activity. RAS tracks activity steps to detect omission errors. When an error is detected, the RAS robot finds and approaches the human with an offer of assistance. Assistance consists of playing a video recording of the entire activity, showing the omitted activity step, or guiding the resident to the object that is required for the current step. We evaluated RAS performance for 54 participants performing three scripted activities in a smart home testbed and for 2 participants using the system over multiple days in their own homes. In the testbed experiment, activity errors were detected with a sensitivity of 0.955 and specificity of 0.992. RAS assistance was performed successfully with a rate of 0.600. In the in-home experiments, activity errors were detected with a combined sensitivity of 0.905 and a combined specificity of 0.988. RAS assistance was performed successfully for the in-home experiments with a rate of 0.830.

Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not always be the case. As a complement to this challenge, single-source unsupervised domain adaptation can handle situations where a network is trained on labeled data from a source domain and unlabeled data from a related but different target domain with the goal of performing well at test-time on the target domain. Many single-source and typically homogeneous unsupervised deep domain adaptation approaches have thus been developed, combining the powerful, hierarchical representations from deep learning with domain adaptation to reduce reliance on potentially-costly target data labels. This survey will compare these approaches by examining alternative methods, the unique and common elements, results, and theoretical insights. We follow this with a look at application areas and open research directions.

Ecological Momentary Assessment (EMA) is an in-the-moment data collection method which avoids retrospective biases and maximizes ecological validity. A challenge in designing EMA systems is finding a time to ask EMA questions that increases participant engagement and improves the quality of data collection. In this work, we introduce SEP-EMA, a machine learning-based method for providing transition-based context-aware EMA prompt timings. We compare our proposed technique with traditional time-based prompting for 19 individuals living in smart homes. Results reveal that SEP-EMA increased participant response rate by 7.19% compared to time-based prompting. Our findings suggest that prompting during activity transitions makes the EMA process more usable and effective by increasing EMA response rates and mitigating loss of data due to low response rates.

In order to meet the health needs of the coming "age wave," technology needs to be designed that supports remote health monitoring and assessment. In this study we design clinician in the loop (CIL), a clinician-in-the-loop visual interface, that provides clinicians with patient behavior patterns, derived from smart home data. A total of 60 experienced nurses participated in an iterative design of an interactive graphical interface for remote behavior monitoring. Results of the study indicate that usability of the system improves over multiple iterations of participatory design. In addition, the resulting interface is useful for identifying behavior patterns that are indicative of chronic health conditions and unexpected health events. This technology offers the potential to support self-management and chronic conditions, even for individuals living in remote locations.

Change Point Detection (CPD) is the problem of discovering time points at which the behavior of a time series changes abruptly. In this paper, we present a novel real-time nonparametric change point detection algorithm called SEP, which uses Separation distance as a divergence measure to detect change points in high-dimensional time series. Through experiments on artificial and real-world datasets, we demonstrate the usefulness of the proposed method in comparison with existing methods.

Smart cities use information and communication technologies (ICT) to scale services include utilities and transportation to a growing population. In this article we discuss how smart city ICT can also improve healthcare effectiveness and lower healthcare cost for smart city residents. We survey current literature and introduce original research to offer an overview of how smart city infrastructure supports strategic healthcare using both mobile and ambient sensors combined with machine learning. Finally, we consider challenges that will be faced as healthcare providers make use of these opportunities.

As members of an increasingly aging society, one of our major priorities is to develop tools to detect the earliest stage of age-related disorders such as Alzheimer's Disease (AD). The goal of this paper is to evaluate the possibility of using unobtrusively collected activity-aware smart home behavior data to detect the multimodal symptoms that are often found to be impaired in AD. After gathering longitudinal smart home data for 29 older adults over an average duration of 2 years, we automatically labeled the data with corresponding activity classes and extracted time-series statistics containing ten behavioral features. Mobility, cognition, and mood were evaluated every six months. Using these data, we created regression models to predict symptoms as measured by the tests and a feature selection analysis was performed. Classification models were built to detect reliable absolute changes in the scores predicting symptoms and SmoteBOOST and wRACOG algorithms were used to overcome class imbalance where needed. Results show that all mobility, cognition, and depression symptoms can be predicted from activity-aware smart home data. Similarly, these data can be effectively used to predict reliable changes in mobility and memory skills. Results also suggest that not all behavioral features contribute equally to the prediction of every symptom. Future work therefore can improve model sensitivity by including additional longitudinal data and by further improving strategies to extract relevant features and address class imbalance. The results presented herein contribute toward the development of an early change detection system based on smart home technology.

We introduce an approach to learning from imbalanced class distributions that does not change the underlying data distribution. The ICC algorithm decomposes majority classes into smaller sub-classes that create a more balanced class distribution. In this paper, we explain how ICC can not only addressthe class imbalance problem but may also increase the expressive power of the hypothesis space. We validate ICC and analyze alternative decomposition methods on well-known machine learning datasets as well as new problems in pervasive computing. Our results indicate that ICC performs as well or better than existing approaches to handling class imbalance.

Smartphone prompts and notifications are popular because they provide users with timely and important information. However, they can also be an annoyance if they pop up at inopportune times and interrupt important tasks. In this paper, we introduce Thyme, an intelligent notification front end that uses activity recognition and machine learning to identify the best times to prompt smartphone users. We evaluate the performance of an activity-aware prompting approach based on 47 participants with fixed time and Thyme-based prompts. Our results show that responsiveness improves from 12.8% to 93.2% using this intelligent approach to the timing of smartphone-based prompts.

One of major challenges in chronic disease self-management is the lack of medication adherence. Despite the proliferation of mobile technologies, the potential of using pervasive computing solutions for improved medication management has remained almost unexplored. In this paper, we present a smart-phone based system capable of delivering adaptive activity-aware medication reminders by learning the user's activity of daily living and detecting the most appropriate and effective timing for medication reminders centered around the initial user-specified schedule.

The papers in this special section focus on cyber-physical man-machine systems with particular emphasis on situation, activity, and goal awareness deployed in these systems. Recent advances in sensing technologies, the Internet of Things, pervasive computing, smart environments have transformed traditional embedded ICT systems into an ecosystem of interconnected and collaborating smart objects, devices, embedded systems, and most importantly humans. Such systems, often referred to as cyber-physical systems (CPS), are usually human user-driven or user-centered, and are aimed at providing people and businesses with a wide range of innovative applications and services. For example, a “smart home” can monitor and analyze the daily activities of its inhabitants, usually the elderly or individuals with disabilities, so that personalized context-aware assistance can be provided. A “smart city” can monitor, manage, and potentially control all basic city functionalities such as transport, energy supply, and waste collection, at a higher level of automation by collecting and harnessing sensor data across a large geographic expanse. In order to respond in real-time to an individual user’s specific needs in dynamic and complex situations, and to support ergonomics and user-friendliness through consideration of human factors such as privacy, dignity, and behavior characteristics, cyber-physical human–machine systems need to be aware of the physical environment and human participant behavior. This awareness enables effective and fast feedback loops between sensing and actuation, possibly with cognitive and learning capabilities adapting to participant preferences, capabilities, and the modality of human–machine interaction as well as dynamic situations.

Recent progress in Internet of Things (IoT) platforms has allowed us to collect large amounts of sensing data. However, there are significant challenges in converting this large-scale sensing data into decisions for real-world applications. Motivated by applications like health monitoring and intervention and home automation we consider a novel problem called Activity Prediction, where the goal is to predict future activity occurrence times from sensor data. In this paper, we make three main contributions. First, we formulate and solve the activity prediction problem in the framework of imitation learning and reduce it to a simple regression learning problem. This approach allows us to leverage powerful regression learners that can reason about the relational structure of the problem with negligible computational overhead. Second, we present several metrics to evaluate activity predictors in the context of real-world applications. Third, we evaluate our approach using real sensor data collected from 24 smart home testbeds. We also embed the learned predictor into a mobile-device-based activity prompter and evaluate the app for nine participants living in smart homes. Our results indicate that our activity predictor performs better than the baseline methods, and offers a simple approach for predicting activities from sensor data.

Smart home environments offer an unprecedented opportunity to unobtrusively monitor human behavior. Sensor data collected from smart homes can be labeled using activity recognition to help determine whether relationships exist between behavior in the home and health changes. To detect and analyze behavior changes that accompany health events, we introduce the behavior change detection (BCD) approach. BCD detects activity timing and duration changes between windows of time, determines the significance of the detected changes, and analyzes the nature of the changes. We demonstrate our approach using two case studies for older adults living in smart homes who experienced major health events, including cancer treatment and insomnia. Our algorithm detects behavior changes consistent with the medical literature for these cases. The results suggest the changes can be automatically detected using BCD. The proposed smart home, activity recognition algorithms, and change detection approach are useful data mining techniques for understanding the behavioral effects of major health conditions.

Wearable sensors are gaining traction in various healthcare domains, including patient mobility assessment performed in rehabilitation environments. Typically, clinical observations by therapists are used to characterize patient movement abilities and progress. More precise quantitative measurements of patient performance can be collected with wearable inertial sensors. Highly useful quantitative information and visual presentations of wearable sensor data are critical in gaining therapist acceptance of the technology and improving the therapy experience for patients. To bridge the gap between design of mobility monitoring technology and actual use of the technology, we report responses from interviews conducted with physical therapy providers at an inpatient rehabilitation facility. The information presented during the interviews includes results from our wearable sensor-based mobility assessment algorithms. Our smart computing algorithms utilize wearable sensor data to extract patient movement metrics, train clinical assessment prediction models, and visualize the data. The interview results indicate therapy providers are interested in using wearable sensors and wearable sensor- based metrics, prediction tools, and visualizations while they provide therapy services for their patients. Based on therapist feedback, we suggest future research directions that may increase the clinical utility and adoption of wearable sensor systems and data visualization for mobility assessment.

Smart home technologies offer potential benefits for assisting clinicians by automating health monitoring and well-being assessment. In this paper, we examine the actual benefits of smart home-based analysis by monitoring daily behavior in the home and predicting clinical scores of the residents. To accomplish this goal, we propose a clinical assessment using activity behavior (CAAB) approach to model a smart home resident's daily behavior and predict the corresponding clinical scores. CAAB uses statistical features that describe characteristics of a resident's daily activity performance to train machine learning algorithms that predict the clinical scores. We evaluate the performance of CAAB utilizing smart home sensor data collected from 18 smart homes over two years. We obtain a statistically significant correlation ( r=0.72) between CAAB-predicted and clinician-provided cognitive scores and a statistically significant correlation ( r=0.45) between CAAB-predicted and clinician-provided mobility scores. These prediction results suggest that it is feasible to predict clinical scores using smart home sensor data and learning-based data analysis.

We consider a novel problem called Activity Prediction, where the goal is to predict the future activity occurrence times from sensor data. In this paper, we make three main contributions. First, we formulate and solve the activity prediction problem in the framework of imitation learning and reduce it to simple regression learning problem. This approach allows us to leverage powerful regression learners; is easy to implement; and can reason about the relational and temporal structure of the problem with negligible computational overhead. Second, we present several evaluation metrics to evaluate a given activity predictor, and discuss their pros and cons in the context of real-world applications. Third, we evaluate our approach using real sensor data collected from 24 smart home testbeds. We also embed the learned predictor into a mobile device based activity prompter and evaluate the app on multiple participants living in smart homes. Our experimental results indicate that the activity predictor learned with our approach performs better than the baseline methods, and offers a simple and reliable approach to prediction of activities from sensor data.

Individuals with cognitive impairment can benefit from intervention strategies like recording important information in a memory notebook. However, training individuals to use the notebook on a regular basis requires a constant delivery of reminders. In this work, we design and evaluate machine learning-based methods for providing automated reminders using a digital memory notebook interface. Specifically, we identify transition periods between activities as times to issue prompts. We consider the problem of detecting activity transitions using supervised and unsupervised machine learning techniques, and find that both techniques show promising results for detecting transition periods. We test the techniques in a scripted setting with 15 individuals. Motion sensors data is recorded and annotated as participants perform a fixed set of activities. We also test the techniques in an unscripted setting with 8 individuals. Motion sensor data is recorded as participants go about their normal daily routine. In both the scripted and unscripted settings a true positive rate of greater than 80% can be achieved while maintaining a false positive rate of less than 15%. On average, this leads to transitions being detected within 1 minute of a true transition for the scripted data and within 2 minutes of a true transition on the unscripted data.

Transfer learning aims to improve performance on a target task by utilizing previous knowledge learned from source tasks. In this paper we introduce a novel heterogeneous transfer learning technique, Feature- Space Remapping (FSR), which transfers knowledge between domains with different feature spaces. This is accomplished without requiring typical feature-feature, feature instance, or instance-instance co-occurrence data. Instead we relate features in different feature-spaces through the construction of meta-features. We show how these techniques can utilize multiple source datasets to construct an ensemble learner which further improves performance. We apply FSR to an activity recognition problem and a document classification problem. The ensemble technique is able to outperform all other baselines and even performs better than a classifier trained using a large amount of labeled data in the target domain. These problems are especially difficult because in addition to having different feature-spaces, the marginal probability distributions and the class labels are also different. This work extends the state of the art in transfer learning by considering large transfer across dramatically different spaces.

One of the many services that intelligent systems can provide is the ability to analyze the impact of different medical conditions on daily behavior. In this study, we use smart home and wearable sensors to collect data, while ( n = 84) older adults perform complex activities of daily living. We analyze the data using machine learning techniques and reveal that differences between healthy older adults and adults with Parkinson disease not only exist in their activity patterns, but that these differences can be automatically recognized. Our machine learning classifiers reach an accuracy of 0.97 with an area under the ROC curve value of 0.97 in distinguishing these groups. Our permutation-based testing confirms that the sensor-based differences between these groups are statistically significant.

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.

The Ambient Intelligence (AmI) paradigm brings about an important challenge: to make environments adaptive, responsive, and reactive to users’ current contextual situations. It proclaims that our e...

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 over sampling 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 well represented which leads to high misclassification error. We introduce wRACOG, a Gibbs sampling-based over sampling approach to synthetically generating and strategically selecting new minority class samples. The Gibbs sampler uses the joint probability distribution of data attributes to generate new minority class samples in the form of a Markov chain. wRACOG iteratively learns a model by selecting samples from the Markov chain that have the highest probability of being misclassified. We validate the effectiveness of wRACOG using five UCI datasets and one new application domain dataset. A comparative study of wRACOG with three other well-known resampling methods provides evidence that wRACOG offers a definite improvement in classification accuracy for minority class samples over other methods.

We propose a hybrid approach for recognizing complex Activities of Daily Living that lie between the two extremes of intensive use of body-worn sensors and the use of infrastructural sensors. Our approach harnesses the power of infrastructural sensors (e.g., motion sensors) to provide additional `hidden' context (e.g., room-level location) of an individual and combines this context with smartphone-based sensing of micro-level postural/locomotive states. The major novelty is our focus on multi-inhabitant environments, where we show how spatiotemporal constraints can be used to significantly improve the accuracy and computational overhead of traditional coupled-HMM based approaches. Experimental results on a smart home dataset demonstrate that this approach improves the accuracy of complex ADL classification by over 30% compared to pure smartphone-based solutions.

Ambient Intelligence (AmI) is a new paradigm in information technology aimed at empowering people's capabilities by the means of digital environments that are sensitive, adaptive, and responsive to human needs, habits, gestures, and emotions. This futuristic vision of daily environment will enable innovative human-machine interactions characterized by pervasive, unobtrusive and anticipatory communications. Such innovative interaction paradigms make ambient intelligence technology a suitable candidate for developing various real life solutions, including in the health care domain. This survey will discuss the emergence of ambient intelligence (AmI) techniques in the health care domain, in order to provide the research community with the necessary background. We will examine the infrastructure and technology required for achieving the vision of ambient intelligence, such as smart environments and wearable medical devices. We will summarize of the state of the art artificial intelligence methodologies used for developing AmI system in the health care domain, including various learning techniques (for learning from user interaction), reasoning techniques (for reasoning about users' goals and intensions) and planning techniques (for planning activities and interactions). We will also discuss how AmI technology might support people affected by various physical or mental disabilities or chronic disease. Finally, we will point to some of the successful case studies in the area and we will look at the current and future challenges to draw upon the possible future research paths.

Active learning is a supervised learning technique that reduces the number of examples required for building a successful classifier, because it can choose the data it learns from. This technique holds promise for many biological domains in which classified examples are expensive and time-consuming to obtain. Most traditional active learning methods ask very specific queries to the Oracle (e.g., a human expert) to label an unlabeled example. The example may consist of numerous features, many of which are irrelevant. Removing such features will create a shorter query with only relevant features, and it will be easier for the Oracle to answer. We propose a generalized query-based active learning (GQAL) approach that constructs generalized queries based on multiple instances. By constructing appropriately generalized queries, we can achieve higher accuracy compared to traditional active learning methods. We apply our active learning method to find differentially DNA methylated regions (DMRs). DMRs are DNA locations in the genome that are known to be involved in tissue differentiation, epigenetic regulation, and disease. We also apply our method on 13 other data sets and show that our method is better than another popular active learning technique.

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.

The increasing aging population in the coming decades will result in many complications for society and in particular for the healthcare system due to the shortage of healthcare professionals and healthcare facilities. To remedy this problem, researchers have pursued developing remote monitoring systems and assisted living technologies by utilizing recent advances in sensor and networking technology, as well as in the data mining and machine learning fields. In this article, we report on our fully automated approach for discovering and monitoring patterns of daily activities. Discovering and tracking patterns of daily activities can provide unprecedented opportunities for health monitoring and assisted living applications, especially for older adults and individuals with mental disabilities. Previous approaches usually rely on preselected activities or labeled data to track and monitor daily activities. In this article, we present a fully automated approach by discovering natural activity patterns and their variations in real-life data. We will show how our activity discovery component can be integrated with an activity recognition component to track and monitor various daily activity patterns. We also provide an activity visualization component to allow caregivers to visually observe and examine the activity patterns using a user-friendly interface. We validate our algorithms using real-life data obtained from two apartments during a three-month period.

introduction Introduction to the special section on intelligent systems for socially aware computing Authors: Zhiwen Yu Northwestern Polytechnical University, China Northwestern Polytechnical University, ChinaView Profile , Daqing Zhang Institute Telecom and Management SudPans, France Institute Telecom and Management SudPans, FranceView Profile , Nathan Eagle Media Lab, MIT, USA Media Lab, MIT, USAView Profile , Diane Cook Washington State University, USA Washington State University, USAView Profile Authors Info & Claims ACM Transactions on Intelligent Systems and TechnologyVolume 4Issue 3Article No.: 45pp 1–3https://doi.org/10.1145/2483669.2483678Published:01 July 2013Publication History 25citation183DownloadsMetricsTotal Citations25Total Downloads183Last 12 Months1Last 6 weeks1 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

Intelligent environments (IEs) are expected to support people in their daily lives. One of the hidden assumptions in IEs is that they propose a change of perspective in the relationships between humans and technology, shifting from a techno-centered perspective to a human-centered one. Unlike current computing systems where the user has to learn how to use the technology, an IE adapts its behavior to the users, even anticipating their needs, preferences, or habits. For this reason, the environment should learn how to react to the actions and needs of the users, and this should be achieved in an unobtrusive and transparent way. In order to provide personalized and adapted services, it is necessary to know the preferences and habits of users. Thus, the ability to learn patterns of behavior becomes an essential aspect for the successful implementation of IEs. This paper presents a system, learning frequent patterns of user behavior system (LFPUBS), that discovers users' frequent behaviors taking into consideration the specific features of IEs. The core of LFPUBS is the learning layer, which, unlike some other components, is independent of the particular environment in which the system is being applied. On one hand, it includes a language that allows the representation of discovered behaviors in a clear and unambiguous way. On the other hand, coupled with the language, an algorithm that discovers frequent behaviors has been designed and implemented. For this reason, it uses association, workflow mining, clustering, and classification techniques. LFPUBS was validated using data collected from two real environments. In MavPad environment, LFPUBS was tested with different confidence levels using data collected in three different trials, whereas in a WSU Smart Apartment environment LFPUBS was able to discover a predefined behavior.

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.

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.

In this paper we have proposed and designed FindingHuMo (Finding Human Motion), a real-time user tracking system for Smart Environments. FindingHuMo can perform device-free tracking of multiple (unknown and variable number of) users in the Hallway Environments, just from non-invasive and anonymous (not user specific) binary motion sensor data stream. The significance of our designed system are as follows: (a) fast tracking of individual targets from binary motion data stream from a static wireless sensor network in the infrastructure. This needs to resolve unreliable node sequences, system noise and path ambiguity, (b) Scaling for multi-user tracking where user motion trajectories may crossover with each other in all possible ways. This needs to resolve path ambiguity to isolate overlapping trajectories, FindingHumo applies the following techniques on the collected motion data stream: (i) a proposed motion data driven adaptive order Hidden Markov Model with Viterbi decoding (called Adaptive-HMM), and then (ii) an innovative path disambiguation algorithm (called CPDA). Using this methodology the system accurately detects and isolates motion trajectories of individual users. The system performance is illustrated with results from real-time system deployment experience in a Smart Environment.

In the effort to build a sustainable society, smart home research attention is being directed toward green technology and environmentally-friendly building designs. In this paper, we analyze the distribution of home energy consumption, and then present both linear and non-linear regression learning models for predicting energy usage given known human behavior and time-scale features. To guarantee the validity of our methods, two real-world data sets collected over three months are applied into training the models. Based upon our learning models, a web-based end-user system is developed for providing users feedback about behavior-based energy usage to promote energy efficiency and sustainability through behavior changes.

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 user's 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.

This paper presents a sequence-based activity prediction approach which uses Bayesian networks in a novel two-step process to predict both activities and their corresponding features. In addition to the proposed model, we also present the results of several search and score (S&S) and constraint-based (CB) Bayesian structure learning algorithms. The activity prediction performance of the proposed model is compared with the naïve Bayes and the other aforementionedS&S and CB algorithms. The experimental results are performed on real data collected from a smart home over the period of five months. The results suggest the superior activity prediction accuracy of the proposed network over the resulting networks of the mentioned Bayesian network structure learning algorithms.

BACKGROUND: Analyzing global experimental data can be tedious and time-consuming. Thus, helping biologists see results as quickly and easily as possible can facilitate biological research, and is the purpose of the software we describe. RESULTS: We present BirdsEyeView, a software system for visualizing experimental transcriptomic data using different views that users can switch among and compare. BirdsEyeView graphically maps data to three views: Cellular Map (currently a plant cell), Pathway Tree with dynamic mapping, and Gene Ontology http://www.geneontology.org Biological Processes and Molecular Functions. By displaying color-coded values for transcript levels across different views, BirdsEyeView can assist users in developing hypotheses about their experiment results. CONCLUSIONS: BirdsEyeView is a software system available as a Java Webstart package for visualizing transcriptomic data in the context of different biological views to assist biologists in investigating experimental results. BirdsEyeView can be obtained from http://metnetdb.org/MetNet_BirdsEyeView.htm.

A sensor network, unlike a traditional communication network, is deeply embedded in physical environments and its operation is mainly driven by the event activities in the environment. In long-term operations, the event activities usually show certain patterns that can be learned and exploited to optimize the network design. However, this has been underexplored in the literature. One work related to this is using Activity Transition Probability Graph (ATPG) for radio duty cycling [Tang et al. (2011) ActSee: Activity-Aware Radio Duty-Cycling for Sensor Networks in Smart Environments. Proc. IEEE INSS 2011, Penghu, Taiwan, June 12–15. IEEE Press]. In this paper, we present a novel Energy and Activity-aware Routing (EAR) protocol for sensor networks. As a case study, we have evaluated EAR with the data trace of real Smart Environments. In EAR an ATPG is learned and built from the event activity patterns. EAR is an online routing protocol, that chooses the next-hop relay node by utilizing: activity pattern information in the ATPG graph and a novel index of energy balance in the network. EAR extends the network lifetime by maintaining an energy balance across the nodes in the network, while meeting the application performance with desired throughput and low data delivery latency. We theoretically prove that: (i) the network throughput with EAR achieves a competitive ratio (i.e. the ratio of the performance of any offline algorithm that has knowledge of all past and future packet arrivals to the performance of our online algorithm) that is asymptotically optimal, and (ii) EAR achieves a lower bound in the network lifetime. Extensive experimental results from: (i) a 82 node Motelab sensor network testbed [Werner-Allen et al. (2005) MoteLab: A Wireless Sensor Network Testbed. Proc. ACM IPSN 2005, Los Angeles, CA, USA, April 25–27, pp. 483–488. IEEE Press, NJ, USA] and (ii) a varying size network (20–100) in sensor network simulator TOSSIM, validate that EAR outperforms the existing methods both in terms of network performance (network lifetime, network energy consumption) and application performance (low latency, desired throughput) for an energy-constrained sensor network.

Research on sensor-based activity recognition has, recently, made significant progress and is attracting growing attention in a number of disciplines and application domains. However, there is a lack of high-level overview on this topic that can inform related communities of the research state of the art. In this paper, we present a comprehensive survey to examine the development and current status of various aspects of sensor-based activity recognition. We first discuss the general rationale and distinctions of vision-based and sensor-based activity recognition. Then, we review the major approaches and methods associated with sensor-based activity monitoring, modeling, and recognition from which strengths and weaknesses of those approaches are highlighted. We make a primary distinction in this paper between data-driven and knowledge-driven approaches, and use this distinction to structure our survey. We also discuss some promising directions for future research.

Activity recognition research relies heavily on test data to verify the modeling technique and the performance of the activity recognition algorithm. But data from real deployments are expensive and time consuming to obtain. And even if cost is not an issue, regulatory limitations on the use of human subjects prohibit the collection of extensive datasets that can test all scenarios, under all circumstances. A powerful and verifiable simulation tool is needed to accelerate research on human activity recognition. We present Persim, an event driven simulator of human activities in pervasive spaces. Persim is capable of capturing elements of space, sensors, behaviors (activities), and their inter-relationships. We focus on presenting the five main use cases for Persim addressing dataset synthesis, reuse and extension of existing datasets, sharing of data and simulation projects, as well as data validation.

Active learning methods are used to improve the classification accuracy when little labeled data is available. Most traditional active learning methods pose a very specific query to the oracle, i.e. they ask for the label of an unlabeled example. This paper proposes a novel active learning method called RIQY (Rule Induced active learning QuerY). It can construct generic active learning queries based on rule induction from multiple unlabeled instances. These queries are shorter and more readable for the oracle and encompass many similar cases. Also the learning algorithm can achieve higher accuracy rates by asking fewer queries. We evaluate our algorithm on 12 different real datasets. Our results show that we can achieve higher accuracy rates using fewer queries compared to the traditional active learning methods.

The machine learning and pervasive sensing technologies found in smart homes offer unprecedented opportunities for providing health monitoring and assistance to individuals experiencing difficulties living independently at home. In order to monitor the functional health of smart home residents, we need to design technologies that recognize and track activities that people normally perform as part of their daily routines. Although approaches do exist for recognizing activities, the approaches are applied to activities that have been pre-selected and for which labeled training data is available. In contrast, we introduce an automated approach to activity tracking that identifies frequent activities that naturally occur in an individual's routine. With this capability we can then track the occurrence of regular activities to monitor functional health and to detect changes in an individual's patterns and lifestyle. In this paper we describe our activity mining and tracking approach and validate our algorithms on data collected in physical smart environments.

The generation of useful sensory data from real-world deployments of Ambient Intelligent Environments (AIEs) is challenging because of the high cost, significant groundwork and lack of access to human subjects. This situation can be improved by providing efficient simulators that can produce realistic simulation of the data collection from AIEs. One of the main problems for developing AIE simulators lies in the ability to verify how close the simulated data are to the real world data. In this paper, we present a fuzzy based verification agent for Persim - an event driven simulator for human activities in AIEs. The employed fuzzy based verification agent builds a data model that mimics the operation of Persim which allows for the latter's objective and subjective verification. We have conducted the verification on real world data captured from an actual smart apartment deployment. The results show the effectiveness of the fuzzy based verification agent in analyzing and comparing the Persim simulated data with the real world collected data. We also demonstrate how the verification agent is able to pinpoint specific changes to the simulation model to increase the realism of the simulation.

In recent years, new emerging application domains have introduced new constraints and methods in data mining field. One of such application domains is activity discovery from sensor data. Activity discovery and recognition plays an important role in a wide range of applications from assisted living to security and surveillance. Most of the current approaches for activity discovery assume a static model of the activities and ignore the problem of mining and discovering activities from a data stream over time. Inspired by the unique requirements of activity discovery application domain, in this paper we propose a new stream mining method for finding sequential patterns over time from streaming non-transaction data using multiple time granularities. Our algorithm is able to find sequential patterns, even if the patterns exhibit discontinuities (interruptions) or variations in the sequence order. Our algorithm also addresses the problem of dealing with rare events across space and over time. We validate the results of our algorithms using data collected from two different smart apartments.

Intelligent Environments depend on their capability to understand and anticipate user's habits and needs. Therefore, learning user's common behaviours becomes an important step towards allowing an environment to provide such personalized services. Due to the complexity of the entire learning system, this paper will focus on the automatic discovering of models of user's behaviours. Discovering the models means to discover the order of such actions, representing user's behaviours as sequences of actions.

Recent years have witnessed the emergence of Smart Environments technology for assisting people with their daily routines and for remote health monitoring. A lot of work has been done in the past few years on Activity Recognition and the technology is not just at the stage of experimentation in the labs, but is ready to be deployed on a larger scale. In this paper, we design a data-mining framework to extract the useful features from sensor data collected in the smart home environment and select the most important features based on two different feature selection criterions, then utilize several machine learning techniques to recognize the activities. To validate these algorithms, we use real sensor data collected from volunteers living in our smart apartment test bed. We compare the performance between alternative learning algorithms and analyze the prediction results of two different group experiments performed in the smart home.

In smart home environments, it is highly desirable to know who is performing what actions. This knowledge allows the system to accurately build individuals' histories and to take personalized action based on the current resident. Without a good handle on identity, multi-resident smart homes are less effective when used for medical and assistive applications. Most smart home systems either have a single occupancy requirement, or rely on a wireless or video device to identify individuals. These requirements are too burdensome in some situations, which can limit the deployment of smart home technologies in environments that would derive benefits from them. This research work introduces the use of passive sensors and a Hidden Markov Model as a means to identify individuals. The result is a passive, low profile means to attribute individual events to unique residents. For this work, two different pairs of individuals living in a smart home testbed are used to evaluate the tools. The data used is from unscripted, full time occupancy and annotated by the residents themselves for accuracy. Lastly, the Hidden Markov Model approach is compared and contrasted against a prior Naive Bayes solution on the same data sets.

Household electricity consumption is a direct contributor to household expenses. Electricity acts as a backbone for a strong economy [1]. The rise in the energy consumption is clearly observed in this past decade, and so is the rise in the need for energy efficiency and conservation [2]. Monitoring power consumption by using various devices and instruments is on the rise; however a smart environment scenario needs more than just real-time monitoring. The need for identifying abnormal power consumption is clearly present. In this paper, we introduce our work on building novel outlier detection algorithms which uses statistical techniques to identify outliers and anomalies in power datasets collected in smart environments. We also experiment clustering techniques on the same dataset and report the results found.

Smart environment applications have gained a lot of attention and acceptance from the community. For this reason, many design and evaluation efforts target these applications. However, these applications rely on a software architecture that driven by a well-designed middleware. In this paper we propose design and evaluation requirements for smart environment software architectures and demonstrate how these requirements can be met with a simple, lightweight publish-subscribe design paradigm. We describe our CLM middleware that follows these requirements and illustrate its extensive use as part of the CASAS smart home system.

The pervasive sensing technologies found in smart environments offer unprecedented opportunities for monitoring and assisting the individuals who live and work in these spaces. An aspect of daily life that is important for one's emotional and physical health is social interaction. In this paper we investigate the use of smart environment technologies to detect and analyze interactions in smart spaces. We introduce techniques for collect and analyzing sensor information in smart environments to help in interpreting resident behavior patterns and determining when multiple residents are interacting. The effectiveness of our techniques is evaluated using two physical smart environment testbeds.

The graph classification problem is learning to classify separate, individual graphs in a graph database into two or more categories. A number of algorithms have been introduced for the graph classification problem. We present an empirical comparison of the major approaches for graph classification introduced in literature, namely, SubdueCL, frequent subgraph mining in conjunction with SVMs, walk-based graph kernel, frequent subgraph mining in conjunction with AdaBoost and DT-CLGBI. Experiments are performed on five real world data sets from the mutagenesis and predictive toxicology domain which are considered benchmark data sets for the graph classification problem. Additionally, experiments are performed on a corpus of artificial data sets constructed to investigate the performance of the algorithms across a variety of parameters of interest. Our conclusions are as follows. In datasets where the underlying concept has a high average degree, walk-based graph kernels perform poorly as compared to other approaches. The hypothesis space of the kernel is walks and it is insufficient at capturing concepts involving significant structure. In datasets where the underlying concept is disconnected, SubdueCL performs poorly as compared to other approaches. The hypothesis space of SubdueCL is connected graphs and it is insufficient at capturing concepts which consist of a disconnected graph. FSG+SVM, FSG+AdaBoost, DT-CLGBI have comparable performance in most cases.

The direct product kernel, introduced by Gartner et al. for graph classification, is based on defining a feature for every possible label sequence in a labelled graph and counting how many label sequences in two given graphs are identical. Although the direct product kernel has achieved promising results in terms of accuracy, the kernel computation is not feasible for large graphs. This is because computing the direct product kernel for two graphs is essentially computing either the inverse of or by diagonalizing the adjacency matrix of the direct product of these two graphs. For two graphs with adjacency matrices of sizes m and n, the adjacency matrix of their direct product graph can be of size mn in the worst case. As both matrix inversion or matrix diagonalizing in the general case is O(n3), computing the direct product kernel is O((mn)3). Our survey of data sets in graph classification indicates that most graphs have adjacency matrices of sizes in the order of hundreds which often leads to adjacency matrices of direct product graphs (of two graphs) having sizes in the order of thousands. In this work we show how the direct product kernel can be computed in O((m + n)3). The key insight behind our result is that the language of label sequences in a labeled graph is a regular language and that regular languages are closed under union and intersection.

Intelligent Environments depend on their capability to understand and anticipate user's habits and needs. Therefore, learning user's common behaviours becomes an important step towards allowing an environment to provide such personalized services. We have developed a system which learns user's patterns taking into account the special features of Intelligent Environments. Due to the complexity of the system, this paper will focus on a specific part of such a system, the module that discovers what sets of actions are frequently carried out by the user.

Persistent problems in obtaining test data while developing technologies for pervasive spaces include the lack of data generation and representation standards, limited amount of available test data, incompleteness of existing data sets, and high cost of implementing a given pervasive space. This not only hinders the development and design of pervasive spaces, but also decreases the ability of researchers to compare results with those of other areas in computer science. For example, in the interaction between sensors and actuators, testing the robustness of new algorithms and evaluating risk requires large datasets that portray different scenarios. However, associated costs can be prohibitive as the data burden increases. In response to this situation, we propose a Pervasive Space Simulation Technique (PSST) that uses Markov chains, non-homogenous Poisson processes, and distribution fitting for generation of synthetic test data. PSST provides a realistic simulation of events in the pervasive space.

Most commonly-used techniques in smart environments such as ADL recognition are designed and tested for a specific space and a specific person; therefore learning in each environmental situation is treated as a separate context. In this paper, we try to develop a method for recognizing and transferring learned knowledge of activities between different residents. Our method is able to map activities despite intra-subject variability and inter-subject variability, by using a discontinuous mining method and a similarity measurement method. At the end, we will provide the results of our experiments on real data obtained from a smart apartment.

Smart environments rely on artificial intelligence techniques to make sense of the sensor data and to use the information for recognition and tracking activities. However, many of the techniques that have been developed are designed for simplified situations. In this paper we discuss a more complex situation, namely recognizing activities when they are interweaved in complex and realistic scenarios. This technology is beneficial for monitoring the health of smart environment residents and for correlating activities with parameters such as energy usage. We describe our approach to interleaved activity recognition and evaluate various probabilistic techniques for activity recognition. We validate our algorithm on real sensor data collecting in our smart apartment testbed.

Our dynamic graph-based relational mining approach has been developed to learn structural patterns in biological networks as they change over time. The analysis of dynamic networks is important not only to understand life at the system-level, but also to discover novel patterns in other structural data. Most current graph-based data mining approaches overlook dynamic features of biological networks, because they are focused on only static graphs. Our approach analyzes a sequence of graphs and discovers rules that capture the changes that occur between pairs of graphs in the sequence. These rules represent the graph rewrite rules that the first graph must go through to be isomorphic to the second graph. Then, our approach feeds the graph rewrite rules into a machine learning system that learns general transformation rules describing the types of changes that occur for a class of dynamic biological networks. The discovered graph-rewriting rules show how biological networks change over time, and the transformation rules show the repeated patterns in the structural changes. In this paper, we apply our approach to biological networks to evaluate our approach and to understand how the biosystems change over time. We evaluate our results using coverage and prediction metrics, and compare to biological literature.

Advancements in supporting fields have increased the likelihood that smart-home technologies will become part of our everyday environments. However, many of these technologies are brittle and do not adapt to the user's explicit or implicit wishes. Here, we introduce CASAS, an adaptive smart-home system that utilizes machine learning techniques to discover patterns in resident's daily activities and to generate automation polices that mimic these patterns. Our approach does not make any assumptions about the activity structure or other underlying model parameters but leaves it completely to our algorithms to discover the smart-home resident's patterns. Another important aspect of CASAS is that it can adapt to changes in the discovered patterns based on the resident implicit and explicit feedback and can automatically update its model to reflect the changes. In this paper, we provide a description of the CASAS technologies and the results of experiments performed on both synthetic and real-world data.

The unprecedented rate at which genomic data is accumulated underscores the need to develop highly efficient analytical capabilities. Traditionally, most of the effort post-sequencing has been focused on the identification and annotation of genes along with their promoters and regulatory elements. However, a major part of the vastness outside the gene-space is still left unexplored because of a lack of appropriate computational tools. Here, we propose a new approach for exploring and describing a genome without biasing the search process towards already known structural entities. Our primary objective is to discover novel conserved patterns that would typically fall off the scope of the current suite of repeat finding tools because of irregularities in their structure. The output is a hierarchy of patterns with arbitrary structural characteristics. A hierarchical representation captures the genomic sequence content at an abstract level and offers novel ways to examine the information contained in them. Our approach is an information theoretic search process which uses pattern matching techniques for processing the sequence data. Preliminary evaluation on the Drosophila genome has resulted in the finding of a number of irregular patterns. Discovering new patterns is an important problem in both whole- and comparative genomic application domains. The proposed approach can provide an information-theoretic framework for conducting pattern and knowledge discovery on genomic data.

We introduce a graph-based relational learning approach using graph-rewriting rules for temporal and structural analysis of biological networks changing over time. The analysis of dynamic biological networks is necessary to understand life at the system-level, because biological networks continuously change their structures and properties, while an organism performs various biological activities. A dynamic graph represents dynamic properties as well as structural properties of biological networks. Microarray data can reflect dynamic properties of biological processes. Biological networks, which contain various molecules and relationships between molecules, show structural properties representing various relationships between entities. Most current graph-based data mining approaches overlook dynamic features of biological networks, because they are focused on only static graphs. Most approaches for analysis of microarray data disregard structural properties on biological systems. But our dynamic graph-based relational learning approach describes how the graphs temporally and structurally change over time in the dynamic graph representing biological networks in combination with microarray data.

Currently available pixel-based image analysis techniques do not effectively extract the information content from the increasingly available high spatial resolution remotely sensed imagery data. We are exploring an approach to object-based image analysis in which hierarchical image segmentations provided by the Recursive Hierarchical Segmentation (RHSEG) software are analyzed by the Subdue graph-based knowledge-discovery system. In this paper we discuss our initial approach to representing the RHSEG-produced hierarchical image segmentations in a graphical form understandable by Subdue, and discuss results from real and simulated data.

There is much video available today. To help viewers find video of interest, work has begun on methods of automatic video classification. In this paper, we survey the video classification literature. We find that features are drawn from three modalities—text, audio, and visual—and that a large variety of combinations of features and classification have been explored. We describe the general features chosen and summarize the research in this area. We conclude with ideas for further research.

Sexually transmitted diseases and infections are, by definition, transferred among intimate social settings. Although the circumstances under which these social settings are established and maintained may vary, the common prerequisite remains an intimate level of social atmosphere. For this reason, the development of sexually transmitted disease mathematical and computational models must utilize a precise and efficient social networking tool. This paper describes a computational simulator created to embody the intimate social networks related to the transmission of sexually transmitted diseases and infections for the utilization by public health professionals to facilitate evaluation of targeted intervention strategies.

The ability to transfer knowledge learned in one environment in order to improve performance in a different environment is one of the hallmarks of human intelligence. Insights into human transfer learning help us to design computer-based agents that can better adapt to new environments without the need for substantial reprogramming. In this paper, we study the transfer of knowledge by humans playing various scenarios in a graphically realistic urban setting that are specifically designed to test various levels of transfer. We determine the amount and type of transfer that is being performed based on the performance of trained and untrained human players. In addition, we use a graph-based relational learning algorithm to extract patterns from player graphs. These analyses reveal that indeed humans are transferring knowledge from on 3 set of games to another and the amount and type of transfer varies according to player experience and scenario complexity. The results of this analysis help us understand the nature of human transfer in such environments and shed light on how we might endow computer-based agents with similar capabilities. The game simulator and human data collection also represent a significant testbed in which other Al capabilities can be tested and compared to human performance.

In this paper, we examine the problem of learning inhabitant behavioral models in intelligent environments. We maintain that inhabitant interactions in smart environments can be automated using a data-driven approach to generate hierarchical inhabitant models and learn decision policies. To validate this hypothesis, we have designed the ProPHeT decision-learning algorithm that learns a strategy for controlling a smart environment based on sensor observation, power line control, and the generated hierarchical model. The performance of the algorithm is evaluated using real data collected from our MavHome smart home and smart office environments.

Computer programs that can be expressed in two or more dimensions are typically called visual programs. The underlying theories of visual programming languages involve graph grammars. As graph grammars are usually constructed manually, construction can be a time-consuming process that demands technical knowledge. Therefore, a technique for automatically constructing graph grammars - at least in part - is desirable. An induction method is given to infer node replacement graph grammars. The method operates on labeled graphs of broad applicability. It is evaluated by its performance on inferring graph grammars from various structural representations. The correctness of an inferred grammar is verified by parsing graphs not present in the training set

In this paper we describe an approach to learning node replacement graph grammars. This approach is based on previous research in frequent isomorphic subgraphs discovery. We extend the search for frequent subgraphs by checking for overlap among the instances of the subgraphs in the input graph. If subgraphs overlap by one node we propose a node replacement grammar production. We also can infer a hierarchy of productions by compressing portions of a graph described by a production and then infer new productions on the compressed graph. We validate this approach in experiments where we generate graphs from known grammars and measure how well our system infers the original grammar from the generated graph.

Human motion not only contains a wealth of information about actions and intentions, but also about identity and personal attributes of the moving person. Research also indicates that there are positive relationships between the health of a person and their pattern of motion. In this research we utilize human walking data collected from volunteers to identify age categories and to detect possible changes in the individual's health condition. The approach is based on transforming biological motion data into a representation that subsequently allows for analysis using artificial intelligence techniques. Using wireless accelerometer sensors we were able to collect and transform the data into a numeric representation. We then applied the numeric data to various artificial intelligence algorithms to form classification models and use it for our analysis.

This paper summarizes our experience in designing and modeling single habitant and multiple inhabitant smart environments based on learning and prediction based paradigm.

The goal of the MavHome project is to develop technologies to manage adaptive versatile environments. In this paper, we present a complete agent architecture for a single inhabitant intelligent environment and discuss the development, deployment, and techniques utilized in our working intelligent environments. Empirical evaluation of our approach has proven its effectiveness at reducing inhabitant interactions by 72.2%

Developing technologies and systems for automated control of home and workplace environments is a challenging problem. We present a complete agent architecture for learning to automate a smart environment and discuss integration of AT and middleware technologies necessary to achieve the goals of this project. Results are demonstrated using the MavPad and MavLab intelligent environments.

The data stream captured by recording inhabitant-device interactions in an environment can be mined to discover significant patterns, which an intelligent agent could use to automate device interactions. However, this knowledge discovery problem is complicated by several challenges, such as excessive noise in the data, data that does not naturally exist as transactions, a need to operate in real time, and a domain where frequency may not be the best discriminator. We propose a novel data mining technique that addresses these challenges and discovers regularly-occurring interactions with a smart home. We also discuss a case study that shows the data mining technique can improve the accuracy of two prediction algorithms, thus demonstrating multiple uses for a home automation system. Finally, we present an analysis of the algorithm and results obtained using inhabitant interactions.

Autonomous robots hold the possibility of performing a variety of assistive tasks in intelligent environments. However, widespread use of robot assistants in these environments requires ease of use by individuals who are generally not skilled robot operators. In this paper we present a method of training robots that bridges the gap between user programming of a robot and autonomous learning of a robot task. With our approach to variable autonomy, we integrate user commands at varying levels of abstraction into a reinforcement learner to permit faster policy acquisition. We illustrate the ideas using a robot assistant task, that of retrieving medicine for an inhabitant of a smart home.

Anomaly detection is an area that has received much attention in recent years. It has a wide variety of applications, including fraud detection and network intrusion detection. A good deal of research has been performed in this area, often using strings or attribute-value data as the medium from which anomalies are to be extracted. Little work, however, has focused on anomaly detection in graph-based data. In this paper, we introduce two techniques for graph-based anomaly detection. In addition, we introduce a new method for calculating the regularity of a graph, with applications to anomaly detection. We hypothesize that these methods will prove useful both for finding anomalies, and for determining the likelihood of successful anomaly detection within graph-based data. We provide experimental results using both real-world network intrusion data and artificially-created data.

The goal of the MavHome (Managing An Intelligent Versatile Home) project is to create a home that acts as an intelligent agent. In this paper we introduce the MavHome architecture. The role of prediction algorithms within the architecture is discussed, and a meta-predictor is presented which combines the strengths of multiple approaches to inhabitant action prediction. We demonstrate the effectiveness of these algorithms on smart home data.

The rapid advances in a wide range of wireless access technologies along with the efficient use of smart spaces have already set the stage for the development of smart homes. Context-awareness is perhaps the most salient feature in these intelligent computing platforms. The "location" information of the users plays a vital role in defining this context. To extract the best performance and efficacy of such smart computing environments, one needs a scalable, technology-independent location service. We have developed a predictive framework for location-aware resource optimization in smart homes. The underlying compression mechanism helps in efficient learning of an inhabitant's movement (location) profiles in the symbolic domain. The concept of Asymptotic Equipartition Property (AEP) in information theory helps to predict the inhabitant's future location as well as most likely path-segments with good accuracy. Successful prediction helps in pro-active resource management and on-demand operations of automated devices along the inhabitant's future paths and locations - thus providing the necessary comfort at a near-optimal cost. Simulation results on a typical smart home floor plans corroborate this high prediction success and demonstrate sufficient reduction in daily energy-consumption, manual operations and time spent by the inhabitant which are considered as a fair measure of his/her comfort.

The World Wide Web provides an immense source of information. Accessing information of interest presents a challenge to scientists and analysts, particularly if the desired information is structural in nature. Our goal is to design a structural search engine that uses the hyperlink structure of the Web, in addition to textual information, to search for sites of interest. Our structural search engine, called WebSUBDUE, searches not only for particular words or topics but also for a desired hyperlink structure. Enhanced by WordNet text functions, our search engine retrieves sites corresponding to structures formed by graph-based user queries. We hypothesize that this system can form the heart of a structural query engine, and demonstrate the approach on a number of structural web queries.

Human and software agents exhibit regularities in their activities. We describe our ONASI algorithm, which derives a Markov model from such observed regularities, and dynamically scales the model through merging and splitting of states. ONASI uses this model to predict the agent's next action. We evaluate ONASI's predictive accuracy on a dataset of Wumpus World games, and demonstrate from this approach that the model can correctly predict the agent's next action with adjustable computation and memory resources. These predictions can be used to imitate, assist or obstruct an agent.

Knowledge engineering for planning is expensive and the resulting knowledge can be imperfect. To autonomously learn a plan operator definition from environmental feedback, our learning system WISER explores an instantiated literal space using a breadth‐first search technique. Each node of the search tree represents a state, a unique subset of the instantiated literal space. A state at the root node is called a seed state. WISER can generate seed states with or without utilizing imperfect expert knowledge. WISER experiments with an operator at each node. The positive state, in which an operator can be successfully executed, constitutes initial preconditions of an operator. We analyze the number of required experiments as a function of the number of missing preconditions in a seed state. We introduce a naive domain assumption to test only a subset of the exponential state space. Since breadth‐first search is expensive, WISER introduces two search techniques to reorder literals at each level of the search tree. We demonstrate performance improvement using the naive domain assumption and literal‐ordering heuristics. To learn the effects of an operator, WISER computes the delta state, composed of the add list and the delete list, and parameterizes it. Unlike previous systems, WISER can handle unbound objects in the delta state. We show that machine‐generated effects definitions are often simpler in representation than expert‐provided definitions.

In recent years, there has been an explosive amount of molecular biology information obtained and deposited in various databases. Identifying and interpreting interesting patterns from this massive amount of information has become an essential component in directing further molecular biology research. The goal of this research is to discover structural regularities in protein sequences by applying the SUBDUE discovery system to databases found in the Brookhaven Protein Data Bank. In this paper we discuss issues relevant to this application including data preparation and representation. We report on the results of applying SUBDUE to several classes of protein structures and discuss the potential significance of these results in the study of proteins.

The large amount of data collected today is quickly overwhelming researchers' abilities to interpret the data and discover interesting patterns. Knowledge discovery and data mining approaches hold the potential to automate the interpretation process, but these approaches frequently utilize computationally expensive algorithms. In particular, scientific discovery systems focus on the utilization of richer data representation, sometimes without regard for scalability. This research investigates approaches for scaling a particular knowledge discovery in databases (KDD) system, SUBDUE, using parallel and distributed resources. SUBDUE has been used to discover interesting and repetitive concepts in graph-based databases from a variety of domains, but requires a substantial amount of processing time. Experiments that demonstrate scalability of parallel versions of the SUBDUE system are performed using CAD circuit databases and artificially-generated databases, and potential achievements and obstacles are discussed.

Many of the artificial intelligence techniques developed to date rely on heuristic search through large spaces. Unfortunately, the size of these spaces and the corresponding computational effort reduce the applicability of otherwise novel and effective algorithms. A number of parallel and distributed approaches to search have considerably improved the performance of the search process. Our goal is to develop an architecture that automatically selects parallel search strategies for optimal performance on a variety of search problems. In this paper we describe one such architecture realized in the Eureka system, which combines the benefits of many different approaches to parallel heuristic search. Through empirical and theoretical analyses we observe that features of the problem space directly affect the choice of optimal parallel search strategy. We then employ machine learning techniques to select the optimal parallel search strategy for a given problem space. When a new search task is input to the system, Eureka uses features describing the search space and the chosen architecture to automatically select the appropriate search strategy. Eureka has been tested on a MIMD parallel processor, a distributed network of workstations, and a single workstation using multithreading. Results generated from fifteen puzzle problems, robot arm motion problems, artificial search spaces, and planning problems indicate that Eureka outperforms any of the tested strategies used exclusively for all problem instances and is able to greatly reduce the search time for these applications.

Discovering repetitive, interesting, and functional substructures in a structural database improves the ability to interpret and compress the data. However, scientists working with a database in their area of expertise often search for predetermined types of structures or for structures exhibiting characteristics specific to the domain. The paper presents a method for guiding the discovery process with domain specific knowledge. The SUBDUE discovery system is used to evaluate the benefits of using domain knowledge to guide the discovery process. Domain knowledge is incorporated into SUBDUE following a single general methodology to guide the discovery process. Results show that domain specific knowledge improves the search for substructures that are useful to the domain and leads to greater compression of the data. To illustrate these benefits, examples and experiments from the computer programming, computer aided design circuit, and artificially generated domains are presented.

This paper describes a decision-theoretic approach to cooperative sensor planning between multiple autonomous vehicles executing a military mission. For this autonomous vehicle application, intelligent cooperative reasoning must be used to select optimal vehicle viewing locations and select optimal camera pan and tilt angles throughout the mission. Decisions are made in such a way as to maximize the value of information gained by the sensors while maintaining vehicle stealth. Because the mission involves multiple vehicles, cooperation can be used to balance the work load and to increase information gain. This paper presents the theoretical foundations of our cooperative sensor planning research and describes the application of these techniques to ARPA's Unmanned Ground Vehicle program.

Functionality-based recognition systems recognize objects at the category level by reasoning about how well the objects support the expected function. Such systems naturally associate a ``measure of goodness'' or ``membership value'' with a recognized object. This measure of goodness is the result of combining individual measures, or membership values, from potentially many primitive evaluations of different properties of the object's shape. A membership function is used to compute the membership value when evaluating a primitive of a particular physical property of an object. In previous versions of a recognition system known as Gruff, the membership function for each of the primitive evaluations was hand-crafted by the system designer. In this paper, we provide a learning component for the Gruff system, called Omlet, that automatically learns membership functions given a set of example objects labeled with their desired category measure. The learning algorithm is generally applicable to any problem in which low-level membership values are combined through an and-or tree structure to give a final overall membership value.

The ability to identify interesting and repetitive substructures is an essential component to discovering knowledge in structural data. We describe a new version of our SUBDUE substructure discovery system based on the minimum description length principle. The SUBDUE system discovers substructures that compress the original data and represent structural concepts in the data. By replacing previously-discovered substructures in the data, multiple passes of SUBDUE produce a hierarchical description of the structural regularities in the data. SUBDUE uses a computationally-bounded inexact graph match that identifies similar, but not identical, instances of a substructure and finds an approximate measure of closeness of two substructures when under computational constraints. In addition to the minimum description length principle, other background knowledge can be used by SUBDUE to guide the search towards more appropriate substructures. Experiments in a variety of domains demonstrate SUBDUE's ability to find substructures capable of compressing the original data and to discover structural concepts important to the domain. Description of Online Appendix: This is a compressed tar file containing the SUBDUE discovery system, written in C. The program accepts as input databases represented in graph form, and will output discovered substructures with their corresponding value.

Iterative-Deepening-A (IDA*) is an optimal search technique which is useful for large search spaces, because it requires no intermediate state storage. We show how Transformation-Ordering Iterative-Deepening-A* (TOIDA*) improves the performance of IDA* by dynamically modifying the node expansion order based on results from previous cost limits. We then describe a window parallel implementation of TOIDA* on a Hypercube, and present empirical evidence that the parallel implementation dramatically reduces time spent in search. Finally, we analyze the best and worst case results of sequential and parallel TOIDA*, and compare the results with those of standard IDA* search. Empirical and analytical results show that TOIDA* can provide significant improvements in search speed over IDA* with no penalty in storage requirements, and parallel TOIDA* offers substantial cost reduction over sequential TOIDA*, though at the cost of optimality. © 1993 John Wiley & Sons, Inc.

Concept discovery in structural data requires the identification of repetitive substructures in the data. A method for discovering substructures in data using an inexact graph match is described. An implementation of the authors' SUBDUE system that employs an inexact graph match to discover substructures which occur often in the data, but not always in the same form, is described. This inexact substructure discovery can be used to formulate fuzzy concepts, compress the data description, and discover interesting structures in data that are found either in an identical or in a slightly convoluted form. Examples from the domains of scene analysis and chemical compound analysis demonstrate the benefits of the inexact discovery technique.>

Analogical plaiining provides a. nieaiis of solving problems in some situations where other ma.chine lea,riiing methods fail, because it, does not, require iiuinerous previous examples or a rich doiiia.in theory. Given a problem in an unfamiliar doiimiu (tlie target ca.se) ~ an analogical planning system locates a. succ fill 11la.n in a similar domain (the base case), a.nd uses the siinihrities t.0 generate the target plan. One planning doinain which can ma.ke use of analogical planning to improve performance is robot arm path planning. In the Intelligent, Mechanisms Group at NASA Ames Research Center, algorithms are designed to guide a Puma. robot arm with 7 degrees of freedom through a 3dimensional workspace. The search spa.ce is immense, a.nd current inotion planning techniques do not t,alie advant,age of the fact that many planning situatioiis are similar. This paper describes a method of using analogies to improve the performance of robot arm path planning. C' veil an enviroiiiiient description, tjhe system looks for a siinilar previous case with a. successful plan. Thatm plan is ina.pped to the current problem environment^ tmo suggest a. possible path for the robot. An example of how the robot a.rm at, NASA Anies can iimke use of amlogies to generate plans is detailed.