Human Activity Recognition (HAR) using ambient sensors has great potential for practical applications, particularly in elder care and independent living. However, deploying HAR systems in real-world settings remains challenging due to the high cost of labeled data, the need for pre-segmented sensor streams, and the lack of flexibility in activity granularity. To address these limitations, we introduce DISCOVER, a method designed to discover fine-grained human sub-activities from unlabeled sensor data without relying on pre-segmentation. DISCOVER combines unsupervised feature extraction and clustering with a user-friendly visualization tool to streamline the labeling process. DISCOVER enables domain experts to efficiently annotate only a minimal set of representative cluster centroids, reducing the annotation workload to a small number of samples (0.05% of our dataset). We demonstrate DISCOVER's effectiveness through a re-annotation exercise on widely used HAR datasets, showing that it uncovers finer-grained activities and produces more nuanced annotations than traditional coarse labels. DISCOVER represents a step toward practical, deployable HAR systems that adapt to diverse real environments.

Human activity recognition (HAR) using ambient sensors in smart homes has numerous applications for human healthcare and wellness. However, building general-purpose HAR models that can be deployed to new smart home environments requires a significant amount of annotated sensor data and training overhead. Most smart homes vary significantly in their layouts, i.e., floor plans and the specifics of sensors embedded, resulting in low generalizability of HAR models trained for specific homes. We address this limitation by introducing a novel, layout-agnostic modeling approach for HAR systems in smart homes that utilizes the transferrable representational capacity of natural language descriptions of raw sensor data. To this end, we generate Textual Descriptions Of Sensor Triggers (TDOST) that encapsulate the surrounding trigger conditions and provide cues for underlying activities to the activity recognition models. Leveraging textual embeddings, rather than raw sensor data, we create activity recognition systems that predict standard activities across homes without either (re-)training or adaptation on target homes. Through an extensive evaluation, we demonstrate the effectiveness of TDOST-based models in unseen smart homes through experiments on benchmarked CASAS datasets. Furthermore, we conduct a detailed analysis of how the individual components of our approach affect downstream activity recognition performance.

Sensor-based human activity recognition (HAR) has been an active research area, owing to its applications in smart environments, assisted living, fitness, healthcare, etc. Recently, deep learning based end-to-end training has resulted in state-of-the-art performance in domains such as computer vision and natural language, where large amounts of annotated data are available. However, large quantities of annotated data are not available for sensor-based HAR. Moreover, the real-world settings on which the HAR is performed differ in terms of sensor modalities, classification tasks, and target users. To address this problem, transfer learning has been employed extensively. In this survey, we focus on these transfer learning methods in the application domains of smart home and wearables-based HAR. In particular, we provide a problem-solution perspective by categorizing and presenting the works in terms of their contributions and the challenges they address. We also present an updated view of the state-of-the-art for both application domains. Based on our analysis of 205 papers, we highlight the gaps in the literature and provide a roadmap for addressing them. This survey provides a reference to the HAR community, by summarizing the existing works and providing a promising research agenda.

Human activity recognition (HAR) in wearable computing is typically based on direct processing of sensor data. Sensor readings are translated into representations, either derived through dedicated preprocessing, or integrated into end-to-end learning. Independent of their origin, for the vast majority of contemporary HAR, those representations are typically continuous in nature. That has not always been the case. In the early days of HAR, discretization approaches have been explored - primarily motivated by the desire to minimize computational requirements, but also with a view on applications beyond mere recognition, such as, activity discovery, fingerprinting, or large-scale search. Those traditional discretization approaches, however, suffer from substantial loss in precision and resolution in the resulting representations with detrimental effects on downstream tasks. Times have changed and in this paper we propose a return to discretized representations. We adopt and apply recent advancements in Vector Quantization (VQ) to wearables applications, which enables us to directly learn a mapping between short spans of sensor data and a codebook of vectors, resulting in recognition performance that is generally on par with their contemporary, continuous counterparts - sometimes surpassing them. Therefore, this work presents a proof-of-concept for demonstrating how effective discrete representations can be derived, enabling applications beyond mere activity classification but also opening up the field to advanced tools for the analysis of symbolic sequences, as they are known, for example, from domains such as natural language processing. Based on an extensive experimental evaluation on a suite of wearables-based benchmark HAR tasks, we demonstrate the potential of our learned discretization scheme and discuss how discretized sensor data analysis can lead to substantial changes in HAR.

The concept of immediacy is ingrained in 21st-century life. From shopping on Amazon with next-day delivery to internet and location services providing real-time information in the palm of our hands, it is clear that instant results are only going to become more prevalent in everyday life. In an era when many are jaded about tech -- and it is increasingly harder to surprise and excite people about what it can do -- ChatGPT has been a refreshing development. It is engaging, can be a lot of fun to test-drive and has proved beneficial for students and professionals looking to generate content. And it is all done in an instant.

The dichotomy between the challenging nature of obtaining annotations for activities, and the more straightforward nature of data collection from wearables, has resulted in significant interest in the development of techniques that utilize large quantities of unlabeled data for learning representations. Contrastive Predictive Coding (CPC) is one such method, learning effective representations by leveraging properties of time-series data to setup a contrastive future timestep prediction task. In this work, we propose enhancements to CPC, by systematically investigating the encoder architecture, the aggregator network, and the future timestep prediction, resulting in a fully convolutional architecture, thereby improving parallelizability. Across sensor positions and activities, our method shows substantial improvements on four of six target datasets, demonstrating its ability to empower a wide range of application scenarios. Further, in the presence of very limited labeled data, our technique significantly outperforms both supervised and self-supervised baselines, positively impacting situations where collecting only a few seconds of labeled data may be possible. This is promising, as CPC does not require specialized data transformations or reconstructions for learning effective representations.

Were you unable to attend Transform 2022? Check out all of the summit sessions in our on-demand library now! In a digital world fueled by a steady influx of data, achieving organizational excellence depends on giving everyone immediate access to accurate, up-to-date information. Organizational-wide communication and collaboration are vital. Mission-critical decisions, in particular, depend on the timely sharing of lessons learned and insights from all departments.

Hear from top leaders discuss topics surrounding AL/ML technology, conversational AI, IVA, NLP, Edge, and more. In a digital world fueled by a steady influx of data, achieving organizational excellence depends on giving everyone immediate access to accurate, up-to-date information. Organizational-wide communication and collaboration are vital. Mission-critical decisions, in particular, depend on the timely sharing of lessons learned and insights from all departments. With new technology based on artificial intelligence (AI) and machine learning (ML), it's easier than ever to share data effectively and consistently.

We are excited to bring Transform 2022 back in-person July 19 and virtually July 20 - 28. Join AI and data leaders for insightful talks and exciting networking opportunities. What if your doctor could instantly test dozens of different treatments to discover the perfect one for your body, your health and your values? In my lab at Stanford University School of Medicine, we are working on artificial intelligence (AI) technology to create a "digital twin": a virtual representation of you based on your medical history, genetic profile, age, ethnicity, and a host of other factors like whether you smoke and how much you exercise. If you're sick, the AI can test out treatment options on this computerized twin, running through countless different scenarios to predict which interventions will be most effective. Instead of choosing a treatment regimen based on what works for the average person, your doctor can develop a plan based on what works for you.

Did you miss a session at the Data Summit? Language models -- AI systems that can be prompted to write essays and emails, answer questions, and more -- remain flawed in many ways. Because they "learn" to write from examples on the web, including problematic social media posts, they're prone to generating misinformation, conspiracy theories, and racist, sexist, or otherwise toxic language. Another major limitation of many of today's language models is that they're "stuck in time," in a sense. Because they're trained once on a large collection of text from the web, their knowledge of the world -- which they gain from that collection -- can quickly become outdated depending on when they were deployed.