Complex work activity recognition based on wearable sensors is crucial for streamlining work processes in industrial domains. Unlike basic activities such as walking or running, which involve simple repetitive motions, a complex work activity consists of discrete atomic actions such as an action of spreading a shipping label or cutting tape in a packaging task. In addition, the atomic actions sometimes involve characteristic short-term sensor data patterns. In addition, these actions can be performed in different orders by different workers to achieve similar outcomes, resulting in different long-term sensor data trends for different workers. Because multilayer networks for activity recognition may learn short-term features from shallow-level layers and long-term trends from deeper layers, we propose a new transfer learning method called multilevel knowledge transfer (MLKT), which performs level-wise source selection according to trend similarity across workers in different levels. For example, for training shallow layers, highly similar workers are selected for specific short motions (e.g., pasting a shipping label), and to train the deeper layers, workers with similar cadence are selected. This method also enables the adaptive thresholding of source data selection for each layer level during network training using the proposed adaptive level-wise discerning module.

Unlike human daily activities, existing publicly available sensor datasets for work activity recognition in industrial domains are limited by difficulties in collecting realistic data as close collaboration with industrial sites is required. This also limits research on and development of methods for industrial applications. To address these challenges and contribute to research on machine recognition of work activities in industrial domains, in this study, we introduce a new large-scale dataset for packaging work recognition called OpenPack. OpenPack contains 53.8 hours of multimodal sensor data, including acceleration data, keypoints, depth images, and readings from IoT-enabled devices (e.g., handheld barcode scanners), collected from 16 distinct subjects with different levels of packaging work experience. We apply state-of-the-art human activity recognition techniques to the dataset and provide future directions of complex work activity recognition studies in the pervasive computing community based on the results. We believe that OpenPack will contribute to the sensor-based action/activity recognition community by providing challenging tasks. The OpenPack dataset is available at https://open-pack.github.io.

This seminar introduces recent trends in sensor-based activity recognition technology. Technology to recognize human activities using sensors has been a hot topic in the field of mobile and ubiquitous computing for many years. Recent developments in deep learning and sensor technology have expanded the application of activity recognition to various domains such as industrial and natural science fields. However, because activity recognition in the new domains suffers from various real problems such as the lack of sufficient training data and complexity of target activities, new solutions have been proposed for the practical problems in applying activity recognition to real-world applications in the new domains. In this seminar, we introduce recent topics in activity recognition from the viewpoints of (1) recent trends in state-of-the-art machine learning methods for practical activity recognition, (2) recently focused domains for human activity recognition such as industrial and medical domains and their public datasets, and (3) applications of activity recognition to the natural science field, especially in animal behavior understanding.

This study presents a new method for recognizing complex human activities within the logistics domain, such as packaging operations, using acceleration data from a body-worn sensor. The recognition of packaging tasks using standard supervised machine learning is complex because the observed data vary considerably depending on the number of items to be packed, the size of the items, and other parameters. In this study, we focused on the characteristics and necessary key actions (motions) that occur during a specific operation. For instance, when the packaging tape is stretched while assembling the shipping boxes. To focus on these characteristic actions when recognizing data, we propose the use of an attention-based neural network. With our method, the attention-based neural network’s training is guided such that its focus is on the motifs. In addition, this method was designed to accurately recognize short operations by leveraging data augmentation techniques. We tested our method on two logistics datasets and achieved a 3.9% improvement over the previous MGA-Net approach.

Since ancient times, a hug has been one of the most basic ways to express emotions and has played an important role in building relationships between people. On the other hand, social robots that are designed to provide mental health care to patients have been attracting great attention, and hugging between humans and robots is becoming more and more popular. In this study, we propose a huggable robot that allows intimate interactions between humans and robots. Our robot is based on a tensegrity structure, which is composed of rigid elements connected by springs, and the structure allows the robot to flexibly respond to external force from a hugging interaction, and express various emotions through its movements. In addition, we conducted user experiments and explored an interaction design for the affective movement of the proposed robot. Through the experiments, we confirm that a robot with a tensegrity structure can be used for a hug interaction and it has a large possibility for emotional interaction.

This study presents a new method for recognizing complex human activities in a logistical domain, such as packaging, using acceleration data from a body-worn sensor. Recognition of packaging tasks using standard supervised machine learning is difficult because the observed data vary considerably depending on the number of items to pack, the size of the items, and other parameters. In this study, we focus on characteristic and necessary actions (motions) that occur in a specific operation such as an action of stretching packing tape when assembling shipping boxes. We propose the use of an attention-based neural network to focus on these characteristic actions when recognizing the data. However, training of a such deep network model is a data-intensive process, and obtaining a huge amount of labeled training data in actual industrial settings is difficult. To address this problem, we employ motif-detection algorithms to detect sensor data motifs (segments corresponding to characteristic actions) that can be useful for recognizing operations in advance. Moreover, we propose that the training of the attention-based network should be guided such that it pays attention to the detected motifs, i.e., motif-guided training.

Although deep learning-based activity recognition using wearable sensors has been actively studied to implement smart applications such as supporting elderly care, healthcare, and home automation, techniques for understanding the inside of activity recognition networks have not yet been investigated thoroughly. In the computer vision research field, activation maximization (AM) was proposed to visualize the internal functions of networks. However, when conventional AM techniques, which are tailored to image-based recognition, are directly applied to acceleration-based activity recognition networks, meaningless and noisy signals are generated because of the difficulties in regularizing AM by directly using the values of the acceleration signals that are generated. This study proposes novel regularization techniques for AM using activity recognition networks that leverage activation values used in AM to indirectly control the acceleration signals that are generated. We evaluated the proposed method quantitatively using publicly available datasets and confirmed the effectiveness of the proposed techniques.

Inertial sensor data collected from wearable smart devices such as smartwatches are expected to be used in various smart applications such as video game controllers, hand drawing, hand writing, gestural input devices, human activity recognition, and remote communication using sign language. However, since the maximum sampling rate of inertial sensors in commercial smartwatches is restricted, capturing fine-grained body movements using the low-sampled signals is difficult for these sensors. Therefore, this study proposes a new method for generating high sampling rate signals from the low-sampled signals by upsampling the low-sampled signals using interpolation with an artificial neural network. Because it is impossible to obtain "non-existent" data from low-sampled signals according to the information theory, we estimate these data from experience, i.e., using high-sampled signals prepared in advance for training. This is possible because trajectories of a sensor are restricted by the skeletal structure of the body part to which the sensor is attached.