Unsupervised Domain Adaptation for Mitigating Sensor Variability and Interspecies Heterogeneity in Animal Activity Recognition.

Animal activity recognition (AAR) using wearable sensor data has gained significant attention due to its applications in monitoring and understanding animal behavior. However, two major challenges hinder the development of robust AAR models: domain variability and the difficulty of obtaining labeled datasets. To address this issue, this study intensively investigates the impact of unsupervised domain adaptation (UDA) for AAR. We compared three distinct types of UDA techniques: minimizing divergence-based, adversarial-based, and reconstruction-based approaches. By leveraging UDA, AAR classifiers enable the model to learn domain-invariant features, allowing classifiers trained on the source domain to perform well on the target domain without labels. We evaluated the effectiveness of UDA techniques using dog movement sensor data and additional data from horses. The application of UDA across sensor positions (neck and back), sizes (middle-sized and large-sized), and gender (female and male) within the dog data, as well as across species (dog and horses), exhibits significant improvements in the classification performance and reduced the domain discrepancy. The results highlight the potential of UDA to mitigate the domain shift and enhance AAR in various settings and for different animal species, providing valuable insights for practical applications in real-world scenarios where labeled data is scarce.

An Accurate Deep Learning-Based System for Automatic Pill Identification: Model Development and Validation.

BACKGROUND: Medication errors account for a large proportion of all medical errors. In most homes, patients take a variety of medications for a long period. However, medication errors frequently occur because patients often throw away the containers of their medications. OBJECTIVE: We proposed a deep learning-based system for reducing medication errors by accurately identifying prescription pills. Given the pill images, our system located the pills in the respective pill databases in South Korea and the United States. METHODS: We organized the system into a pill recognition step and pill retrieval step, and we applied deep learning models to train not only images of the pill but also imprinted characters. In the pill recognition step, there are 3 modules that recognize the 3 features of pills and their imprints separately and correct the recognized imprint to fit the actual data. We adopted image classification and text detection models for the feature and imprint recognition modules, respectively. In the imprint correction module, we introduced a language model for the first time in the pill identification system and proposed a novel coordinate encoding technique for effective correction in the language model. We identified pills using similarity scores of pill characteristics with those in the database. RESULTS: We collected the open pill database from South Korea and the United States in May 2022. We used a total of 24,404 pill images in our experiments. The experimental results show that the predicted top-1 candidates achieve accuracy levels of 85.6% (South Korea) and 74.5% (United States) for the types of pills not trained on 2 different databases (South Korea and the United States). Furthermore, the predicted top-1 candidate accuracy of our system was 78% with consumer-granted images, which was achieved by training only 1 image per pill. The results demonstrate that our system could identify and retrieve new pills without additional model updates. Finally, we confirmed through an ablation study that the language model that we emphasized significantly improves the pill identification ability of the system. CONCLUSIONS: Our study proposes the possibility of reducing medical errors by showing that the introduction of artificial intelligence can identify numerous pills with high precision in real time. Our study suggests that the proposed system can reduce patients' misuse of medications and help medical staff focus on higher-level tasks by simplifying time-consuming lower-level tasks such as pill identification.

A Comparative Study on the Influence of Undersampling and Oversampling Techniques for the Classification of Physical Activities Using an Imbalanced Accelerometer Dataset.

Accelerometer data collected from wearable devices have recently been used to monitor physical activities (PAs) in daily life. While the intensity of PAs can be distinguished with a cut-off approach, it is important to discriminate different behaviors with similar accelerometry patterns to estimate energy expenditure. We aim to overcome the data imbalance problem that negatively affects machine learning-based PA classification by extracting well-defined features and applying undersampling and oversampling methods. We extracted various temporal, spectral, and nonlinear features from wrist-, hip-, and ankle-worn accelerometer data. Then, the influences of undersampilng and oversampling were compared using various ML and DL approaches. Among various ML and DL models, ensemble methods including random forest (RF) and adaptive boosting (AdaBoost) exhibited great performance in differentiating sedentary behavior (driving) and three walking types (walking on level ground, ascending stairs, and descending stairs) even in a cross-subject paradigm. The undersampling approach, which has a low computational cost, exhibited classification results unbiased to the majority class. In addition, we found that RF could automatically select relevant features for PA classification depending on the sensor location by examining the importance of each node in multiple decision trees (DTs). This study proposes that ensemble learning using well-defined feature sets combined with the undersampling approach is robust for imbalanced datasets in PA classification. This approach will be useful for PA classification in the free-living situation, where data imbalance problems between classes are common.

Deep Convolutional Gated Recurrent Unit Combined with Attention Mechanism to Classify Pre-Ictal from Interictal EEG with Minimized Number of Channels.

The early prediction of epileptic seizures is important to provide appropriate treatment because it can notify clinicians in advance. Various EEG-based machine learning techniques have been used for automatic seizure classification based on subject-specific paradigms. However, because subject-specific models tend to perform poorly on new patient data, a generalized model with a cross-patient paradigm is necessary for building a robust seizure diagnosis system. In this study, we proposed a generalized model that combines one-dimensional convolutional layers (1D CNN), gated recurrent unit (GRU) layers, and attention mechanisms to classify preictal and interictal phases. When we trained this model with ten minutes of preictal data, the average accuracy over eight patients was 82.86%, with 80% sensitivity and 85.5% precision, outperforming other state-of-the-art models. In addition, we proposed a novel application of attention mechanisms for channel selection. The personalized model using three channels with the highest attention score from the generalized model performed better than when using the smallest attention score. Based on these results, we proposed a model for generalized seizure predictors and a seizure-monitoring system with a minimized number of EEG channels.

In-Ear EEG Based Attention State Classification Using Echo State Network.

It is important to maintain attention when carrying out significant daily-life tasks that require high levels of safety and efficiency. Since degradation of attention can sometimes have dire consequences, various brain activity measurement devices such as electroencephalography (EEG) systems have been used to monitor attention states in individuals. However, conventional EEG instruments have limited utility in daily life because they are uncomfortable to wear. Thus, this study was designed to investigate the possibility of discriminating between the attentive and resting states using in-ear EEG signals for potential application via portable, convenient earphone-shaped EEG instruments. We recorded both on-scalp and in-ear EEG signals from 6 subjects in a state of attentiveness during the performance of a visual vigilance task. We have designed and developed in-ear EEG electrodes customized by modelling both the left and right ear canals of the subjects. We use an echo state network (ESN), a powerful type of machine learning algorithm, to discriminate attention states on the basis of in-ear EEGs. We have found that the maximum average accuracy of the ESN method in discriminating between attentive and resting states is approximately 81.16% with optimal network parameters. This study suggests that portable in-ear EEG devices and an ESN can be used to monitor attention states during significant tasks to enhance safety and efficiency.