Deep learning models have shown excellent performance in human activity recognition tasks. However, these models typically require large amounts of computational resources, which makes them inefficient to deploy on edge devices. Furthermore, the superior performance of deep learning models relies heavily on the availability of large datasets to avoid over-fitting. However, the expensive efforts for labeling limits the amount of datasets. We address both challenges by designing a more lightweight model, called TinyHAR. TinyHAR is designed specifically for human activity recognition employing different saliency of multi modalities, multimodal collaboration, and temporal information extraction. Initial experimental results show that TinyHAR is several times smaller and often meets or even surpasses the performance of DeepConvLSTM, a state-of-the-art human activity recognition model.

Background: Classifying breast cancer subtypes is crucial for clinical diagnosis and treatment. However, the early symptoms of breast cancer may not be apparent. Rapid advances in high-throughput sequencing technology have led to generating large number of multi-omics biological data. Leveraging and integrating the available multi-omics data can effectively enhance the accuracy of identifying breast cancer subtypes. However, few efforts focus on identifying the associations of different omics data to predict the breast cancer subtypes.Results: In this paper, we propose a differential sparse canonical correlation analysis network (DSCCN) for classifying the breast cancer subtypes. DSCCN performs differential analysis on multi-omics expression data to identify differentially expressed (DE) genes and adopts sparse canonical correlation analysis (SCCA) to mine highly correlated features between multi-omics DE-genes. Meanwhile, DSCCN uses multi-task deep learning neural network separately to train the correlated DE-genes to predict breast cancer subtypes, which spontaneously tackle the data heterogeneity problem in integrating multi-omics data.Conclusions: The experimental results show that by mining the associations among multi-omics data, DSCCN is more capable of accurately classifying breast cancer subtypes than the existing methods.

Sensor-based HAR models face challenges in cross-subject generalization due to the complexities of data collection and annotation, impacting the size and representativeness of datasets. While data augmentation has been successfully employed in domains like natural language and image processing, its application in HAR remains underexplored. This study presents AutoAugHAR, an innovative two-stage gradient-based data augmentation optimization framework. AutoAugHAR is designed to take into account the unique attributes of candidate augmentation operations and the unique nature and challenges of HAR tasks. Notably, it optimizes the augmentation pipeline during HAR model training without substantially extending the training duration. In evaluations on eight inertial-measurement-units-based benchmark datasets using five HAR models, AutoAugHAR has demonstrated superior robustness and effectiveness compared to other leading data augmentation frameworks. A salient feature of AutoAugHAR is its model-agnostic design, allowing for its seamless integration with any HAR model without the need for structural modifications. Furthermore, we also demonstrate the generalizability and flexible extensibility of AutoAugHAR on four datasets from other adjacent domains. We strongly recommend its integration as a standard protocol in HAR model training and will release it as an open-source tool1.

A fundamental computational problem in metabolic engineering is to find pathways between compounds. Pathfinding methods using atom tracking have been widely used to find biochemically relevant pathways. However, these methods require the user to define the atoms to be tracked. This may lead to failing to predict the pathways that do not conserve the user-defined atoms. In this work, we propose a pathfinding method called AGPathFinder to find biochemically relevant metabolic pathways between two given compounds. In AGPathFinder, we find alternative pathways by tracking the movement of atomic groups through metabolic networks and use combined information of reaction thermodynamics and compound similarity to guide the search towards more feasible pathways and better performance. The experimental results show that atomic group tracking enables our method to find pathways without the need of defining the atoms to be tracked, avoid hub metabolites, and obtain biochemically meaningful pathways. Our results also demonstrate that atomic group tracking, when incorporated with combined information of reaction thermodynamics and compound similarity, improves the quality of the found pathways. In most cases, the average compound inclusion accuracy and reaction inclusion accuracy for the top resulting pathways of our method are around 0.90 and 0.70, respectively, which are better than those of the existing methods. Additionally, AGPathFinder provides the information of thermodynamic feasibility and compound similarity for the resulting pathways.

Passive Haptic Learning (PHL) is a method by which users are able to learn motor skills without paying active attention. In past research, vibration is widely applied in PHL as the signal delivered on the participant's skin. The human somatosensory system provides not only discriminative input (the perception of pressure, vibration, slip, and texture, etc.) to the brain but also an affective input (sliding, tapping and stroking, etc.). The former is often described as being mediated by low-threshold mechanosensitive (LTM) units with rapidly conducting large myelinated (Aᵬ) afferents, while the latter is mediated by a class of LTM afferents called C-tactile afferents (CTs). We investigated whether different tactile sensations (tapping, light stroking, and vibration) influence the learning effect of PHL in this work. We built three wearable systems corresponding to the three sensations respectively. 17 participants were invited to learn to play three different note sequences passively via three different systems. The subjects were then tested on their remembered note sequences after each learning session. Our results indicate that the sensations of tapping or stroking are as effective as the vibration system in passive haptic learning of piano songs, providing viable alternatives to the vibration sensations that have been used so far. We also found that participants on average made up to 1.06 errors less when using affective inputs, namely tapping or stroking. As the first work exploring the differences in multiple types of tactile sensations in PHL, we offer our design to the readers and hope they may employ our works for further research of PHL.

Neural network models have demonstrated exceptional performance in wearable human activity recognition (HAR) tasks. However, the increasing size or complexity of HAR models significantly impacts their deployment on wearable devices with limited computational power. In this study, we introduce a novel HAR model architecture named Multi-Layer Perceptron-HAR (MLP-HAR), which contains solely fully connected layers. This model is specifically designed to address the unique characteristics of HAR tasks, such as multi-modality interaction and global temporal information. The MLP-HAR model employs fully connected layers that alternately operate along the modality and temporal dimensions, enabling multiple fusions of information across these dimensions. Our proposed model demonstrates comparable performance with other state-of-the-art HAR models on six open-source datasets, while utilizing significantly fewer learnable parameters and exhibiting lower model complexity. Specifically, the complexity of our model is at least ten times smaller than that of the TinyHAR model and several hundred times smaller than the benchmark model DeepConvLSTM. Additionally, due to its purely fully connected layer-based architecture, MLP-HAR offers the advantage of ease of deployment. To substantiate these claims, we report the inference time performance of MLP-HAR on the Samsung Galaxy Watch 5 PRO and the Arduino Portenta H7 LITE, comparing it against other state-of-the-art HAR models.