With the widespread application of wearable sensors in health monitoring and human–computer interaction, deep learning-based human activity recognition (HAR) research faces challenges such as the effective extraction of multi-scale temporal features and the enhancement of robustness against noise in multi-source data. This study proposes the TGA-HAR (TCN-GRU-Attention-HAR) model. The TGA-HAR model integrates Temporal Convolutional Neural Networks and Recurrent Neural Networks by constructing a hierarchical feature abstraction architecture through cascading Temporal Convolutional Network (TCN) and Bidirectional Gated Recurrent Unit (BiGRU) layers for complex activity recognition. This study utilizes TCN layers with dilated convolution kernels to extract multi-order temporal features. This study utilizes BiGRU layers to capture bidirectional temporal contextual correlation information. To further optimize feature representation, the TGA-HAR model introduces residual connections to enhance the stability of gradient propagation and employs an adaptive weighted attention mechanism to strengthen feature representation. The experimental results of this study demonstrate that the model achieved test accuracies of 99.37% on the WISDM dataset, 95.36% on the USC-HAD dataset, and 96.96% on the PAMAP2 dataset. Furthermore, we conducted tests on datasets collected in real-world scenarios. This method provides a highly robust solution for complex human activity recognition tasks.

In recent years, embedded system technologies and products for sensor networks and wearable devices used for monitoring people’s activities and health have become the focus of the global IT industry. In order to enhance the speech recognition capabilities of wearable devices, this article discusses the implementation of audio positioning and enhancement in embedded systems using embedded algorithms for direction detection and mixed source separation. The two algorithms are implemented using different embedded systems: direction detection developed using TI TMS320C6713 DSK and mixed source separation developed using Raspberry Pi 2. For mixed source separation, in the first experiment, the average signal-to-interference ratio (SIR) at 1 m and 2 m distances was 16.72 and 15.76, respectively. In the second experiment, when evaluated using speech recognition, the algorithm improved speech recognition accuracy to 95%.

With the rapid advancement of modern hardware technology, breakthroughs have been made in many areas of artificial intelligence research, leading to the direction of machine replacement or assistance in various fields. However, most artificial intelligence or deep learning techniques require large amounts of training data and are typically applicable to a single task objective. Acquiring such large training datasets can be particularly challenging, especially in domains like medical imaging. In the field of image processing, few-shot image segmentation is an area of active research. Recent studies have employed deep learning and meta-learning approaches to enable models to segment objects in images with only a small amount of training data, allowing them to quickly adapt to new task objectives. This paper proposes a network architecture for meta-learning few-shot image segmentation, utilizing a meta-learning classification weight transfer network to generate masks for few-shot image segmentation. The architecture leverages pre-trained classification weight transfers to generate informative prior masks and employs pre-trained feature extraction architecture for feature extraction of query and support images. Furthermore, it utilizes a Feature Enrichment Module to adaptively propagate information from finer features to coarser features in a top-down manner for query image feature extraction. Finally, a classification module is employed for query image segmentation prediction. Experimental results demonstrate that compared to the baseline using the mean Intersection over Union (mIOU) as the evaluation metric, the accuracy increases by 1.7% in the one-shot experiment and by 2.6% in the five-shot experiment. Thus, compared to the baseline, the proposed architecture with meta-learning classification weight transfer network for mask generation exhibits superior performance in few-shot image segmentation.

The field of autonomous driving has seen continuous advances, yet achieving higher levels of automation in real-world applications remains challenging. A critical requirement for autonomous navigation is accurate map construction, particularly in novel and unstructured environments. In recent years, Simultaneous Localization and Mapping (SLAM) has evolved to support diverse sensor modalities, with some implementations incorporating machine learning to improve performance. However, these approaches often demand substantial computational resources. The key challenge lies in achieving efficiency within resource-constrained environments while minimizing errors that could degrade downstream tasks. This paper presents an enhanced ORB-SLAM2 (Oriented FAST and Rotated BRIEF Simultaneous Localization and Mapping, version 2) algorithm implemented on a Raspberry Pi 3 (ARM A53 CPU) to improve mapping performance under limited computational resources. ORB-SLAM2 comprises four main stages: Tracking, Local Mapping, Loop Closing, and Full Bundle Adjustment (BA). The proposed improvements include employing a more efficient feature descriptor to increase stereo feature-matching rates and optimizing loop-closing parameters to reduce accumulated errors. Experimental results demonstrate that the proposed system achieves notable improvements on the Raspberry Pi 3 platform. For monocular SLAM, RMSE is reduced by 18.11%, mean error by 22.97%, median error by 29.41%, and maximum error by 17.18%. For stereo SLAM, RMSE decreases by 0.30% and mean error by 0.38%. Furthermore, the ROS topic frequency stabilizes at 10 Hz, with quad-core CPU utilization averaging approximately 90%. These results indicate that the system satisfies real-time requirements while maintaining a balanced trade-off between accuracy and computational efficiency under resource constraints.