This study focuses on enhancing the intelligence level of assisted living robots to meet the needs of older adults with disabilities. The goal is to achieve efficient multitarget detection of everyday objects and to improve the accuracy and recall of the detection algorithm. To this end, an improved YOLOv8 algorithm (YOLOv8 - CBW3) is proposed. First, the GAM global attention mechanism is embedded in the backbone network of YOLOv8 to improve the sensitivity of the backbone network to the important feature information and reduce the attention to the irrelevant features, and it is determined that the GAM global attention mechanism will be embedded in the backbone network of YOLOv8 after comparing and analyzing the GAM with the attention mechanisms of CBAM, SE, and ECA; second, at the neck layer, the original PAN-FPN network structure is replaced with the BiFPN structure at the neck layer to realize bidirectional cross-scale connectivity and weighted feature fusion. In addition, a small-target detection layer is added to the original YOLOv8 model to enhance the detection capability for small-scale targets. Finally, the WIoUv3 loss is used instead of the CIoU loss as the localization regression loss function, which reduces the influence of low-quality anchor frames and enhances the model's focus on global information, thus improving the accuracy of target object detection. After 300 rounds of testing on 3000 data samples, the YOLOv8 - CBW3 algorithm achieves a detection accuracy of 95.11%, a recall of 94.60%, and an average precision of 95.23%, which are improvements of 2.78% and 3.72% in accuracy and recall, respectively, compared with YOLOv8n. A comparison with other popular models shows that YOLOv8 - CBW3 has strong generalizability, localization performance, detection ability and robustness. To verify that YOLOv8-CBW3 has strong generalizability, a comparative analysis is conducted on the VOC2007 public dataset, which shows through the data that its detection ability is still optimal, and it provides a reference solution for subsequent similar problems.

Mobility robots for elderly care not only satisfy the basic needs of disabled seniors but also help ensure their safety. Safety monitoring is particularly critical when disabled seniors remain alone indoors. This research focuses on detecting flame and smoke targets in indoor environments, enabling faster decision-making during fires, facilitating timely evacuation for disabled seniors, and thereby providing improved protection. This study aims to enhance detection accuracy and algorithm performance by introducing the improved YOLO11-BSCS model. The Biformer two-layer routing attention mechanism is incorporated into the Backbone and Neck of YOLO11s, replacing the original C2SPA module with C2SPA_Biformer to enable dynamic, query-aware sparse attention, reduce the number of model parameters, and improve the detection of dynamic targets. The SCConv convolution replaces the C3k2 convolution module in the original model with the C3k2_SCConv module, reducing spatial and channel redundancy during the fusion of image features extracted by the model and increasing detection speed. The loss function of the model was optimized by replacing CIoU-Loss with the SIoU-Loss module. This modification improves both convergence speed and detection accuracy. Through 600 rounds of experimental testing on 5,000 data samples, supplemented by three independent training runs using random seeds (107,325,592) for evaluation, YOLO11-BSCS achieved 94.612% accuracy, 89.678% recall, and 90.319% average precision—representing improvements of 4.934, 7.452, and 5.184%, respectively, over YOLO11s. Comparative analysis with widely used models indicates that YOLO11-BSCS provides strong generalizability, precise localization, robust detection, and overall superior performance. The necessity of each model enhancement was validated through ablation experiments, confirming that all modifications contributed meaningfully to performance improvements. These findings provide a valuable reference for addressing similar challenges in object detection.

In natural language understanding, intent recognition plays a central role in human–computer interaction. However, in elderly-care scenarios, acoustic signals are often affected by atypical speech patterns, slower speaking rates, and environmental noise, making audio information less reliable and reducing the effectiveness of conventional text–audio fusion methods. To address this problem, we propose a prompt-guided and quality-aware text–audio intent recognition framework. Specifically, a χ²-based intent prototype soft prompt is introduced to enhance the semantic representation of text. Then, a residual-free text-guided cross-attention module is designed to refine degraded acoustic features using textual semantics as reliable guidance. In addition, a dynamic fusion gate is developed to adjust the contributions of text and audio based on modality reliability and intent-related information. Experiments on the MIntRec dataset with simulated acoustic degradation show that the proposed model achieves 60.90% accuracy, 60.80% weighted F1, and 57.90% macro-F1, outperforming several competitive baselines. These results indicate that the proposed framework can improve the robustness of intent recognition under challenging acoustic conditions in elderly-oriented interaction scenarios.