In this paper, a novel flower detection application anchor-based method is proposed, which is combined with an attention mechanism to detect the flowers in a smart garden in AIoT more accurately and fast. While many researchers have paid much attention to the flower classification in existing studies, the issue of flower detection has been largely overlooked. The problem we have outlined deals largely with the study of a new design and application of flower detection. Firstly, a new end-to-end flower detection anchor-based method is inserted into the architecture of the network to make it more precious and fast and the loss function and attention mechanism are introduced into our model to suppress unimportant features. Secondly, our flower detection algorithms can be integrated into the mobile device. It is revealed that our flower detection method is very considerable through a series of investigations carried out. The detection accuracy of our method is similar to that of the state-of-the-art, and the detection speed is faster at the same time. It makes a major contribution to flower detection in computer vision.

Portable/Wearable (P/W) electroencephalography (EEG) devices capture and analyze EEG signals, which are widely used in different research fields, such as consumer psychology prediction, attention and fatigue monitoring. Nonetheless, EEG signals obtained through P/W devices are sensitive to environmental conditions and physiological activities, rendering real-time denoising a challenge on computation and memory limited consumer electronics (CE). In this work, we propose a lightweight network of P/W devices for real-time EEG signal denoising (LTDNet-EEG). Specifically, LTDNet-EEG performs automatic linearized modeling of nonlinear EEG signals via Taylor series expansion, then utilizes a Kalman smoothing filter to remove noise from EEG signals and designs a lightweight network based on depthwise separable convolution (DSC) to update Kalman gain and other parameters. Besides, it applies data layout and common subexpression elimination to optimize model structure and code computation respectively. Experiments on the benchmark EEGdenoiseNet database show that LTDNet-EEG outperforms the existing state-of-the-art algorithm. Additionally, the LTDNet-EEG can be effectively implemented on the hardware platform equipped with a 4th generation Raspberry Pi (4GB RAM, 16GB Flash). Compared to training and reasoning on CPU, the LTDNet-EEG with optimized approaches achieves approximately a 2.5-fold reduction in execution time which has great potential widely to be used in CE.

In this paper, a novel deep learning method Mamba-RAYOLO is presented, which can improve detection and classification in the processing and analysis of ECG images in real time by integrating three advanced modules. The feature extraction module in our work with a multi-branch structure during training can capture a wide range of features to ensure efficient inference and rich feature extraction. The attention mechanism module utilized in our proposed network can dynamically focus on the most relevant spatial and channel-wise features to improve detection accuracy and computational efficiency. Then, the extracted features can be refined for efficient spatial feature processing and robust feature fusion. Several sets of experiments have been carried out to test the validity of the proposed Mamba-RAYOLO and these indicate that our method has made significant improvements in the detection and classification of ECG images. The research offers a promising framework for more accurate and efficient medical ECG diagnostics.

This study aims to leverage the advanced capabilities of quantum computing to construct an efficient framework for processing large-scale health data, uncover potential higher-order correlations in medicine, and enhance the accuracy of smart healthcare diagnosis and treatment. A data processing framework is developed using quantum annealing algorithms and quantum circuits. We call it the quantum medical data simulation computational model (Q-MDSC). A unique encoding method based on quantum bits is employed for health data features, such as encoding symptom information from electronic health records into different quantum bits and representing different alleles of genetic data through superposition states of quantum bits. The properties of quantum entanglement are utilized to relate different data types, and quantum parallelism is harnessed to process multiple data combinations simultaneously. Additionally, this quantum computing framework is compared with traditional data mining methods using the same datasets, which include the Cochrane Systematic Review Database (https://www.cochranelibrary.com), the BioASQ Dataset (https://participants-area.bioasq.org), the PubMed Central Dataset (https://www.ncbi.nlm.nih.gov/pmc), and the Cancer Genome Atlas (TCGA) (https://portal.gdc.cancer.gov). The datasets are divided into training and testing sets in a 7:3 ratio during the experiments. Tests are conducted on association mining tasks of varying data scales and complexities, ranging from simple symptom-disease associations to complex gene-symptom-disease higher-order associations. The results indicate that, when processing large-scale data, the quantum computing framework improves overall computational speed by approximately 45% compared to traditional algorithms. Regarding uncovering higher-order correlations, the quantum computing framework enhances accuracy by about 30% relative to traditional algorithms. For early disease prediction, the accuracy achieved with the new framework is approximately 25% higher than that of conventional methods. Furthermore, for personalized treatment plan matching, the matching accuracy of the quantum computing framework surpasses traditional approaches by about 35%. These findings demonstrate the significant potential of the quantum computing-based smart healthcare framework for processing large-scale health data in the context of higher-order correlation mining, paving new pathways for the development of smart healthcare. This study utilizes multiple public datasets to achieve breakthroughs in computational speed, higher-order correlation mining, early disease prediction, and personalized treatment plan matching, thus opening new avenues for advancing smart healthcare.

In this paper, a novel visual image real‐time detection LSE‐Yolo neural network is presented, which is in artificial intelligence‐based Internet of Things for smart cites and smart homes. Despite the great achievements that have been acquired in image detection, the issue of visual image real‐time detection combined with privacy data protection to serve for smart cities and smart homes has been overlooked. The technique we applied in our study is referred to as visual object detection, which can contribute to more healthy and comfortable life. When several studies have been carried out to test the validity, it is suggested that our proposed LSE‐Yolo neural network has better performance in image real‐time detection based on AIoT for smart cities and smart homes. And it is similar to state‐of‐the‐art. The fruitful work has made great contributions to our present understanding of the visual image detection serving for smart cities and smart homes.