Domestic trash detection is an essential technology toward achieving a smart city. Due to the complexity and variability of urban trash scenarios, the existing trash detection algorithms suffer from low detection rates and high false positives, as well as the general problem of slow speed in industrial applications. This paper proposes an i-YOLOX model for domestic trash detection based on deep learning algorithms. First, a large number of real-life trash images are collected into a new trash image dataset. Second, the lightweight operator involution is incorporated into the feature extraction structure of the algorithm, which allows the feature extraction layer to establish long-distance feature relationships and adaptively extract channel features. In addition, the ability of the model to distinguish similar trash features is strengthened by adding the convolutional block attention module (CBAM) to the enhanced feature extraction network. Finally, the design of the involution residual head structure in the detection head reduces the gradient disappearance and accelerates the convergence of the model loss values allowing the model to perform better classification and regression of the acquired feature layers. In this study, YOLOX-S is chosen as the baseline for each enhancement experiment. The experimental results show that compared with the baseline algorithm, the mean average precision (mAP) of i-YOLOX is improved by 1.47%, the number of parameters is reduced by 23.3%, and the FPS is improved by 40.4%. In practical applications, this improved model achieves accurate recognition of trash in natural scenes, which further validates the generalization performance of i-YOLOX and provides a reference for future domestic trash detection research.

Underwater object detection is crucial in marine exploration, presenting a challenging problem in computer vision due to factors like light attenuation, scattering, and background interference. Existing underwater object detection models face challenges such as low robustness, extensive computation of model parameters, and a high false detection rate. To address these challenges, this paper proposes a lightweight underwater object detection method integrating deep learning and image enhancement. Firstly, FUnIE-GAN is employed to perform data enhancement to restore the authentic colors of underwater images, and subsequently, the restored images are fed into an enhanced object detection network named YOLOv7-GN proposed in this paper. Secondly, a lightweight higher-order attention layer aggregation network (ACC3-ELAN) is designed to improve the fusion perception of higher-order features in the backbone network. Moreover, the head network is enhanced by leveraging the interaction of multi-scale higher-order information, additionally fusing higher-order semantic information from features at different scales. To further streamline the entire network, we also introduce the AC-ELAN-t module, which is derived from pruning based on ACC3-ELAN. Finally, the algorithm undergoes practical testing on a biomimetic sea flatworm underwater robot. The experimental results on the DUO dataset show that our proposed method improves the performance of object detection in underwater environments. It provides a valuable reference for realizing object detection in underwater embedded devices with great practical potential.

Passion fruit, renowned for its significant nutritional, medicinal, and economic value, is extensively cultivated in subtropical regions such as China, India, and Vietnam. In the production and processing industry, the quality grading of passion fruit plays a crucial role in the supply chain. However, the current process relies heavily on manual labor, resulting in inefficiency and high costs, which reflects the importance of expanding the application of fruit appearance quality classification mechanisms based on computer vision. Moreover, the existing passion fruit detection algorithms mainly focus on real-time detection and overlook the quality-classification aspect. This paper proposes the ATC-YOLOv5 model based on deep learning for passion fruit detection and quality classification. First, an improved Asymptotic Feature Pyramid Network (APFN) is utilized as the feature-extraction network, which is the network modified in this study by adding weighted feature concat pathways. This optimization enhances the feature flow between different levels and nodes, allowing for the adaptive and asymptotic fusion of richer feature information related to passion fruit quality. Secondly, the Transformer Cross Stage Partial (TRCSP) layer is constructed based on the introduction of the Multi-Head Self-Attention (MHSA) layer in the Cross Stage Partial (CSP) layer, enabling the network to achieve a better performance in modeling long-range dependencies. In addition, the Coordinate Attention (CA) mechanism is introduced to enhance the network’s learning capacity for both local and non-local information, as well as the fine-grained features of passion fruit. Moreover, to validate the performance of the proposed model, a self-made passion fruit dataset is constructed to classify passion fruit into four quality grades. The original YOLOv5 serves as the baseline model. According to the experimental results, the mean average precision (mAP) of ATC-YOLOv5 reaches 95.36%, and the mean detection time (mDT) is 3.2 ms, which improves the mAP by 4.83% and the detection speed by 11.1%, and the number of parameters is reduced by 10.54% compared to the baseline, maintaining the lightweight characteristics while improving the accuracy. These experimental results validate the high detection efficiency of the proposed model for fruit quality classification, contributing to the realization of intelligent agriculture and fruit industries.

Sensor-based human activity recognition (HAR) plays a fundamental role in various mobile application scenarios, but the model performance of HAR heavily relies on the richness of the dataset and the completeness of data annotation. To address the shortage of comprehensive activity types in collected datasets, we adopt the domain adaptation technique with a graph neural network-based approach by incorporating an adaptive learning mechanism to enhance the action recognition model’s generalization ability, especially when faced with limited sample sizes. To evaluate the effectiveness of our proposed approach, we conducted experiments using three well-known datasets: MHealth, PAMAP2, and TNDA. The experimental results demonstrate the efficacy of our approach in sensor-based HAR tasks, achieving impressive average accuracies of 98.88%, 98.58%, and 97.78% based on the respective datasets. Furthermore, we conducted transfer learning experiments to address the domain adaptation problem. These experiments revealed that our proposed model exhibits exceptional transferability and distinguishing ability, even in scenarios with limited available samples. Thus, our approach offers a practical and viable solution for sensor-based HAR tasks.

Wire electrical discharge machining (WEDM), widely used to fabricate micro and precision parts in manufacturing industry, is a nontraditional machining method using discharge energy which is transformed into thermal energy to efficiently remove materials. A great amount of research has been conducted based on pulse characteristics. However, the spark image-based approach has little research reported. This paper proposes a discharge spark image-based approach. A model is introduced to predict the discharge status using spark image features through a synchronous high-speed image and waveform acquisition system. First, the relationship between the spark image features (e.g., area, energy, energy density, distribution, etc.) and discharge status is explored by a set of experiments). Traditional methods have claimed that pulse waveform of “short” status is related to the status of non-machining while through our research, it is concluded that this is not always true by conducting experiments based on the spark images. Second, a deep learning model based on Convolution neural network (CNN) and Gated recurrent unit (GRU) is proposed to predict the discharge status. A time series of spark image features extracted by CNN form a 3D feature space is used to predict the discharge status through GRU. Moreover, a quantitative labeling method of machining state is proposed to improve the stability of the model. Due the effective features and the quantitative labeling method, the proposed approach achieves better predict result comparing with the single GRU model.