The Design and Experimentation of a Differential Grain Moisture Detection Device for a Combined Harvester.

To conveniently implement the online detection of grain moisture in combined harvesters and the address the influence of the no-load measurement baseline, thereby enhancing detection accuracy and measurement continuity, this study developed a differential grain moisture detection device. For its convenient installation and integration on combined harvesters, a single-pole plate measurement element with a 1.6 mm thick epoxy resin coated with a 2-ounce copper film was designed, and a grain moisture detection device was constructed based on the STM32F103 microprocessor (STMicroelectronics International NV, Geneva, Switzerland). To enhance the device's interference resistance, a differential amplification measurement circuit integrated with high-frequency excitation was designed using a reference capacitance. To improve the resolution of the measurement circuit, Malab simulations were conducted at different excitation frequencies, ultimately selecting 30 kHz as the system's excitation signal frequency. To validate the effectiveness of the measurement circuit, validity tests were performed on the constructed sensor, which showed that the sensor's measurement voltage could effectively distinguish the moisture levels in grains, with a determination coefficient (R²) reaching 0.9978. To address the errors in moisture measurement caused by changes in grain temperature, an interaction experiment of the effect of moisture content and temperature on the measurement voltage was conducted using an integrated temperature sensor, resulting in the construction of a moisture content calculation model. Both the indoor static detection and field testing of the moisture detection device were conducted, indicating that the maximum average error in static measurements was 0.3%, with a maximum relative error of 0.47%, and the average relative error in field tests was ≤0.4%.

The Bridge Between Childhood Trauma and Alexithymia Among Adolescents with Depressive and Bipolar Disorders: A Network Bridge Analysis.

Childhood trauma and alexithymia are significant risk factors for adolescent mental health issues. Prior research has linked these factors to psychopathology, but the complexities of their interrelation remain underexplored. This study aims to elucidate the relationship between various forms of childhood trauma and alexithymia in adolescents with depressive and bipolar disorders. Structural Equation Modeling (SEM) and network analysis were utilized on data from 2343 Chinese adolescents (aged 12-18 years, 77.93% female) diagnosed with depression or bipolar disorder. Measures included the Childhood Trauma Questionnaire (CTQ) and the Toronto Alexithymia Scale (TAS-20). SEM demonstrated a significant correlation between childhood trauma and alexithymia. Network analysis identified emotional abuse and difficulty identifying feelings as central nodes. Emotional abuse emerged as a key factor for difficulty in emotional identification among adolescents. This study highlights the need for early intervention and the importance of emotional nurturing in childhood to prevent long-term socioemotional difficulties.

DeeplabV3+-based navigation line extraction for the sunlight robust combine harvester.

Visual navigation is widely used in intelligent combine harvesters, but the existing algorithms do not have sufficiently high accuracy of the visual navigation line recognition under different sunlight conditions. To address this problem, this article proposes a sunlight-robust DeepLabV3+-based navigation line extraction method for combine harvesters. The navigation lines are extracted by constructing a new dataset and predicting the boundaries of the areas that have been and have not been cut. To address the problem that DeeplabV3+ is not sufficient light in the DCNN part, improvement is proposed by incorporating the MobileNetV2 module. In image segmentation, the prediction time is 22.5 ms, and the mean intersection over union (FMIOU) is 0.79. After image segmentation, the navigation lines are drawn using the line segment detection algorithm for the harvester. The proposed method is compared with other mainstream networks, and the prediction results are compared using the line segment detection method. The results show that this method can more quickly identify the navigation lines under different conditions of sunlight with less labeled data than the improved U-Net and DeeplabV3+, which uses Xception as the backbone. Compared to the traditional method and the improved U-Net, this method achieves good results and improves the recognition speed by 27 and 9 ms, respectively.

A dataset of the quality of soybean harvested by mechanization for deep-learning-based monitoring and analysis.

Deep learning and machine vision technology are widely applied to detect the quality of mechanized soybean harvesting. A clean dataset is the foundation for constructing an online detection learning model for the quality of mechanized harvested soybeans. In pursuit of this objective, we established an image dataset for mechanized harvesting of soybeans. The photos were taken on October 9, 2018, at a soybean experimental field of Liangfeng Grain and Cotton Planting Professional Cooperative in Guanyi District, Liangshan, Shandong, China. The dataset contains 40 soybean images of different qualities. By scaling, rotating, flipping, filtering, and adding noise to enhance the data, we expanded the dataset to 800 frames. The dataset consists of three folders, which store images, label maps, and record files for partitioning the dataset into training, validation, and testing sets. In the initial stages, the author devised an online detection model for soybean crushing rate and impurity rate based on machine vision, and research outcomes affirm the efficacy of this dataset. The dataset can help researchers construct a quality prediction model for mechanized harvested soybeans using deep learning techniques.