Machine learning enables electrical resistivity modeling of printed lines in aerosol jet 3D printing.

Among various non-contact direct ink writing techniques, aerosol jet printing (AJP) stands out due to its distinct advantages, including a more adaptable working distance (2-5 mm) and higher resolution (~ 10 µm). These characteristics make AJP a promising technology for the precise customization of intricate electrical functional devices. However, complex interactions among the machine, process, and materials result in low controllability over the electrical performance of printed lines. This significantly affects the functionality of printed components, thereby limiting the broad applications of AJP. Therefore, a systematic machine learning approach that integrates experimental design, geometrical features extraction, and non-parametric modeling is proposed to achieve printing quality optimization and electrical resistivity prediction for the printed lines in AJP. Specifically, three classical convolutional neural networks (CNNs) architectures are compared for extracting representative features of printed lines, and an optimal operating window is identified to effectively discriminate better line morphology from inferior printed line patterns within the design space. Subsequently, three representative non-parametric machine learning techniques are employed for resistivity modeling. Following that, the modeling performances of the adopted machine learning methods were systematically compared based on four conventional evaluation metrics. Together, these aspects contribute to optimizing the printed line morphology, while simultaneously identifying the optimal resistivity model for accurate predictions in AJP.

Long-Term Straw Incorporation under Controlled Irrigation Improves Soil Quality of Paddy Field and Rice Yield in Northeast China.

Soil quality is an indicator of the ability to ensure ecological security and sustainable soil usage. The effects of long-term straw incorporation and different irrigation regimes on the yield and soil quality of paddy fields in cold regions remain unclear. This study established four treatments: controlled irrigation + continuous straw incorporation for 3 years (C3), controlled irrigation + continuous straw incorporation for 7 years (C7), flooded irrigation + continuous straw incorporation for 3 years (F3), and flooded irrigation + continuous straw incorporation for 7 years (F7). Analysis was conducted on the impact of various irrigation regimes and straw incorporation years on the physicochemical characteristics and quality of the soil. The soil quality index (SQI) for rice fields was computed using separate datasets for each treatment. The soil nitrate nitrogen, available phosphorus, soil organic carbon, and soil organic matter contents of the C7 were 93.51%, 5.80%, 8.90%, and 8.26% higher compared to C3, respectively. In addition, the yield of the C7 treatment was 5.18%, 4.89%, and 10.32% higher than those of F3, C3, and F7, respectively. The validity of the minimum data set (MDS) was verified by correlation, Ef and ER, which indicated that the MDS of all treatments were able to provide a valid evaluation of soil quality. The MDS based SQI of C7 was 11.05%, 11.97%, and 27.71% higher than that of F3, C3, and F7, respectively. Overall, long-term straw incorporation combined with controlled irrigation increases yield and soil quality in paddy fields in cold regions. This study provides a thorough assessment of soil quality concerning irrigation regimes and straw incorporation years to preserve food security and the sustainability of agricultural output. Additionally, it offers a basis for soil quality diagnosis of paddy fields in the Northeast China.

Self-Catalyzed Growth of Co4N and N-Doped Carbon Nanotubes toward Bifunctional Cathode for Highly Safe and Flexible Li-Air Batteries.

The practical application of high-energy density lithium-oxygen (Li-O2) batteries is severely impeded by the notorious cycling stability and safety, which mainly comes from slow kinetics of oxygen reduction reaction (ORR) and oxygen evolution reaction (OER) at cathodes, causing inferior redox overpotentials and reactive lithium metal in flammable liquid electrolyte. Herein, a bifunctional electrode, a safe gel polymer electrolyte (GPE), and a robust lithium anode are proposed to alleviate above problems. The bifunctional electrode is composed of N-doped carbon nanotubes (N-CNTs) and Co4N by in situ chemical vapor deposition self-catalyzed growth on carbon cloth (N-CNTs@Co4N@CC). The self-supporting, binder-free N-CNTs@Co4N@CC electrode has a strong and stable three-dimensional (3D) interconnected conductive structure, which provides interconnectivity between the active sites and the electrode to promote the transfer of electrons. Furthermore, the N-CNT-intertwined Co4N ensures efficient catalytic activity. Hence, the electrode demonstrates improved electrochemical properties even under a large current density (2000 mA g-1) and long cycling operation (250 cycles). Moreover, a highly safe and flexible rechargeable cell using the 3D N-CNTs@Co4N@CC electrode, GPE, and robust lithium anode design has been explored. The open circuit voltage is stable at ∼3.0 V even after 9800 cycles, which proves the mechanical durability of the integrated GPE cell. The stable cable-type Li-air battery was demonstrated to stably drive the light-emitting diodes (LEDs), highlighting the reliability for practical use.

Advantages of transformer and its application for medical image segmentation: a survey.

PURPOSE: Convolution operator-based neural networks have shown great success in medical image segmentation over the past decade. The U-shaped network with a codec structure is one of the most widely used models. Transformer, a technology used in natural language processing, can capture long-distance dependencies and has been applied in Vision Transformer to achieve state-of-the-art performance on image classification tasks. Recently, researchers have extended transformer to medical image segmentation tasks, resulting in good models. METHODS: This review comprises publications selected through a Web of Science search. We focused on papers published since 2018 that applied the transformer architecture to medical image segmentation. We conducted a systematic analysis of these studies and summarized the results. RESULTS: To better comprehend the benefits of convolutional neural networks and transformers, the construction of the codec and transformer modules is first explained. Second, the medical image segmentation model based on transformer is summarized. The typically used assessment markers for medical image segmentation tasks are then listed. Finally, a large number of medical segmentation datasets are described. CONCLUSION: Even if there is a pure transformer model without any convolution operator, the sample size of medical picture segmentation still restricts the growth of the transformer, even though it can be relieved by a pretraining model. More often than not, researchers are still designing models using transformer and convolution operators.

Characteristics of Oil-in-Oil Emulsions under AC Electric Fields.

Emulsions have been applied in a number of industries such as pharmaceutics, cosmetics, and food, which are also of great scientific interest. Although aqueous emulsions are commonly used in our daily life, oil-in-oil (o/o) emulsions also play an irreplaceable role in view of their unique physics and complementary applications. In this paper, we investigate typical behaviors of organic droplets surrounded by organic medium (o/o emulsions) with different functional groups controlled by the AC electric field. Droplet behaviors can be catalogued into five types: namely, "no effect", "movement", "deformation", "interface rupture", and "disorder". We identify the key dimensionless number Wee·Ca, combined with the channel geometry, for characterizing the typical behaviors in silicon oil/1,6-hexanediol diacrylate and mineral oil/1,6-hexanediol diacrylate emulsions. Unlike aqueous emulsion, the Maxwell-Wagner relaxation inhibits the electric effect and leads to an effective frequency, ranging from 0.5 to 3 kHz. The increasing viscosity of the droplet facilitates the escalation by promoting the shearing effect under the same flow conditions. Ethylene glycol droplets primarily show the efficient coalescence even at a low Wee·Ca, which is attributed to the attraction of free charges induced by the increasing conductivity. In 1,6-hexanediol diacrylate/silicon oil emulsion, the droplet tends to form a liquid film that expands into the entire channel due to the affinity of the droplet to the channel wall. A variety of elongated columns are observed to oscillate between the electrodes at high voltages. These findings can contribute to understanding the electrohydrodynamic physics in o/o emulsion and controlling droplet behaviors in a fast response, programmable, and high-throughput way. We expect that this droplet manipulation technology can be widely adopted in a broad range of chemical synthesis and biological and material science.

Pan-genome Analysis of WOX Gene Family and Function Exploration of CsWOX9 in Cucumber.

Cucumber is an economically important vegetable crop, and the warts (composed of spines and Tubercules) of cucumber fruit are an important quality trait that influences its commercial value. WOX transcription factors are known to have pivotal roles in regulating various aspects of plant growth and development, but their studies in cucumber are limited. Here, genome-wide identification of cucumber WOX genes was performed using the pan-genome analysis of 12 cucumber varieties. Our findings revealed diverse CsWOX genes in different cucumber varieties, with variations observed in protein sequences and lengths, gene structure, and conserved protein domains, possibly resulting from the divergent evolution of CsWOX genes as they adapt to diverse cultivation and environmental conditions. Expression profiles of the CsWOX genes demonstrated that CsWOX9 was significantly expressed in unexpanded ovaries, especially in the epidermis. Additionally, analysis of the CsWOX9 promoter revealed two binding sites for the C2H2 zinc finger protein. We successfully executed a yeast one-hybrid assay (Y1H) and a dual-luciferase (LUC) transaction assay to demonstrate that CsWOX9 can be transcriptionally activated by the C2H2 zinc finger protein Tu, which is crucial for fruit Tubercule formation in cucumber. Overall, our results indicated that CsWOX9 is a key component of the molecular network that regulates wart formation in cucumber fruits, and provide further insight into the function of CsWOX genes in cucumber.

Multi-domain feature joint optimization based on multi-view learning for improving the EEG decoding.

Background: Brain-computer interface (BCI) systems based on motor imagery (MI) have been widely used in neurorehabilitation. Feature extraction applied by the common spatial pattern (CSP) is very popular in MI classification. The effectiveness of CSP is highly affected by the frequency band and time window of electroencephalogram (EEG) segments and channels selected. Objective: In this study, the multi-domain feature joint optimization (MDFJO) based on the multi-view learning method is proposed, which aims to select the discriminative features enhancing the classification performance. Method: The channel patterns are divided using the Fisher discriminant criterion (FDC). Furthermore, the raw EEG is intercepted for multiple sub-bands and time interval signals. The high-dimensional features are constructed by extracting features from CSP on each EEG segment. Specifically, the multi-view learning method is used to select the optimal features, and the proposed feature sparsification strategy on the time level is proposed to further refine the optimal features. Results: Two public EEG datasets are employed to validate the proposed MDFJO method. The average classification accuracy of the MDFJO in Data 1 and Data 2 is 88.29 and 87.21%, respectively. The classification result of MDFJO was significantly better than MSO (p < 0.05), FBCSP32 (p < 0.01), and other competing methods (p < 0.001). Conclusion: Compared with the CSP, sparse filter band common spatial pattern (SFBCSP), and filter bank common spatial pattern (FBCSP) methods with channel numbers 16, 32 and all channels as well as MSO, the MDFJO significantly improves the test accuracy. The feature sparsification strategy proposed in this article can effectively enhance classification accuracy. The proposed method could improve the practicability and effectiveness of the BCI system.

[Grain yield estimation of wheat-maize rotation cultivated land based on Sentinel-2 multi-spectral image: A case study in Caoxian County, Shandong, China]. / 基于Sentinel-2å¤šå ‰è°±å½±åƒçš„å°éº¦-玉米轮作耕地粮食产量估测­­ä»¥æ›¹åŽ¿ä¸ºä¾‹.

Establishing the remote sensing yield estimation model of wheat-maize rotation cultivated land can timely and accurately estimate the comprehensive grain yield. Taking the winter wheat-summer maize rotation cultivated land in Caoxian County, Shandong Province, as test object, using the Sentinel-2 images from 2018 to 2019, we compared the time-series feature classification based on QGIS platform and support vector machine algorithm to select the best method and extract sowing area of wheat-maize rotation cultivated land. Based on the correlation between wheat and maize vegetation index and the statistical yield, we screened the sensitive vegetation indices and their growth period, and obtained the vegetation index integral value of the sensitive spectral period by using the Newton-trapezoid integration method. We constructed the multiple linear regression and three machine learning (random forest, RF; neural network model, BP; support vector machine model, SVM) models based on the integral value combination to get the best and and optimized yield estimation model. The results showed that the accuracy rate of extracting wheat and maize sowing area based on time-series features using QGIS platform reached 94.6%, with the overall accuracy and Kappa coefficient were 5.9% and 0.12 higher than those of the support vector machine algorithm, respectively. The remote sensing yield estimation in sensitive spectral period was better than that in single growth period. The normalized differential vegetation index and ratio vegetation index integral group of wheat and enhanced vegetation index and structure intensify pigment vegetable index integral group of maize could more effectively aggregate spectral information. The optimal combination of vegetation index integral was difference, and the fitting accuracy of machine learning algorithm was higher than that of empirical statistical model. The optimal yield estimation model was the difference value group-random forest (DVG-RF) model of machine learning algorithm (R2=0.843, root mean square error=2.822 kg·hm-2), with a yield estimation accuracy of 93.4%. We explored the use of QGIS platform to extract the sowing area, and carried out a systematical case study on grain yield estimation method of wheat-maize rotation cultivated land. The established multi-vegetation index integral combination model was effective and feasible, which could improve accuracy and efficiency of yield estimation.

[Study on the length and quality of prostate biopsy tissue strips].

OBJECTIVE: To improve the diagnostic yield of prostate biopsy, which we can achieve by puncture more sites and number of cores, another way to obtain more tissue is to take longer tissue strips. In this study, we evaluated the effect of strip length on cancer diagnosis by needle biopsy and derived a cutoff value of strip length to improve cancer detection. METHODS: The pathological reports of 754 patients with suspected prostate cancer who underwent transperineal prostate biopsy were retrospectively analyzed. The age, serum prostate specific antigen (PSA), prostate volume, Gleason score and tissue strip length were analyzed. The length of the tissue strip was compared between the biopsy positive patients and the biopsy negative patients, and the patients were divided into group A（biopsy positive group）and group B（biopsy negative group）, respectively. Statistical analysis of tissue strip lengths was performed to determine cutoff values for biopsy length quality. RESULTS: A total of 10 556 tissue strips were obtained from 754 patients, and 45.1 % of the patients were pathologically diagnosed as prostate cancer. The median length of the tissue strip was 10.5 (9.5, 12.5) mm, the median age was 69 (64,75) years, the median PSA was 12.4 (8.6, 20.8) µg/L, and the median prostate volume was 44.8 (30.5, 64.4) ml. The median length of tissue strips in group A and group B was 11 (10,13) mm and 10 (9,12) mm, respectively. Receiver operating characteristic (ROC) curve analysis was performed on the length of tissue strips in all cases, and the cutoff value of quality assurance was 11.8mm, the area under curve (AUC) was 0.82, and the cut-off value of quality assurance was 11.8mm. Sensitivity 71.4%, specificity 73.8%(P<0.001). CONCLUSIONS: In transperineal prostate biopsy, the cancer detection rate of tissue strips may increase with length. The results of ROC analysis showed that 11.8 mm was used as the cut-off value for quality assurance.