SAA-SDM: Neural Networks Faster Learned to Segment Organ Images.

In the field of medicine, rapidly and accurately segmenting organs in medical images is a crucial application of computer technology. This paper introduces a feature map module, Strength Attention Area Signed Distance Map (SAA-SDM), based on the principal component analysis (PCA) principle. The module is designed to accelerate neural networks' convergence speed in rapidly achieving high precision. SAA-SDM provides the neural network with confidence information regarding the target and background, similar to the signed distance map (SDM), thereby enhancing the network's understanding of semantic information related to the target. Furthermore, this paper presents a training scheme tailored for the module, aiming to achieve finer segmentation and improved generalization performance. Validation of our approach is carried out using TRUS and chest X-ray datasets. Experimental results demonstrate that our method significantly enhances neural networks' convergence speed and precision. For instance, the convergence speed of UNet and UNET + + is improved by more than 30%. Moreover, Segformer achieves an increase of over 6% and 3% in mIoU (mean Intersection over Union) on two test datasets without requiring pre-trained parameters. Our approach reduces the time and resource costs associated with training neural networks for organ segmentation tasks while effectively guiding the network to achieve meaningful learning even without pre-trained parameters.

Design of dynamic ski motion capture and human posture detection model based on spatio-temporal Transformer and wireless device tracking technology.

As a result of significant advancements in living conditions, individuals have redirected their attention towards physical exercise. Skiing, as a widely popular sport, necessitates the real-time maintenance of correct posture during movement. Therefore, we present a dynamic skiing motion capture and human posture detection model that leverages wireless device tracking. Primarily, personnel tracking is enabled through the construction of service base stations and the utilization of wireless device tracking technology. Subsequently, a human posture detection model is formulated in the form of human posture key points, employing the image information of each frame obtained via wireless devices. Finally, we introduce a spatio-temporal Transformer structure that facilitates the detection and recognition of human posture in consecutive frames. Our results demonstrate that our approach can precisely locate and track the position of skiing personnel. Compared to the latest Blip and Conformer methods, our technique yields F values that surpass them by 1.20% and 4.51%, respectively. Moreover, our model can achieve convergent model parameters and accomplish training objectives more efficiently, thus enabling posture detection and dynamic capture of skiing personnel via image and video information.

Numerical simulation and investigation of methane gas distribution and extraction in goaf with U-type ventilation of working face.

The accumulated methane in goaf during coal mining may leak into the working face under the airflow influence, which is possibly causing disasters such as methane gas excessive at the working face and seriously threatening the mine safety. This paper first established a three-dimensional numerical model of the mining area under U-shaped ventilation, introducing the gas state equation, continuity equation, momentum equation, porosity evolution equation, and permeability evolution equation to simulate the airflow field and gas concentration field in the mining area under the natural state. The reliability of the numerical simulations is then verified by the measured air volumes at the working face. The areas in the mining area where gas is likely to accumulate are also delineated. Subsequently, the gas concentration field in goaf under the gas extraction state was theoretically simulated for different locations of large-diameter borehole. The maximum gas concentration in goaf and the gas concentration trend in the upper corner were analyzed in detail, and the critical borehole location (17.8 m from the working face) was determined as the optimum location for gas extraction from the upper corner. Finally, a gas extraction test was carried out on-site to evaluate the application effect. The results show that the measured airflow rate has a small error with the simulated results. The gas concentration in the area without gas extraction is high, with the gas concentration in the upper corner being over 1.2%, which is greater than the critical value of 0.5%. The maximum reduction in gas concentration was 43.9%, effectively reducing the gas concentration in the extraction area after employing a large borehole to extract methane gas. The gas concentration in the upper corner and the distance of the borehole from the working face are expressed as a positive exponential function. The field engineering results show that the implementation of the large borehole at a distance of less than 17.8 m from the working face can control the gas in the upper corner to less than 0.5%, effectively reducing the risk of gas in the upper corner. The numerical simulation work in this paper can provide some basic support for the design of an on-site borehole to extract gas from the mining void and reduce the gas hazard in coal mines.

[Screening of reference genes based on real-time quantitative PCR analysis in Monochasma savatieri].

Monochasma savatieri belongs to Scrophulariaceae family. It is a facultative parasitic plant distributed in southern China that has been found in Jiangxi, Guangdong, and Fujian provinces. Previous studies on this plant have focused on its chemical constituents and pharmacological effects. The research foundation of molecular biology and functional genomics is still very in-depth, and there is no report on the reference genes. In this study, 6 reference gene(UBQ, GAPDH, AP-2, ACT, TUB and CYP) from transcriptome database, were selected and analyzed in M. savatieri.The experiment mainly involve two variables, soil moisture content and arbuscular mycorrhizal symbiosis(Rhizophagus irregularis). And the different combination of the factors result in a total of 6 treatments.Statistical tools, including GeNorm, NormFinder and Bestkeeper were utilized to assess the suitability of reference genes based on their stability rankings for different treatment. The result showed that the stability of 6 reference genes were significantly different. TUB and GAPDH were the most stable gene, while ACT was the most instable one. The results would provide reliable and optional available reference genes in gene expression analysis of M. savatieri, which has important application value.

Effects of one haustorium-inducing quinone DMBQ on growth and development of root hemiparasitic plant Monochasma savatieri / Efeitos de quinona indutor de haustório (DMBQ) no crescimento e desenvolvimento de plantas hemiparasitárias de raiz Monochasma savatieri

ABSTRACT: Monochasma savatieri Franch. ex Maxim is a perennial, parasitic herb used in traditional Chinese medicine and its wild resources have decreased sharply in recent years due to destructively harvesting and habitat destruction. Haustorium formation is a key event of parasites, but the concentrations of haustorium-inducing factors vary with species and cultivation conditions. In this study, we investigated the effects of the 2,6-dimethoxy-p-benzoquinone (DMBQ) concentration and cultivation density on the growth traits, haustorium formation and biomass of M. savatieri in the absence of a host plant. The results showed that both the DMBQ concentration and cultivation density regulated growth traits, haustorium formation and biomass in M. savatieri. The number of haustoria was significantly positively correlated with seedling height, maximum root length, the number of root tips and total dry weight. Membership function analysis revealed an overall greater increase in growth traits, haustorium formation and biomass when M. savatieri was treated with 10 μmol·L-1DMBQ and grew solitarily. These results offer an understanding of growth in M. savatieri influenced by the DMBQ concentration and cultivation density, which may aid in the establishment of a comprehensive cultivation system for M. savatieri or similar plants.

RESUMO: Monochasma savatieri Franch. O ex Maxim é uma erva parasitária aperene usada na medicina tradicional chinesa suas fontes diminuíram acentuadamente nos últimos anos devido à colheita destrutiva e à destruição de habitats e condições de sobrevivência no campo. Neste estudo, investigamos os efeitos da concentração de 2,6-dimetoxi-p-benzoquinona (DMBQ) e densidade de cultivo sobre as características de crescimento, formação de haustório e biomassa de M. savatieri na ausência de uma planta hospedeira. Os resultados mostraram que a concentração de DMBQ e a densidade de cultivo regularam as características de crescimento, a formação de haustório e a biomassa em M. savatieri. O número de haustórios foi significativamente correlacionado positivamente com a altura das plântulas, comprimento máximo das raízes, número de pontas das raízes e peso seco total. Revelou também um aumento geral nas características de crescimento, formação de haustório e biomassa quando M. savatieri foi tratado com 10 μmol • L-1DMBQ e cresceu solitariamente. Esses resultados oferecem uma compreensão do crescimento de M. savatieri influenciado pela concentração de DMBQ e densidade de cultivo, o que pode ajudar no estabelecimento de um sistema abrangente de cultivo para plantas similares de M. savatierior.

An improved SOM algorithm and its application to color feature extraction.

Reducing the redundancy of dominant color features in an image and meanwhile preserving the diversity and quality of extracted colors is of importance in many applications such as image analysis and compression. This paper presents an improved self-organization map (SOM) algorithm namely MFD-SOM and its application to color feature extraction from images. Different from the winner-take-all competitive principle held by conventional SOM algorithms, MFD-SOM prevents, to a certain degree, features of non-principal components in the training data from being weakened or lost in the learning process, which is conductive to preserving the diversity of extracted features. Besides, MFD-SOM adopts a new way to update weight vectors of neurons, which helps to reduce the redundancy in features extracted from the principal components. In addition, we apply a linear neighborhood function in the proposed algorithm aiming to improve its performance on color feature extraction. Experimental results of feature extraction on artificial datasets and benchmark image datasets demonstrate the characteristics of the MFD-SOM algorithm.

Fluorescent sensors for Ca(2+) and Pb(2+) based on binaphthyl derivatives.

Two novel binaphthyl compounds have been synthesized for the selective fluorescent recognition of Ca(2+) or Pb(2+). By introducing different terminal groups to the receptor unit, the fluorescence signals of the receptors are significantly changed: 1 is fluorescence enhancement for Ca(2+), 2 is fluorescence quenching for Pb(2+). The binding properties for metal ions were examined by the absorption and fluorescence spectra. The fluorescence intensity enhancement was ascribed to the complex formation between Ca(2+) and 1 which blocked the photo-induced electron transfer process.