Neuromorphic circuits based on memristors: endowing robots with a human-like brain

Robots are widely used,providing significant convenience in daily life and production.With the rapid development of artificial intelligence and neuromorphic computing in recent years,the realization of more intelligent robots through a pro-found intersection of neuroscience and robotics has received much attention.Neuromorphic circuits based on memristors used to construct hardware neural networks have proved to be a promising solution of shattering traditional control limita-tions in the field of robot control,showcasing characteristics that enhance robot intelligence,speed,and energy efficiency.Start-ing with introducing the working mechanism of memristors and peripheral circuit design,this review gives a comprehensive analysis on the biomimetic information processing and biomimetic driving operations achieved through the utilization of neuro-morphic circuits in brain-like control.Four hardware neural network approaches,including digital-analog hybrid circuit design,novel device structure design,multi-regulation mechanism,and crossbar array,are summarized,which can well simulate the motor decision-making mechanism,multi-information integration and parallel control of brain at the hardware level.It will be definitely conductive to promote the application of memristor-based neuromorphic circuits in areas such as intelligent robotics,artificial intelligence,and neural computing.Finally,a conclusion and future prospects are discussed.

ARGA-Unet:Advanced U-net segmentation model using residual grouped convolution and attention mechanism for brain tumor MRI image segmentation

Background Magnetic resonance imaging(MRI)has played an important role in the rapid growth of medical imaging diagnostic technology,especially in the diagnosis and treatment of brain tumors owing to its non invasive characteristics and superior soft tissue contrast.However,brain tumors are characterized by high non uniformity and non-obvious boundaries in MRI images because of their invasive and highly heterogeneous nature.In addition,the labeling of tumor areas is time-consuming and laborious.Methods To address these issues,this study uses a residual grouped convolution module,convolutional block attention module,and bilinear interpolation upsampling method to improve the classical segmentation network U-net.The influence of network normalization,loss function,and network depth on segmentation performance is further considered.Results In the experiments,the Dice score of the proposed segmentation model reached 97.581%,which is 12.438%higher than that of traditional U-net,demonstrating the effective segmentation of MRI brain tumor images.Conclusions In conclusion,we use the improved U-net network to achieve a good segmentation effect of brain tumor MRI images.

Intelligent diagnosis of atrial septal defect in children using echocardiography with deep learning

Background Atrial septal defect(ASD)is one of the most common congenital heart diseases.The diagnosis of ASD via transthoracic echocardiography is subjective and time-consuming.Methods The objective of this study was to evaluate the feasibility and accuracy of automatic detection of ASD in children based on color Doppler echocardiographic static images using end-to-end convolutional neural networks.The proposed depthwise separable convolution model identifies ASDs with static color Doppler images in a standard view.Among the standard views,we selected two echocardiographic views,i.e.,the subcostal sagittal view of the atrium septum and the low parasternal four-chamber view.The developed ASD detection system was validated using a training set consisting of 396 echocardiographic images corresponding to 198 cases.Additionally,an independent test dataset of 112 images corresponding to 56 cases was used,including 101 cases with ASDs and 153 cases with normal hearts.Results The average area under the receiver operating characteristic curve,recall,precision,specificity,F1-score,and accuracy of the proposed ASD detection model were 91.99,80.00,82.22,87.50,79.57,and 83.04,respectively.Conclusions The proposed model can accurately and automatically identify ASD,providing a strong foundation for the intelligent diagnosis of congenital heart diseases.

Investigation and analysis of vascular plant resources and diversity in Wuyi Mountain,Fujian Province

Wuyi Mountain,located in the north of Fujian Province,China,is renowned for its abundant medicinal plant resources.In July 2014,the 8th(second team)of Shenyang Pharmaceutical University’s Chinese Medicine Resources Scientific Expedition Team conducted field investigation in the area.Through specimen collection and extensive literature review,the team identified and analyzed 223 vascular plant species from 175 genera and 85 families.The most dominant families were Compositae and Rosaceae,and perennial herbs were the predominant species,accounting for 44.39%of the total species identified.Notably,we documented five precious and rare medicinal plants unique to Wuyi Mountain.This study updates the database of plant resources and diversity in the region,providing a valuable reference for future studies.Finally,we put forward some suggestions to enhance the conservation and sustainable utilization of Wuyi Mountain’s plant resources.

Mapping and validation of a dominant salt tolerance gene in the cultivated soybean(Glycine max) variety Tiefeng 8

Salt is an abiotic stress factor that strongly affects soybean growth and production. A single dominant gene has been shown to confer salt tolerance in the soybean cultivar Tiefeng 8.The objective of the present study was to genetically map the salt-tolerance gene in an F2:3population and a recombinant inbred line(RIL) population derived from a cross between two cultivated soybeans, Tiefeng 8(tolerant) and 85-140(sensitive). The F2:3families and RILs were treated with 200 mmol L-1Na Cl to evaluate salt tolerance. The F2:3population showed 1(42 tolerant): 2(132 segregating): 1(65 sensitive) segregation, indicating a single dominant gene for salt tolerance in Tiefeng 8. A sequence-characterized amplified region(SCAR) marker from a previously identified random amplified polymorphic DNA(RAPD)marker and four insertion/deletion polymorphism(In Del) markers were developed within the mapping region. Using these markers along with SSR markers, the salt-tolerance gene was mapped within 209 kb flanked by SCAR marker QS08064 and SSR marker Barcsoyssr_3_1301 on chromosome 3. Three markers that cosegregated with the salt tolerance gene and SCAR marker QS08064 were used to genotype 35 tolerant and 23 sensitive soybean accessions. These markers showed selection efficiencies of 76.2% to94.2%. The results indicate that these markers will be useful for marker-assisted breeding and facilitating map-based cloning of the salt tolerance gene in soybean.

Purification Influence of Synthesis Gas Derived from Methanol Cracking on the Performance of Cobalt Catalyst in Fischer-Tropsch Synthesis

Synthesis gas derived from methanol cracking （SGMC） was applied as simulating feedstock of Fischer-Tropsch synthesis （FTS） in laboratory. With MS and GC detector, a trifle of sulfur compounds, a small amount of oxygenates including H2O, CH3OH, DME and CO2 as well as a few of low carbon alkanes were found in the SGMC. After purification, the sulfur compounds, H2O, CH3OH and DME could be eliminated efficiently from the SGMC while CO2 and the low carbon alkanes were partly removed. When the unpurified SGMC, the desufurized SGMC and the totally purified SGMC were sequentially applied in cobalt-based FTS, the catalytic performance of Co/ZrO2/SiO2 catalyst was gradually improved corresponding to the degree of purification. The untreated SGMC led to the serious deactivation of the cobalt catalyst, the partially treated SGMC slowed down the deactivation rate and the totally purified SGMC resulted in little deactivation of the catalyst, which was similar to what the pure synthesis gas （the mixture of pure H2 and CO） did. The results indicated that the SGMC should be purified and the purification course used in this paper was effective for the SGMC. Furthermore, the totally purified SGMC could substitute for the pure synthesis gas in cobalt FTS.

Ultrasonographic Segmentation of Fetal Lung with Deep Learning

The morbidity and mortality of the fetus is related closely with the neonatal respiratory morbidity, which was caused by the immaturity of the fetal lung primarily. The amniocentesis has been used in clinics to evaluate the maturity of the fetal lung, which is invasive, expensive and time-consuming. Ultrasonography has been developed to examine the fetal lung quantitatively in the past decades as a non-invasive method. However, the contour of the fetal lung required by existing studies was delineated in manual. An automated segmentation approach could not only improve the objectiveness of those studies, but also offer a quantitative way to monitor the development of the fetal lung in terms of morphological parameters based on the segmentation. In view of this, we proposed a deep learning model for automated fetal lung segmentation and measurement. The model was constructed based on the U-Net. It was trained by 3500 data sets augmented from 250 ultrasound images with both the fetal lung and heart manually delineated, and then tested on 50 ultrasound data sets. With the proposed method, the fetal lung and cardiac area were automatically segmented with the accuracy, average IoU, sensitivity and precision being 0.98, 0.79, 0.881 and 0.886, respectively.

PCA-U-Net based breast cancer nest segmentation from microarray(jj)hyperspectral images

The incidence of breast cancer is tending younger globally,and tumor development,clinical treatment,and prognosis are largely influenced by histopathological diagnosis.For diagnosed patients,the distinction between the cancer nests and normal tissue is the basis of breast cancer treatment.Microscopic hyperspectral imaging technology has shown its potential in auxiliary pathological examinations due to the superior imaging modality and data characteristics.This paper presents a method for cancer nest segmentation from hyperspectral images of breast cancer tissue microarray samples.The scheme combines the strengths of the U-Net neural network and unsupervised principal component analysis,which reduces the amount of calculation and improves the recognition accuracy.The experimental accuracy of cancer nest segmentation reaches 87.14%.Furthermore,a set of quantitative pathological characteristic parameters reflects the degree of breast cancer lesions from multiple angles,providing a relatively comprehensive reference for the pathologist’s diagnosis.In-depth exploration of the combined development of deep learning and microscopic hyperspectral imaging technology is worthy to promote efficient diagnosis of breast tumors and concern for human health.

Sea-urchin-like ReS_(2) nanosheets with charge edge-collection effect as a novel cocatalyst for high-efficiency photocatalytic H_(2) evolution

The recombination of charge carriers arriving from the random charge movement in semiconductor pho-tocatalysts greatly limits the practical application of solar-driven H_(2)evolution.The design of photo-catalytic systems with spatially oriented charge-transfer is a promising route to achieve high charge-separation efficiency for photocatalysts.Herein,novel sea-urchin-like Re S_(2)nanosheet/TiO_(2)nanoparticle heterojunctions(SURTHs)are constructed.The unique sea-urchin-like structure endows the ReS_(2)cocat-alyst with an unusual charge edge-collection effect,which leads to a significant acceleration of charge separation and transfer,as evidenced by the well-designed selective photodeposition of Pt quantum dots in SURTHs.The markedly improved charge transfer capacity contributes to a high photocatalytic H_(2)evo-lution rate of 3.71 mmol h^(−1)g^(−1)for SURTHs(an apparent quantum efficiency(AQE)of 16.09%),up to 231.9 times by contrast with that of P25 TiO_(2).This work would provide a new platform for designing the high-efficiency cocatalyst/photocatalyst system with excellent charge transfer capacity.

Pollutant reduction effectiveness of low-impact development drainage system in a campus

Building a rainwater system based on the idea of low-impact development （LID） is an important aspect of the current ＂sponge city＂ construction in China. The ＂sponge city＂ concept emphasizes that the runoff can permeate the soil or be stored temporarily, and rainwater could be used again when it is needed. Beijing is one of the earliest cities to study rainwater harvesting and LID techniques in China.Through long-terua monitoring of rainfall, runoff flow, and water quality of a campus demonstration project in Beijing, the runoff quantity and pollutant concentration variations have been analyzed. Furthermore, the runoffreduction effects of single LID measure, such as green roof, filtration chamber, and permeable pavement, have been investigated. Additionally, the overall reduction effectiveness of the LID system on the average annual rainfall runoff and pollution load has been discussed.