|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Role of MR-DWI and MR-PWI in the radiotherapy of implanted pulmonary VX-2 carcinoma in rabbits显示文摘Objective: To detect the activity of tumor cells and tumor blood flow before and after the radiotherapy of implanted pulmonary VX-2 carcinoma in rabbit models by using magnetic resonance diffusion-weighted imaging(MR-DWI) and magnetic resonance perfusion weighted imaging(MR-PWI), and to evaluate the effectiveness and safety of the radiotherapy based on the changes in the MR-DWI and MR-PWI parameters at different treatment stages.Methods: A total of 56 rabbit models with implanted pulmonary VX-2 carcinoma were established, and then equally divided into treatment group and control group. MR-DWI and MR-PWI were separately performed using a Philips Acheiva 1.5T MRI machine(Philips, Netherland). MRI image processing was performed using special perfusion software and the WORKSPACE advanced workstation for MRI. MRDWI was applied for the observation of tumor signals and the measurement of apparent diffusion coefficient(ADC) values; whereas MR-PWI was used for the measurement of wash in rate(WIR), wash out rate(WOR), and maximum enhancement rate(MER). The radiation treatment was performed using Siemens PRIMUS linear accelerator. In the treatment group, the radiotherapy was performed 21 days later on a once weekly dosage of 1,000 c Gy to yield a total dosage of 5,000 c Gy.Results: The ADC parameters in the region of interest on DWI were as follows: on the treatment day for the implanted pulmonary VX-2 carcinoma, the t values at the center and the edge of the lesions were 1.352 and 1.461 in the treatment group and control group(P>0.05). During weeks 0-1 after treatment, the t values at the center and the edge of the lesions were 1.336 and 1.137(P>0.05). During weeks 1-2, the t values were 1.731 and 1.736(P<0.05). During weeks 2-3, the t values were 1.742 and 1.749(P<0.05). During weeks 3-4, the t values were 2.050 and 2.127(P<0.05). During weeks 4-5, the t values were 2.764 and 2.985(P<0.05). The ADC values in the treatment group were significantly higher than in the control group. After the radiotherapy(5,000 c Gy), the tumors remarkably shrank, along with low signal on DWI, decreased signal on ADC map, and remarkably increased ADC values. As shown on PWI, on the treatment day for the implanted pulmonary VX-2 carcinoma, the t values of the WIR, WOR, and MER at the center of the lesions were 1.05, 1.31, and 1.33 in the treatment group and control group(P>0.05); in addition, the t values of the WIR, WOR, and MER at the edge of the lesions were 1.35, 1.07, and 1.51(P>0.05). During weeks 0-1 after treatment, the t values of the WIR, WOR, and MER at the center of the lesions were 1.821, 1.856, and 1.931(P<0.05); in addition, the t values of the WIR, WOR, and MER at the edge of the lesions were 1.799, 2.016, and 2.137(P<0.05). During weeks 1-1 after treatment, the t values of the WIR, WOR, and MER at the center of the lesions were 2.574, 2.156, and 2.059(P<0.05) and the t values of the WIR, WOR, and MER at the edge of the lesions were 1.869, 2.058, and 2.057(P<0.05). During weeks 2-3 after treatment, the t values of the WIR, WOR, and MER at the center of the lesions were 2.461, 2.098, and 2.739(P<0.05) and the t values of the WIR, WOR, and MER at the edge of the lesions were 2.951, 2.625, and 2.154(P<0.05). During weeks 3-4 after treatment, the t values of the WIR, WOR, and MER at the center of the lesions were 2.584, 2.107, and 2.869(P<0.05) and the t values of the WIR, WOR, and MER at the edge of the lesions were 2.057, 2.637, and 2.951(P<0.05). During weeks 4-5 after treatment, the t values of the WIR, WOR, and MER at the center of the lesions were 2.894, 2.827, and 3.285(P<0.05) and the t values of the WIR, WOR, andMER at the edge of the lesions were 3.45, 3.246, and 3.614(P<0.05). After the radiotherapy(500 c Gy), the tumors shrank on the T1 WI, WIR, WOR, and MER; meanwhile, the PWI parameter gradually decreased and reached its minimum value.Conclusions: MR-DWI and MR-PWI can accurately and directly reflect the inactivation of tumor cells and the tumor hemodynamics in rabbit models with implanted pulmonary VX-2 carcinoma, and thus provide theoretical evidences for judging the clinical effectiveness of radiotherapy for the squamous cell carcinoma of the lung. | Qiang Zhang Mingmin Zhang Zhaoxin Liu Baoqi Shi Fuliang Qi Haijiang Wang Yuan Lv Haijiao Jin Weijing Zhang | 2014 | Chinese Journal of Cancer Research2014，26，5： | 5 |
| 2 | Mechanisms of Traditional Chinese Medicine Bushenantai granules(补肾安胎颗粒) in promoting angiogenesis at the maternal-fetal interface of recurrent spontaneous abortion mice显示文摘OBJECTIVE:To assess the effects of Bushenantai(BSAT)granule(补肾安胎颗粒)on angiogenesis-related factors[E2,P,and vascular endothelial growth factor(VEGF)]at the maternal-fetal interface of recurrent spontaneous abortion(RSA)mice,and to evaluate the role of BSAT in promoting angiogenesis at the maternal-fetal interface by influencing the expression of sex hormones,and VEGF.METHODS:A mouse model with normal pregnancy and another with Clark’s classic RSA were established.The RSA mice were randomly assigned to six groups:normal,model,progesterone,high-doseBSAT granule(BSAT-H),medium-dose-BSAT granule(BSAT-M),and low-dose-BSAT granule(BSAT-L)(n=10 for each group).The embryo loss rate and the histopathological changes in the decidual tissues were measured.Serum levels of estrogen(E2),progesterone(P),and VEGF were detected by enzyme-linked immunosorbent assay.The m RNA and protein expressions of estradiol receptor(ER),progesterone receptor(PR),VEGF,and vascular endothelial growth factor receptor 2(VEGFR2)in the decidual tissues were identified by immunohistochemistry,Western blotting,and quantitative reverse transcription polymerase chain reaction.RESULTS:The embryo loss rate in all groups that received BSAT treatment was reduced,while the number of blood vessels at decidual tissues was increased.The serum levels of E2,P and VEGF were elevated,and the m RNA and protein expressions of ER,PR,VEGF,and VEGFR2 in the decidual tissues were enhanced.CONCLUSION:BSAT can improve angiogenesis at the maternal-fetal interface and reduce the embryo loss rate,which may be associated with its ability to increase the serum levels of estrogen,progesterone,and VEGF,in addition to up-regulation of m RNA and protein expression of ER,PR,VEGF,and VEGFR2 in the decidual tissues. | LI Yuanqi LI Weili YU Xinhui WU Hua WANG Yuanzhong JIN Ya HAO Lele LIU Mingmin SONG Xiaoge | 2021 | Journal of Traditional Chinese Medicine2021，41，4： | 3 |
| 3 | Acupuncture stimulation of Yamen(GV 15), Fengfu(GV 16), Baihui(GV 20), Shuigou(GV 26) and Hegu(LI 4) reduces brain microglia activation in a traumatic brain injury rat model显示文摘OBJECTIVE: To evaluate the effect of acupuncture on neuroinflammation in traumatic brain injury(TBI) rats by stimulating Yamen(GV 15), Fengfu(GV16), Baihui(GV 20), Shuigou(GV 26) and Hegu(LI 4)acupoints and to investigate the mechanism underpinning this effect.METHODS: A TBI model was induced in SpragueDawley rats using Feeney's freefall impact method.Acupuncture to stimulate the Yamen(GV 15), Fengfu(GV 16), Baihui(GV 20), Shuigou(GV 26) and Hegu(LI 4) acupoints was performed on the TBI rats. After 3 consecutive days of acupuncture treatment, we investigated signal molecules, receptors and microglia related to neuroinflammation in brain tissue of the TBI rats and analyzed the possi-ble mechanism underlying the effect of acupuncture on neuroinflammation.RESULTS: After the acupuncture treatment, ionized calcium binding adaptor molecule 1(Iba1), a protein specific to microglia, was investigated. In the cortical layer of damaged brain tissue in TBI rats,the Iba1-positive area was 3.3% ± 0.9% in the rats that received acupuncture compared with 5.2% ±1.4% in the TBI rats that did not receive acupuncture, and the microglia were smaller with more slender protrusions in the acupuncture-treated rats.This result indicates that acupuncture can significantly reduce microglia activation in TBI rats. A possible mechanism for this effect is that acupuncture reduces the expression of autotaxin and lysophosphatidic acid. Together, these constitute the autotaxin-lysophosphatidic acid axis, which induces microglial activation in the brains of TBI rats. Acupuncture treatment may downregulate the expression of Lysophosphatidic acid(LPA) receptor(LPAR) 1 and LPAR2 on the microglial cytomembrane, which affects the microglia activation process.CONCLUSION: Acupuncture stimulating the Yamen(GV 15), Fengfu(GV 16), Baihui(GV 20),Shuigou(GV 26) and Hegu(LI 4) acupoints can effectively inhibit the development of neuroinflammation after TBI. One possible mechanism for this effect is that acupuncture downregulates LPA synthesis and affects the LPA-LPAR pathway by inhibiting LPAR1 and LPAR2, thereby inhibiting microglial activation and reducing neuroinflammation. | Lin Shujun Zhu Mingmin Chen Weihao Zhang Yujuan Lin Jihuan Pu Liu Chen Shulian Zhang Yimin Liu Xin | 2020 | Journal of Traditional Chinese Medicine2020，40，2： | 3 |
| 4 | Bayesian network learning algorithm based on unconstrained optimization and ant colony optimization显示文摘Structure learning of Bayesian networks is a wellresearched but computationally hard task.For learning Bayesian networks,this paper proposes an improved algorithm based on unconstrained optimization and ant colony optimization(U-ACO-B) to solve the drawbacks of the ant colony optimization(ACO-B).In this algorithm,firstly,an unconstrained optimization problem is solved to obtain an undirected skeleton,and then the ACO algorithm is used to orientate the edges,thus returning the final structure.In the experimental part of the paper,we compare the performance of the proposed algorithm with ACO-B algorithm.The experimental results show that our method is effective and greatly enhance convergence speed than ACO-B algorithm. | Chunfeng Wang Sanyang Liu Mingmin Zhu | 2012 | Journal of Systems Engineering and Electronics2012，23，5： | 3 |
| 5 | Changes in zooplankton community structure in Sanmen Bay,China显示文摘Seasonal variations in zooplankton abundance,biomass,species diversity and community structure were investigated in the Sanmen Bay,China.Samples were collected from 15 stations,on the seasonal basis,in April(spring),July(summer) and October 2005(autumn) and January 2006(winter),respectively.The results show that zooplankton species number,abundance and biomass varied widely and had distinct spatial heterogeneity in the Sanmen Bay.A total of 72 species of zooplankton belonging to 56 genera and 17 groups of pelagic larvae were identified.The zooplankton species richness was strongly related to salinity.Based on hierarchical cluster analysis,zooplankton in this study area were classified into three groups:coastal,neritic and pelagic groups,which corresponded to the upper,middle and lower portion of the Sanmen Bay,respectively.The coastal low-saline species were dominant in the study area.The zooplankton abundance and biomass reached a peak in summer,moderate in spring and autumn,and the lowest in winter.Zooplankton abundance decreased from the upper to lower portion of the bay in April,when the highest biomass occurred in the middle portion of the bay.There were the same spatial distribution patterns for the biomass and abundance in July,with the maximum in the middle of the bay.However,zooplankton abundance was the highest in the middle of the bay in October,when maximum biomass occurred near the lower of the bay.Zooplankton abundance and biomass were evenly distributed in the Sanmen Bay in January.Spatial and temporal variations in zooplankton and their relationship with environmental factors were also analyzed.The BIOENV results indicate that the combination of chlorophyll a(Chl-a),salinity,dissolved inorganic nitrogen(DIN),dissolved oxygen(DO) and silicate(SiO3) was responsible for the variations in zooplankton community structure in the Sanmen Bay.The environmental changes played an important role in changes in the zooplankton community structure in the Sanmen Bay. | LIU Zhensheng ZHANG Zhinan WANG Chunsheng JIN Haiyan DU Mingmin ZHANG Dongsheng | 2012 | Acta Oceanologica Sinica2012，31，6： | 2 |
| 6 | Lymphangiogenesis and biological behavior in pancreatic carcinoma andother pancreatic tumors显示文摘 | Zhongqiu Wang Jiang Wu Guojun Li Xinhua Zhang Mingmin Tong Zhengcan Wu Zhenjuan Liu | 2012 | Molecular Medicine Reports2012，，4： | 1 |
| 7 | A Bayesian Classi- fier Learning Algorithm Based on Optimization Model显示文摘 | Liu Sanyang Zhu Mingmin Yang Youlong | 2013 | Mathemati- cal Problems in Engineering2013，2013，： | 1 |
| 8 | STIM1 thermosensitivity defines the optimal preference temperature for warm sensation in mice显示文摘Mammals possess a remarkable ability to sense subtle temperature deviations from the thermoneutral skin temperature of -33 ℃, which ensures precise warm sensation.However,the underlying mechanisms remain unclear.Here we show that STIM1,an endoplasmic reticulum (ER)resident transmembrane protein that responds to both ER Ca^2- depletion and heat,mediates temperature-induced Ca^2+ influx in skin keratinocytes via coupling to Orai Ca^2+ channels in plasma membrane.Behaviorally,the keratinocyte-specific knockout of STIM1 shifts the optimal preference temperature (OPT)of mice from -32 ℃ to -34℃,resulting in a strikingly reversed preference between 32℃ and 34℃.Importantly,the thermally inactive STIM1-△K knock-in mice show altered OPT and warm preference behaviors as well,demonstrating the requirement of STIM1 thermosensitivity for warm sensation. Furthermore,the wild-type and mutant mice prefer temperatures closer to their respective OPTs,but poorly distinguish temperatures that are equally but oppositely deviated from their OPTs.Mechanistically,keratinocyte STIM1 affects the in vivo warm responses of sensory neurons by likely involving TRPA1 as a downstream transduction channel.Collectively,our data suggest that STIM1 serves as a novel in vivo thermosensor in keratinocytes to define the OPT,which might be utilized as a peripheral reference temperature for precise warm sensation. | Xiaoling Liu Haiping Wang Yan Jiang Qin Zheng Matt Petrus Mingmin Zhang Sisi Zheng Christian Schmedt Xinzhong Dong Bailong Xiao | 2019 | Cell Research2019，29，2： | 1 |
| 9 | Characterization of copper oxide supported on ceria-modified anatase显示文摘 | Haiyang Zhu Mingmin Shen Yan Kong Jianming Hong Yuhai Hu Tiandong Liu Lin Dong Yi Chen Can Jian Zhong Liu | 2004 | A, Chemical2004，，1： | 1 |
| 10 | A decomposition algorithm for learning Bayesian networks based on scoring function 显示文摘 | Zhu Mingmin Liu Sanyang | 2012 | Journal of Applied Mathematics2012，，1： | 1 |
| 11 | Research and Practice of Flexibility in Distribution Systems:A Review显示文摘Flexibility in energy systems can support the operation of the electricity grid by providing active and reactive power to avoid voltage limit violations or congestion.Active distribution networks can provide this flexibility by implementing systems to control distributed generators,storage or loads.Additionally,power flow controlling devices can be used to implement operational flexibility in the energy system.This paper presents concepts for planning and forecasting of flexibility,monitoring of energy systems and control of flexibility from active distribution networks(ADNs)to enable the use of flexibility in future power systems. | Stefan Dalhues Yang Zhou Oliver Pohl Florian Rewald Fabian Erlemeyer Dennis Schmid Jannik Zwartscholten Zita Hagemann Christian Wagner Daniel Mayorga Gonzalez Hua Liu Mingmin Zhang Jiayan Liu Christian Rehtanz Yong Li Yijia Cao | 2019 | CSEE Journal of Power and Energy Systems2019，5，3： | 1 |
| 12 | Using junction trees for structural learning of Bayesian networks显示文摘The learning Bayesian network (BN) structure from data is an NP-hard problem and still one of the most exciting challenges in the machine learning.In this work,a novel algorithm is presented which combines ideas from local learning,constraintbased,and search-and-score techniques in a principled and effective way.It first reconstructs the junction tree of a BN and then performs a K2-scoring greedy search to orientate the local edges in the cliques of junction tree.Theoretical and experimental results show the proposed algorithm is capable of handling networks with a large number of variables.Its comparison with the well-known K2 algorithm is also presented. | Mingmin Zhu Sanyang Liu Youlong Yang Kui Liu | 2012 | Journal of Systems Engineering and Electronics2012，23，2： | 1 |
| 13 | Prospective comparison of laparoscopic uterine artery occlusion plus myomectomy with classic intrafascial supracervical hysterectomy for symptomatic fibroid treatment:differences in post-operative quality-of-life measures显示文摘 | Mingmin Liu Zhongping Cheng Yu Zhu | 2010 | European Journal of Obstetrics and Gynecology2010，155，1： | 1 |
| 14 | Increased leucine-rich repeats and immunoglobulin- like domains 1 expression enhances chemosensitivity in glioma显示文摘Leucine-rich repeats and immunoglobulin-like domains 1 (LRIG1) is an anti-oncogene. LRIG1 is correlated with Bcl-2 in ependymomas. Decreased Bcl-2 and manganese superoxide dismutase expression can improve the chemosensitivity of glioma. In the present study, a tissue microarray of human brain astrocytomas was constructed. To investigate the relationship of LRIG1 with Bcl-2 and manganese superoxide dismutase, LRIG1, Bcl-2 and manganese su-peroxide dismutase expression in our tissue microarray was determined using immunohisto-chemistry. In addition, we constructed the LRIG1-U251 cell line, and its responses to doxoru-bicin and temozolomide were detected using the MTT assay. Results showed that LRIG1 ex-pression was significantly negatively correlated with Bcl-2 and manganese superoxide dismu-tase expression in glioma. Also, proliferation of LRIG1-U251 cells exposed to doxorubicin or temozolomide was significantly inhibited, i.e. in the LRIG1-U251 cell line, the chemosensitivity to doxorubicin and temozolomide was increased. This indicates that increased LRIG1 expres-sion produces a chemosensitivity in glioma. | Baohui Liu Qianxue Chen Daofeng Tian Licluan Wu Junmin Wang Qiang Cai Heng Shen Baowei Ji Long Wang Shenqi Zhang Dong Ruan Xiaonan Zhu Zhentao Guo Huimin Dong Mingmin Yan | 2011 | Neural Regeneration Research2011，6，32： | 1 |
| 15 | Characterization of copper oxide supported on ceria-modified anatase显示文摘 | Haiyang Zhu Mingmin Shen Yan Kong Jianming Hong Yuhai Hu Tiandong Liu Lin Dong Yi Chen Can Jian Zhong Liu | 2004 | Journal of Molecular Catalysis A Chemical2004，，1： | 1 |
| 16 | Modulate the electronic structure of Cu_(7)S_(4)nanosheet on TiO_(2)for enhanced photocatalytic hydrogen evolution显示文摘TiO_(2)is a promising photocatalyst due to its high thermodynamic stability and non-toxicity.However,its applications have been still limited because of the high recombination rate of electron-hole pairs.Herein,we show that by combining heterojunction construction and electronic structure regulation,the electron-hole pairs in TiO_(2)can be effectively separated for enhanced photocatalytic hydrogen evolution.The optimized Cu_(7)S_(4)nanosheet decorated TiO_(2)achieves much enhanced H_(2)evolution rate(11.5 mmol·g−1·h−1),which is 13.8 and 4.2 times of that of TiO_(2)and Cu_(7)S_(4)/TiO_(2),respectively.The results of photoluminescence spectroscopy,transient photocurrent spectra,ultraviolet-visible diffuse reflectance spectra,and electrochemical impedance spectroscopy collectively demonstrate that the enhanced photocatalytic performance of Air-Cu_(7)S_(4)/TiO_(2)is attributed to the effective separation of charge carriers and widened photoresponse range.The electron paramagnetic resonance and X-ray photoelectron spectroscopy results indicate that the increase of Cu2+in the Cu_(7)S_(4)nanosheet after calcination can promote the charge transfer.This work provides an effective method to improve the electron migration rate and charge separation of TiO_(2),which holds great significance for being extended to other material systems and beyond. | Wenqiang Liu Huiping Peng Leigang Li Mingmin Wang Hongbo Geng Xiaoqing Huang | 2023 | Nano Research2023，16，4： | 0 |
| 17 | Non-IID federated learning via random exchange of local feature maps for textile IIoT secure computing显示文摘With the fast development of artificial intelligence(AI) and industrial Internet of Things(IIoT)technologies, it is challenging to deal with the problems of data privacy protection and secure computing.In recent years, federated learning(FL) is proposed to attack the challenges of learning shared models collaboratively while protecting security based on the data from cross-domain clients. However, data in the real environment is usually not independent and identically distributed(Non-IID) due to the differences in business, working environments, and data acquisition, and thus classic federated methods suffer from significant performance degradation. In this paper, a novel federated framework is proposed for secure textile fiber identification(Fed TFI) via cross-domain texture representation based on high-definition fabric images. In addition to sharing the gradient of Fed TFI, the local patch of feature maps between crossdomain clients is randomly exchanged to build a richer image texture feature distribution while protecting data security simultaneously for secure computing. Furthermore, a texture embedding layer is designed to provide a joint representation through similarity measure between triplet samples in low-dimensional space.To verify the effectiveness of the proposed framework, two textile image datasets, i.e., one public and the other we collected, are utilized to construct four Non-IID scenarios, including label skew, feature skew, and two combined skew scenarios. The experimental results confirm the effectiveness of our model to obtain better detection accuracies than benchmarks in four Non-IID scenarios by keeping data privacy for secure computing in fabric IIoT. | Bo PENG Mingmin CHI Chao LIU | 2022 | Science China(Information Sciences)2022，65，7： | 0 |
| 18 | A novel dephosphorylation targeting chimera selectively promoting tau removal in tauopathies显示文摘Intraneuronal accumulation of hyperphosphorylated tau is a hallmark pathology shown in over twenty neurodegenerative disorders,collectively termed as tauopathies,including the most common Alzheimer's disease(AD).Therefore,selectively removing or reducing hyperphosphorylated tau is promising for therapies of AD and other tauopathies.Here,we designed and synthesized a novel DEPhosphorylation TArgeting Chimera(DEPTAC)to specifically facilitate the binding of tau to Ba-subunit-contalning protein phosphatase 2A(PP2A-Ba),the most active tau phosphatase in the brain.The DEPTAC exhibited high efficiency in dephosphorylating tau at multiple AD-associated sites and preventing tau accumulation both in vitro and in vivo.Further studies revealed that DEPTAC significantly improved microtubule assembly,neurite plasticity,and hippocampus-dependent learning and memory in transgenic mice with inducible overexpression of truncated and neurotoxic human tau N368.Our data provide a strategy for selective removal of the hyperphosphorylated tau,which sheds new light for the targeted therapy of AD and related-tauopathies. | Jie Zheng Na Tian Fei Liu Yidian Zhang Jingfen Su Yang Gao Mingmin Deng Linyu Wei Jingwang Ye Honglian Li Jian-Zhi Wang | 2021 | Signal Transduction and Targeted Therapy2021，6，8： | 0 |
| 19 | The high-quality sequencing of the Brassica rapa‘XiangQingCai’genome and exploration of genome evolution and genes related to volatile aroma显示文摘‘Vanilla’(XQC,brassica variety chinensis)is an important vegetable crop in the Brassica family,named for its strong volatile fragrance.In this study,we report the high-quality chromosome-level genome sequence of XQC.The assembled genome length was determined as 466.11 Mb,with an N50 scaffold of 46.20 Mb.A total of 59.50%repetitive sequences were detected in the XQC genome,including 47570 genes.Among all examined Brassicaceae species,XQC had the closest relationship with B.rapa QGC(‘QingGengCai’)and B.rapa Pakchoi.Two whole-genome duplication(WGD)events and one recent whole-genome triplication(WGT)event occurred in the XQC genome in addition to an ancient WGT event.The recent WGT was observed to occur during 21.59-24.40 Mya(after evolution rate corrections).Our findings indicate that XQC experienced gene losses and chromosome rearrangements during the genome evolution of XQC.The results of the integrated genomic and transcriptomic analyses revealed critical genes involved in the terpenoid biosynthesis pathway and terpene synthase(TPS)family genes.In summary,we determined a chromosome-level genome of B.rapa XQC and identified the key candidate genes involved in volatile fragrance synthesis.This work can act as a basis for the comparative and functional genomic analysis and molecular breeding of B.rapa in the future. | Zhaokun Liu Yanhong Fu Huan Wang Yanping Zhang Jianjun Han Yingying Wang Shaoqin Shen Chunjin Li Mingmin Jiang Xuemei Yang Xiaoming Song | 2023 | Horticulture Research2023，10，10： | 0 |
| 20 | DGConv: A Novel Convolutional Neural Network Approach for Weld Seam Depth Image Detection显示文摘We propose a novel image segmentation algorithm to tackle the challenge of limited recognition and segmentation performance in identifying welding seam images during robotic intelligent operations.Initially,to enhance the capability of deep neural networks in extracting geometric attributes from depth images,we developed a novel deep geometric convolution operator(DGConv).DGConv is utilized to construct a deep local geometric feature extraction module,facilitating a more comprehensive exploration of the intrinsic geometric information within depth images.Secondly,we integrate the newly proposed deep geometric feature module with the Fully Convolutional Network(FCN8)to establish a high-performance deep neural network algorithm tailored for depth image segmentation.Concurrently,we enhance the FCN8 detection head by separating the segmentation and classification processes.This enhancement significantly boosts the network’s overall detection capability.Thirdly,for a comprehensive assessment of our proposed algorithm and its applicability in real-world industrial settings,we curated a line-scan image dataset featuring weld seams.This dataset,named the Standardized Linear Depth Profile(SLDP)dataset,was collected from actual industrial sites where autonomous robots are in operation.Ultimately,we conducted experiments utilizing the SLDP dataset,achieving an average accuracy of 92.7%.Our proposed approach exhibited a remarkable performance improvement over the prior method on the identical dataset.Moreover,we have successfully deployed the proposed algorithm in genuine industrial environments,fulfilling the prerequisites of unmanned robot operations. | Pengchao Li Fang Xu Jintao Wang Haibing Guo Mingmin Liu Zhenjun Du | 2024 | Computers, Materials & Continua2024，78，2： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员