A semantic segmentation-based underwater acoustic image transmission framework for cooperative SLAM

With the development of underwater sonar detection technology,simultaneous localization and mapping(SLAM)approach has attracted much attention in underwater navigation field in recent years.But the weak detection ability of a single vehicle limits the SLAM performance in wide areas.Thereby,cooperative SLAM using multiple vehicles has become an important research direction.The key factor of cooperative SLAM is timely and efficient sonar image transmission among underwater vehicles.However,the limited bandwidth of underwater acoustic channels contradicts a large amount of sonar image data.It is essential to compress the images before transmission.Recently,deep neural networks have great value in image compression by virtue of the powerful learning ability of neural networks,but the existing sonar image compression methods based on neural network usually focus on the pixel-level information without the semantic-level information.In this paper,we propose a novel underwater acoustic transmission scheme called UAT-SSIC that includes semantic segmentation-based sonar image compression(SSIC)framework and the joint source-channel codec,to improve the accuracy of the semantic information of the reconstructed sonar image at the receiver.The SSIC framework consists of Auto-Encoder structure-based sonar image compression network,which is measured by a semantic segmentation network's residual.Considering that sonar images have the characteristics of blurred target edges,the semantic segmentation network used a special dilated convolution neural network(DiCNN)to enhance segmentation accuracy by expanding the range of receptive fields.The joint source-channel codec with unequal error protection is proposed that adjusts the power level of the transmitted data,which deal with sonar image transmission error caused by the serious underwater acoustic channel.Experiment results demonstrate that our method preserves more semantic information,with advantages over existing methods at the same compression ratio.It also improves the error tolerance and packet loss resistance of transmission.

中期18F-FDG PET-CT两种图像判读法在弥漫性大B细胞淋巴瘤预后评估中的应用

目的:探讨中期正电子发射型计算机断层显像(positron emission tomography-computed tomography,PET-CT)Deauville五分法(Deauville five-point scale,5-PS)与最大标准摄取值缩减率(maximum standard uptake value variation,△SUVmax)两种图像判读法在弥漫性大B细胞淋巴瘤(diffuse large B-cell lymphoma,DLBCL)患者预后评估中的应用价值。方法:回顾性分析2012年10月至2018年6月重庆医科大学附属第一医院收治的94例DLBCL患者资料。采用Kaplan-Meier法及Cox比例风险回归模型进行生存资料分析,计算并采用χ2检验比较5-PS和△SUVmax对DLBCL患者预后预测的能力。结果:5-PS和△SUVmax分别以4分、86%进行分组。5-PS<4分组、△SUVmax≥86%组的患者无进展生存期(progression free survival,PFS)和总生存期(overall survival,OS)均优于5-PS≥4分组、△SUVmax<86%组的患者(P<0.05)。△SUVmax与5-PS对患者PFS和OS均有影响,较高的阴性预测值(89.4%,93.6%;76.1%,85.9%),较低的阳性预测值(48.9%,31.9%;47.8%,34.8%),并且△SUVmax对于患者的敏感性优于5-PS(82.1%,83.3%vs.39.3%,44.4%)。单因素分析中国际预后指数(international prognostic index,IPI)(P=0.007)、△SUVmax(P<0.001)、5-PS(P=0.014)及基线全身肿瘤代谢体积(total metabolic tumor volume,TMTV)(P=0.001)与PFS相关,△SUVmax(P=0.014)、5-PS(P=0.033)、TMTV(P=0.004)与OS相关;多因素分析显示TMTV是OS的独立预测因子(P=0.005),△SUVmax和TMTV是PFS的独立预测因子(P=0.002,P=0.020),并且△SUVmax<86%且高水平TMTV患者较低TMTV患者的PFS明显缩短(P=0.001)。结论:5-PS和△SUVmax均能初步评估DLBCL患者预后,但△SUVmax具有更高的预测价值,并且联合基线TMTV可以对DLBCL患者进行再次危险度分层。

High-adhesion anionic copolymer as solid-state electrolyte for dendrite-free Zn-ion battery

To conquer severe dendrites formation and side reactions of zinc metal anodes,which are serious obstacles for the practical applications of aqueous zinc ion battery(ZIB),herein,we develop a sodium allysulfonate(SAS)and acrylamide(AM)copolymer by radical polymerization process(crosslinking of C=C)as solid-state electrolyte.The interface kinetics is improved remarkably due to the high adhesion and excellent ion transferability of AM-SAS(AS)copolymers.Especially the sulfonic acid group in the hydrogel electrolyte can enhance the internal ionic conductivity effectively benefiting from its high affinity to Zn^(2+).Also,polymer chains realize re-regulation to Zn^(2+)flow in atomic-scale,thus leading to controllable deposition of Zn onto the dendrite-free Zn anodes.Consequently,the AS-1.5 electrolyte achieves ultra-stable Zn deposition/stripping behaviors with the lifespan over 1,000 h via the suppression of side-reactions and paralleled Zn deposition.High performances of Zn/Mn-doped V_(2)O_(5)(MnVO)(over 500 cycles)and Zn/diquinoxalino[2,3-a:2',3'-c]phenazine(HATN)(over 2,500 cycles)full cells demonstrate that the AS hydrogel electrolyte is a common approach for ZIBs under various conditions.This molecular regulation engineering opens a novel route for hydrogel electrolyte fabrication,where sulfonic groups perform as media of Zn^(2+)transfer.Therefore,high bulk ionic conductivity as well as excellent interface ion diffusion ability is obtained.

Dynamic Load Restoration Considering the Interdependencies Between Power Distribution Systems and Urban Transportation Systems

After a major outage,mobile emergency resources(MERs)can be dispatched via the transportation system(TS)for service restoration to critical loads in the power distribution system(PDS).In this case study,the efficiency of service restoration in the PDS is associated with the traffic efficiency of the TS,and vice versa,because the PDS and TS are mutually coupled through traffic lights and MERs.This paper proposes a service restoration method considering interdependency between the PDS and TS,which is formulated as a mixed-integer linear program(MILP).The objective includes maximizing the efficiency of both PDS restoration and TS.By solving the MILP,the dynamic load restoration and MER dispatch strategies can be obtained.For the PDS,the availability of MERs,including mobile sources and repair crews,relates to their dispatch in the TS,and their relationship is formulated as mathematical models.For the TS,the dynamic traffic flow is modeled using the cell transmission model and the effect of traffic lights is considered.Case studies validate the effectiveness of the proposed method.

Molecular Scaffold Growth of Two-Dimensional, Strong Interlayer-Bonding-Layered Materials

Currently,most two-dimensional(2D)materials that are of interest to emergent applications have focused on van der Waals–layered materials(VLMs)because of the ease with which the layers can be separated(e.g.,graphene).Strong interlayer-bonding-layered materials(SLMs)in general have not been thoroughly explored,and one of the most critical present issues is the huge challenge of their preparation,although their physicochemical proper-ty transformation should be richer than VLMs and deserves greater attention.MAX phases are a classi-cal kind of SLM.