ThyroidNet:A Deep Learning Network for Localization and Classification of Thyroid Nodules

Aim:This study aims to establish an artificial intelligence model,ThyroidNet,to diagnose thyroid nodules using deep learning techniques accurately.Methods:A novel method,ThyroidNet,is introduced and evaluated based on deep learning for the localization and classification of thyroid nodules.First,we propose the multitask TransUnet,which combines the TransUnet encoder and decoder with multitask learning.Second,we propose the DualLoss function,tailored to the thyroid nodule localization and classification tasks.It balances the learning of the localization and classification tasks to help improve the model’s generalization ability.Third,we introduce strategies for augmenting the data.Finally,we submit a novel deep learning model,ThyroidNet,to accurately detect thyroid nodules.Results:ThyroidNet was evaluated on private datasets and was comparable to other existing methods,including U-Net and TransUnet.Experimental results show that ThyroidNet outperformed these methods in localizing and classifying thyroid nodules.It achieved improved accuracy of 3.9%and 1.5%,respectively.Conclusion:ThyroidNet significantly improves the clinical diagnosis of thyroid nodules and supports medical image analysis tasks.Future research directions include optimization of the model structure,expansion of the dataset size,reduction of computational complexity and memory requirements,and exploration of additional applications of ThyroidNet in medical image analysis.

Electric-controlled pressure relief valve for enhanced safety in liquid-cooled lithium-ion battery packs

The liquid-cooled battery energy sto rage system(LCBESS) has gained significant attention due to its superior thermal management capacity.However,liquid-cooled battery pack(LCBP) usually has a high sealing level above IP65,which can trap flammable and explosive gases from battery thermal runaway and cause explosions.This poses serious safety risks and challenges for LCBESS.In this study,we tested overcharged battery inside a commercial LCBP and found that the conventionally mechanical pressure relief valve(PRV) on the LCBP had a delayed response and low-pressure relief efficiency.A realistic 20-foot model of an energy storage cabin was constructed using the Flacs finite element simulation software.Comparative studies were conducted to evaluate the pressure relief efficiency and the influence on neighboring battery packs in case of internal explosions,considering different sizes and installation positions of the PRV.Here,a newly developed electric-controlled PRV integrated with battery fault detection is introduced,capable of starting within 50 ms of the battery safety valve opening.Furthermore,the PRV was integrated with the battery management system and changed the battery charging and discharging strategy after the PRV was opened.Experimental tests confirmed the efficacy of this method in preventing explosions.This paper addresses the safety concerns associated with LCBPs and proposes an effective solution for explosion relief.

Application of U-Net and Optimized Clustering in Medical Image Segmentation:A Review

As a mainstream research direction in the field of image segmentation,medical image segmentation plays a key role in the quantification of lesions,three-dimensional reconstruction,region of interest extraction and so on.Compared with natural images,medical images have a variety of modes.Besides,the emphasis of information which is conveyed by images of different modes is quite different.Because it is time-consuming and inefficient to manually segment medical images only by professional and experienced doctors.Therefore,large quantities of automated medical image segmentation methods have been developed.However,until now,researchers have not developed a universal method for all types of medical image segmentation.This paper reviews the literature on segmentation techniques that have produced major breakthroughs in recent years.Among the large quantities of medical image segmentation methods,this paper mainly discusses two categories of medical image segmentation methods.One is the improved strategies based on traditional clustering method.The other is the research progress of the improved image segmentation network structure model based on U-Net.The power of technology proves that the performance of the deep learning-based method is significantly better than that of the traditional method.This paper discussed both advantages and disadvantages of different algorithms and detailed how these methods can be used for the segmentation of lesions or other organs and tissues,as well as possible technical trends for future work.

COVID-19 Detection Based on 6-Layered Explainable Customized Convolutional Neural Network

This paper presents a 6-layer customized convolutional neural network model(6L-CNN)to rapidly screen out patients with COVID-19 infection in chest CT images.This model can effectively detect whether the target CT image contains images of pneumonia lesions.In this method,6L-CNN was trained as a binary classifier using the dataset containing CT images of the lung with and without pneumonia as a sample.The results show that the model improves the accuracy of screening out COVID-19 patients.Compared to othermethods,the performance is better.In addition,the method can be extended to other similar clinical conditions.

Enhancing the Combustion Performance of Metastable Al@AP/PVDF Nanocomposites by Doping with Graphene Oxide

利用喷雾造粒技术制备了一类新型的亚稳态分子间复合含能材料(metastable intermixed composite,MIC)。这种复合材料由铝(Al)、高氯酸铵(ammonium perchlorate, AP)和聚偏氟乙烯(polyvinylidene fluoride, PVDF)组成,其中Al作为燃料,AP和PVDF共同作为氧化剂,并根据最大反应放热量确定AP和PVDF的添加比例。此外,在材料中还掺杂了少量的氧化石墨烯(graphene oxide, GO)充当润滑剂和催化剂。结果表明,含有0.2%氧化石墨烯的Al@AP/PVDF具有最大的密度(2.57 g·cm^-3)和最高的反应放热量(5999.5 J·g^-1)。这些值远高于Al@AP/PVDF的密度(2.00 g·cm^-3)和反应放热量(5569.8 J·g^-1)。氧化石墨烯的加入提高了Al@AP/PVDF的反应速率并改善了其热稳定性。掺杂0.2%氧化石墨烯的Al@AP/PVDF使得火焰传播速率达到了4.76 m·s^-1,相对于Al@AP/PVDF的火焰传播速率提高了约10.7%。掺杂氧化石墨烯的Al@AP/PVDF(Al@AP/PVDF-GO)具有更好的界面接触和颗粒分散性,从而提高了传热速率,消除了纳米铝(nano-Al)粉微粒的团聚现象,提高了燃烧反应速率。本研究使得铝基MIC的能量释放和燃烧效率得到了提高。

Sound Source Localization Based on SRP-PHAT Spatial Spectrum and Deep Neural Network

Microphone array-based sound source localization(SSL)is a challenging task in adverse acoustic scenarios.To address this,a novel SSL algorithm based on deep neural network(DNN)using steered response power-phase transform(SRP-PHAT)spatial spectrum as input feature is presented in this paper.Since the SRP-PHAT spatial power spectrum contains spatial location information,it is adopted as the input feature for sound source localization.DNN is exploited to extract the efficient location information from SRP-PHAT spatial power spectrum due to its advantage on extracting high-level features.SRP-PHAT at each steering position within a frame is arranged into a vector,which is treated as DNN input.A DNN model which can map the SRP-PHAT spatial spectrum to the azimuth of sound source is learned from the training signals.The azimuth of sound source is estimated through trained DNN model from the testing signals.Experiment results demonstrate that the proposed algorithm significantly improves localization performance whether the training and testing condition setup are the same or not,and is more robust to noise and reverberation.

COVID-19 Imaging Detection in the Context of Artificial Intelligence and the Internet of Things

Coronavirus disease 2019 brings a huge burden on the medical industry all over the world.In the background of artificial intelligence(AI)and Internet of Things(IoT)technologies,chest computed tomography(CT)and chest Xray(CXR)scans are becoming more intelligent,and playing an increasingly vital role in the diagnosis and treatment of diseases.This paper will introduce the segmentation of methods and applications.CXR and CT diagnosis of COVID-19 based on deep learning,which can be widely used to fight against COVID-19.

ABS/PBT合金两相形态及填料分布

以丙烯腈-丁二烯-苯乙烯共聚物/聚对苯二甲酸丁二醇酯(ABS/PBT)合金为研究对象,尝试建立简单有效的合金相形态评价方法。通过对比不同刻蚀溶剂和刻蚀时间,确定了四氢呋喃(THF)处理5 min并经过超声振荡可以有效刻蚀合金中的ABS相。而80℃下30%g/mL的氢氧化钾(KOH)处理20~40 min则可以较好刻蚀合金中的PBT相。经过刻蚀处理的样品在扫描电镜下可以清晰地观察到合金中两相的形态。在此方法基础上进一步研究了合金的刻蚀方法和原子发射光谱等元素定量方法的结合,利用不同溶剂刻蚀不同组分并测定元素含量变化来评估填料在ABS/PBT合金各个相中的分布情况。结果表明,ABS/PBT/5%OMMT合金体系中有机蒙拓土(OMMT)在PBT相中的含量比ABS相中高出1.39倍,即填料更倾向于分布在PBT相中。上述方法为研究填料的选择性分布开发了一种简单便捷的表征方法,并且为研究多相体系中色粉和其他助剂等成分的选择性分布提供了一种思路和方向。

The Research on Shadow Banking System in China

The shadow banking system has grown stronger in the process of evading supervision.Together with traditional commercial banks,it has become an important participant in the financial system,which has caused a fundamental change in the structure of the global financial system.As an exogenous reform force in China’s special period,Shadow Bank has become an important channel for financial resources to“disconnect from reality”.Despite the lack of substantial securitization,China’s shadow banking system has developed rapidly.This paper analyzes the development motivation.This paper believes that the scope of China’s shadow banking system can be defined according to the nature of the fund supply side.

Analysis on the Demand and Countermeasures of Air Ground Coordination in China’s Aviation Medical Rescue

Compared with ground first aid, aviation medical rescue has better advantages in mountain disaster relief, remote transfer and rapid medical rescue response, which is an effective supplement to ground medical first aid. China’s aviation medical rescue is in its infancy, compared with the level of developed countries there is a big gap. Based on the development and characteristics of aviation medical rescue in China, this paper combs the process of air-ground cooperative rescue, analyzes the demand and current situation of air-ground cooperative rescue in aviation medical rescue in China, and puts forward some countermeasures to improve the ability of aviation medical rescue in China.

The application of aromaticity and antiaromaticity to reaction mechanisms

Aromaticity,in general,can promote a given reaction by stabilizing a transition state or a product via a mobility ofπelectrons in a cyclic structure.Similarly,such a promotion could be also achieved by destabilizing an antiaromatic reactant.However,both aromaticity and transition states cannot be directly measured in experiment.Thus,computational chemistry has been becoming a key tool to understand the aromaticity-driven reaction mechanisms.In this review,we will analyze the relationship between aromaticity and reaction mechanism to highlight the importance of density functional theory calculations and present it according to an approach via either aromatizing a transition state/product or destabilizing a reactant by antiaromaticity.Specifically,we will start with a particularly challenging example of dinitrogen activation followed by other small-molecule activation,Csingle bondF bond activation,rearrangement,as well as metathesis reactions.In addition,antiaromaticity-promoted dihydrogen activation,CO_(2)capture,and oxygen reduction reactions will be also briefly discussed.Finally,caution must be cast as the magnitude of the aromaticity in the transition states is not particularly high in most cases.Thus,a proof of an adequate electron delocalization rather than a complete ring current is recommended to support the relatively weak aromaticity in these transition states.

Self-powered electrochemical anodic oxidation： A new method for preparation of mesoporous Al2O3 without applying electricity

Anodic oxidization （AO） is one of the most important methods available for fabricating mesoporous Al2O3 , which can be conducted at either high potential or low potential; however, the need for an external electricity power source limits its applications. In this work, a novel self-powered electrochemical anodic oxidization （SPAO） system was introduced for preparing mesoporous Al2O3 , by using newly-invented triboelectric nanogenerator （TENG） arrays driven by wind power. Using the controllable voltage output of the TENG arrays, the SPAO system was shown to regulate the pore depth and pore size of the mesoporous Al2O3 . In contrast to traditional AO systems, this technique takes advantage of the high output voltage of TENG arrays without any additional energy costs. In addition, the SPAO system can be used for the preparation of other mesoporous materials.

Twofold bioinspiration of TiO_(2)-PDA hybrid fabrics with desirable robustness and remarkable polar/nonpolar liquid separation performance

The fundamental relationship between microstructure,constituent,processing and performances of separating materials is really a vital issue.Traditional preparation methods for separation membranes are complex,time-consuming and easy to be fouled.Also,the durability of conventional coatings on membrane is poor.By combination of bioinspiration from mussel adhesive and fish scales’underwater superoleophobicity,we propose a general route to prepare organic-inorganic hybrid coatings,while no complex apparatus is needed.Specifically,based on the biomimetic adhesion of polydopamine(PDA),we used it as a binder to adhere TiO_(2)nanoparticles and built rough microstructure on fabric.In this way,we obtained TiO_(2)-PDA treated fabric with special wettability.These TiO_(2)-PDA treated samples owned superamphiphilicity in air,underwater superoleophobicity(underwater oil contact angles(OCAs)>150°),underoil superhydrophobicity(underoil water contact angles(WCAs)>150°),excellent multiresistance;and can separate polar/nonpolar liquid mixture effectively.It also owned superaerophobicity underwater(underwater bubble contact angles(BCAs)>150°).The proposed TiO_(2)-PDA coatings are highly expected to be employed for real situation of water pollution remediation,self-cleaning,oil extraction and harsh chemical engineering issues.