Optimized Binary Neural Networks for Road Anomaly Detection:A TinyML Approach on Edge Devices

Integrating Tiny Machine Learning(TinyML)with edge computing in remotely sensed images enhances the capabilities of road anomaly detection on a broader level.Constrained devices efficiently implement a Binary Neural Network(BNN)for road feature extraction,utilizing quantization and compression through a pruning strategy.The modifications resulted in a 28-fold decrease in memory usage and a 25%enhancement in inference speed while only experiencing a 2.5%decrease in accuracy.It showcases its superiority over conventional detection algorithms in different road image scenarios.Although constrained by computer resources and training datasets,our results indicate opportunities for future research,demonstrating that quantization and focused optimization can significantly improve machine learning models’accuracy and operational efficiency.ARM Cortex-M0 gives practical feasibility and substantial benefits while deploying our optimized BNN model on this low-power device:Advanced machine learning in edge computing.The analysis work delves into the educational significance of TinyML and its essential function in analyzing road networks using remote sensing,suggesting ways to improve smart city frameworks in road network assessment,traffic management,and autonomous vehicle navigation systems by emphasizing the importance of new technologies for maintaining and safeguarding road networks.

离子液体催化氯乙酸甲酯合成氯乙酸-2-庚酯的研究

探索了离子液体催化氯乙酸甲酯和2-庚醇的酯交换反应,制备了1-甲基-3-(丙基-3-磺酸基)咪唑对甲苯磺酸盐[MIM-PS][PTSA]、1-甲基-3-(丙基-3-磺酸基)咪唑硫酸氢盐[MIM-PS][HSO_(4)]、1-丁基-3-甲基咪唑硫酸氢盐[BMIM]HSO_(4)、N-甲基咪唑磷酸盐[HMIM]H_(2)PO_(4)四种离子液体催化剂并用于酯交换反应,通过考察产品氯乙酸-2-庚酯收率,筛选出最佳催化剂[MIM-PS][PTSA]。并用[MIM-PS][PTSA]考察了反应温度、反应时间、催化剂添加量、催化剂循环使用对合成产品收率的影响。结果表明:将氯乙酸甲酯和2-庚醇在100℃下,添加5%[MIM-PS][PTSA]催化剂,反应6 h,合成氯乙酸-2-庚酯,收率可达76.3%,离子液体重复使用3次,氯乙酸-2-庚酯收率仍大于初次收率的95%。本实验用离子液体做溶剂或催化剂,反应条件稳定,可循环利用、对环境友好,且产品收率高,为工艺放大提供实验条件参考。

Thermoelectric enhancement of p-type Si_(80)Ge_(20) alloy via co-compositing of dual oxides:Respective regulation for power factor and thermal conductivity byβ-Ga_(2)O_(3) and SiO_(2) aerogel powders

Si-based thermoelectric(TE)materials are exhibiting remarkable perspectives in self-energized applications with their special advantages.However,the relatively high total thermal conductivity(κ)prevents their TE enhancement.Here,a strategy of co-compositing dual oxides was implemented for enhancing the TE properties of p-type Si_(80)Ge_(20) bulks.Composited Ga2O_(3) was demonstrated to enhance the power factor(PF)due to the crystallization-induced effect of produced Ga by decomposition on SiGe matrix.Associating with compositing SiO_(2) aerogel(a-SiO_(2))powder,not only introduced the fine amorphous inclusions and decreased the grain size of host matrix,but also various nano morphologies were formed,i.e.,nano inclusions,precipitations,twin boundaries(TBs),and faults.Combining with the eutectic Ge,hierarchical scattering centers impeded the phonon transport comprehensively(decreasing the phonon group velocity(a v)and relaxation time)for reducing the lattice-induced thermal conductivity(lκ).As a result,a minimumκof 2.38 W·m^(−1)·K^(−1) was achieved,which is significantly dropped by 32.6%in contrast with that of the pristine counterpart.Ultimately,a maximal dimensionless figure of merit(ZT)of 0.9 was achieved at 600℃,which is better than those of most corresponding oxide-composited Si-based bulks.

Diverse structures and antihepatoma effect of sesquiterpenoid dimers from Artemisia eriopoda by AKT/STAT signaling pathway

Dear Editor,Liver cancer as a common malignant tumor has become a major source of morbidity and mortality worldwide.1 Currently,four synthetic drugs and three monoclonal antibody drugs have been approved for the treatment of hepatocellular carcinoma(HCC)since 2007.Whereas,the disadvantages of the above drugs such as low response rates,severe side effects,and drug resistance hamper their therapeutic effects.Structurally and biologically diverse natural products are a major source in the search for novel antihepatoma agents.

Mesoporous carbon layer encapsulated SnSe nanosheets via covalent bonds for high-performance sodium ion batteries

Sodium ion batteries(SIBs)have been widely studied because of their low cost,low standard redox potential,and abundant sodium availability.However,the structural rupture during the Na+insertion/extraction processes and the poor conductivity of the anode material limit its cycling stability and rate capability.Herein,SnSe@C was prepared by high-temperature annealing with dopamine hydrochloride as the carbon source,while SnSe was prepared by a protein reduction method.The carbon layer not only works as a protective layer to limit the volume expansion of SnSe and reduce the dissolution of Na 2 Se and poly-selenides generated during the discharge process in the electrolyte,but also as a conductive matrix to expedite electron transfer,thereby boosting the cycling stability and rate capability of SnSe@C.Benefiting from the above advantages,SnSe@C exhibits a specific capacity of 211.3 mAh g^(−1) at 0.1 A g^(−1) after 110 cycles and outstanging rate capability(210.1 mAh g^(−1) at 5.0 A g^(−1) and capacity retention rate of 63.2%from 0.1 to 1.0 A g^(−1)).This study not only proposes an idea for promoting the cycling stability and rate capability of SnSe,but also paves the way for providing anodic materials with a stable structure for SIBs.

通航隧道内船行波传播特性及对船舶连续通航安全影响

为填补通航隧道船舶通航安全关键技术研究的空白,基于完全非线性Boussinesq方程的开源程序包FUNWAVETVD建立了直线运河中通航隧道内船行波运动的数值模型,重点分析了船舶在通航隧道中诱导生成的船首孤立波波高以及波速的时空分布规律,并讨论了船行波对船舶连续通航的安全影响.研究得到了最大船首孤立波波高ηmax与船舶吃水P、Fr、通航隧道的水深、宽度以及船型的多元非线性回归方程;基于孤立波波面方程的理论假设,对通航隧道内船首孤立波的波速进行分析,发现船首孤立波的前波面与孤立波波面方程吻合较好,以孤立波的理论波速作为船首孤立波的传播速度,给出了通航隧道内船舶连续通航时安全航距应满足的关系式.结果表明,该模型能较好地捕捉船行波在通航隧道中的传播演变过程.研究结果可为单线直线运河中通航隧道的设计提供参考和依据,并可为通航隧道船舶通航安全关键技术标准或规范的制定奠定理论基础.

Pavement crack image acquisition methods and crack extraction algorithms:A review

The extraction of pavement cracks is always a hard task in image processing.In airport and road construction,cracking is the main factor for pavement damage,which can decrease the quality of pavement and affect transportation seriously.Cracks also exist in other artificial or natural objects,such as buildings,bridges,tunnels,etc.Among all the object images,pavement crack images are the most complex,so the image processing and analysis for them is harder than other crack images.From the early image acquisition based on photography technology to the current 3 D laser scanning technology,the pavement crack image acquisition technology is becoming more convenient and efficient,but there are still challenges in the automatic processing and recognition of cracks in images.From the early global thresholding to deep learning algorithms,the research for crack extraction has been developed for about 40 years.There are many methods and algorithms that are satisfactory in pavement crack applications,but there is no standard until today.Therefore,in order to know the developing history and the advanced research,we have collected a number of literature in this research topic for summarizing the research artwork status,and giving a review of the pavement crack image acquisition methods and2 D crack extraction algorithms.Also,for image acquisition methods and pavement crack image segmentation,more detailed comparison and discussions are made.

p190A inactivating mutations cause aberrant RhoA activation and promote malignant transformation via the Hippo-YAP pathway in endometrial cancer

The Rho family of GTPases is strictly regulated by a large family of GTPase-activating proteins(GAPs)that stimulate the relatively weak intrinsic GTP-hydrolyzing activity of Rho GTPases.p190A is a potent and widely expressed GAP that acts on RhoA GTPases.p190A is frequently mutated in endometrial cancer,but the contribution of p190A mutations to endometrial tumorigenesis remains unclear.Here we identified that p190A is an upstream regulator of the Hippo-YAP signaling pathway,which is a critical regulator of cell proliferation,apoptosis,and cell fate.p190A knockout in endometrial cancer cells promoted cell proliferation,migration,and epithelial–mesenchymal transition(EMT),which were partially dependent on YAP activation.Wild-type p190A,but not endometrial cancer-associated mutants,suppressed the nuclear localization,transcriptional activity,and malignant transformation function of YAP.Moreover,the nuclear localization of YAP was enhanced in p190A-mutated endometrial cancer.These findings reveal novel molecular mechanisms underlying Hippo-YAP pathway-driven endometrial tumorigenesis and elucidate the potential for therapy targeting the Hippo-YAP pathway in p190A-mutated endometrial cancer.

A review of deep learning methods for pixel-level crack detection

Cracks are a major sign of aging transportation infrastructure.The detection and repair of cracks is the key to ensuring the overall safety of the transportation infrastructure.In recent years,due to the remarkable success of deep learning(DL)in the field of crack detection,many researches have been devoted to developing pixel-level crack image segmentation(CIS)models based on DL to improve crack detection accuracy,but as far as we know there is no review of DL-based CIS methods yet.To address this gap,we present a comprehensive thematic survey of DL-based CIS techniques.Our review offers several contributions to the CIS area.First,more than 40 papers of journal or top conference most published in the last three years are identified and collected based on the systematic literature review method.Second,according to the backbone network architecture of the models proposed in them,they are grouped into 10 topics:FCN,U-Net,encoder-decoder model,multi-scale,attention mechanism,transformer,two-stage detection,multi-modal fusion,unsupervised learning and weakly supervised learning,to be reviewed.Meanwhile,our survey focuses on discussing strengths and limitations of the models in each topic so as to reveal the latest research progress in the CIS field.Third,publicly accessible data sets,evaluation metrics,and loss functions that can be used for pixel-level crack detection are systematically introduced and summarized to facilitate researchers to select suitable components according to their own research tasks.Finally,we discuss six common problems and existing solutions to them in the field of DL-based CIS,and then suggest eight possible future research directions in this field.

Mitochondria as multifaceted regulators of ferroptosis

Mitochondria are well known to be“energy factories”of the cell as they provide intracellular ATP via oxidative phosphorylation.Interestingly,they also function as a“cellular suicidal weapon store”by acting as a key mediator of various forms of regulated cell death,including apoptosis,pyroptosis,necroptosis,and ferroptosis.Ferroptosis,distinct from the other types of regulated cell death,is characterized by iron-dependent lipid peroxidation and subsequent plasma membrane rupture.Growing evidence suggests that an impaired ferroptotic response is implicated in various diseases and pathological conditions,and this impaired response is associated with dramatic changes in mitochondrial morphology and function.Mitochondria are the center of iron metabolism and energy production,leading to altered lipid peroxidation sensitivity.Although a growing number of studies have explored the inextricable link between mitochondria and ferroptosis,the role of this organelle in regulating ferroptosis remains unclear.Here,we review recent advances in our understanding of the role of mitochondria in ferroptosis and summarize the characteristics of this novel iron-based cellular suicide weapon and its arsenal.We also discuss the importance of ferroptosis in pathophysiology,including the need for further understanding of the relationship between mitochondria and ferroptosis to identify combinatorial targets that are essential for the development of successful drug discovery.