Range estimation of few-shot underwater sound source in shallow water based on transfer learning and residual CNN

Taking the real part and the imaginary part of complex sound pressure of the sound field as features,a transfer learning model is constructed.Based on the pre-training of a large amount of underwater acoustic data in the preselected sea area using the convolutional neural network(CNN),the few-shot underwater acoustic data in the test sea area are retrained to study the underwater sound source ranging problem.The S5 voyage data of SWellEX-96 experiment is used to verify the proposed method,realize the range estimation for the shallow source in the experiment,and compare the range estimation performance of the underwater target sound source of four methods:matched field processing(MFP),generalized regression neural network(GRNN),traditional CNN,and transfer learning.Experimental data processing results show that the transfer learning model based on residual CNN can effectively realize range estimation in few-shot scenes,and the estimation performance is remarkably better than that of other methods.

Generation of mitochondrial replacement monkeys by female pronucleus transfer

Mutations in mitochondrial DNA(mtDNA)are maternally inherited and have the potential to cause severe disorders.Mitochondrial replacement therapies,including spindle,polar body,and pronuclear transfers,are promising strategies for preventing the hereditary transmission of mtDNA diseases.While pronuclear transfer has been used to generate mitochondrial replacement mouse models and human embryos,its application in non-human primates has not been previously reported.In this study,we successfully generated four healthy cynomolgus monkeys(Macaca fascicularis)via female pronuclear transfer.These individuals all survived for more than two years and exhibited minimal mtDNA carryover(3.8%–6.7%),as well as relatively stable mtDNA heteroplasmy dynamics during development.The successful establishment of this nonhuman primate model highlights the considerable potential of pronuclear transfer in reducing the risk of inherited mtDNA diseases and provides a valuable preclinical research model for advancing mitochondrial replacement therapies in humans.

Part-Whole Relational Few-Shot 3D Point Cloud Semantic Segmentation

This paper focuses on the task of few-shot 3D point cloud semantic segmentation.Despite some progress,this task still encounters many issues due to the insufficient samples given,e.g.,incomplete object segmentation and inaccurate semantic discrimination.To tackle these issues,we first leverage part-whole relationships into the task of 3D point cloud semantic segmentation to capture semantic integrity,which is empowered by the dynamic capsule routing with the module of 3D Capsule Networks(CapsNets)in the embedding network.Concretely,the dynamic routing amalgamates geometric information of the 3D point cloud data to construct higher-level feature representations,which capture the relationships between object parts and their wholes.Secondly,we designed a multi-prototype enhancement module to enhance the prototype discriminability.Specifically,the single-prototype enhancement mechanism is expanded to the multi-prototype enhancement version for capturing rich semantics.Besides,the shot-correlation within the category is calculated via the interaction of different samples to enhance the intra-category similarity.Ablation studies prove that the involved part-whole relations and proposed multi-prototype enhancement module help to achieve complete object segmentation and improve semantic discrimination.Moreover,under the integration of these two modules,quantitative and qualitative experiments on two public benchmarks,including S3DIS and ScanNet,indicate the superior performance of the proposed framework on the task of 3D point cloud semantic segmentation,compared to some state-of-the-art methods.

Comparing Fine-Tuning, Zero and Few-Shot Strategies with Large Language Models in Hate Speech Detection in English

Large Language Models(LLMs)are increasingly demonstrating their ability to understand natural language and solve complex tasks,especially through text generation.One of the relevant capabilities is contextual learning,which involves the ability to receive instructions in natural language or task demonstrations to generate expected outputs for test instances without the need for additional training or gradient updates.In recent years,the popularity of social networking has provided a medium through which some users can engage in offensive and harmful online behavior.In this study,we investigate the ability of different LLMs,ranging from zero-shot and few-shot learning to fine-tuning.Our experiments show that LLMs can identify sexist and hateful online texts using zero-shot and few-shot approaches through information retrieval.Furthermore,it is found that the encoder-decoder model called Zephyr achieves the best results with the fine-tuning approach,scoring 86.811%on the Explainable Detection of Online Sexism(EDOS)test-set and 57.453%on the Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter(HatEval)test-set.Finally,it is confirmed that the evaluated models perform well in hate text detection,as they beat the best result in the HatEval task leaderboard.The error analysis shows that contextual learning had difficulty distinguishing between types of hate speech and figurative language.However,the fine-tuned approach tends to produce many false positives.

Embryo Transfer Strategies for Women with Recurrent Implantation Failure During the Frozen-thawed Embryo Transfer Cycles:Sequential Embryo Transfer or Double-blastocyst Transfer?

Objective Both sequential embryo transfer(SeET)and double-blastocyst transfer(DBT)can serve as embryo transfer strategies for women with recurrent implantation failure(RIF).This study aims to compare the effects of SeET and DBT on pregnancy outcomes.Methods Totally,261 frozen-thawed embryo transfer cycles of 243 RIF women were included in this multicenter retrospective analysis.According to different embryo quality and transfer strategies,they were divided into four groups:group A,good-quality SeET(GQ-SeET,n=38 cycles);group B,poor-quality or mixed-quality SeET(PQ/MQ-SeET,n=31 cycles);group C,good-quality DBT(GQ-DBT,n=121 cycles);and group D,poor-quality or mixed-quality DBT(PQ/MQ-DBT,n=71 cycles).The main outcome,clinical pregnancy rate,was compared,and the generalized estimating equation(GEE)model was used to correct potential confounders that might impact pregnancy outcomes.Results GQ-DBT achieved a significantly higher clinical pregnancy rate(aOR 2.588,95%CI 1.267–5.284,P=0.009)and live birth rate(aOR 3.082,95%CI 1.482–6.412,P=0.003)than PQ/MQ-DBT.Similarly,the clinical pregnancy rate was significantly higher in GQ-SeET than in PQ/MQ-SeET(aOR 4.047,95%CI 1.218–13.450,P=0.023).The pregnancy outcomes of GQ-SeET were not significantly different from those of GQ-DBT,and the same results were found between PQ/MQ-SeET and PQ/MQ-DBT.Conclusion SeET relative to DBT did not seem to improve pregnancy outcomes for RIF patients if the embryo quality was comparable between the two groups.Better clinical pregnancy outcomes could be obtained by transferring good-quality embryos,no matter whether in SeET or DBT.Embryo quality plays a more important role in pregnancy outcomes for RIF patients.

Selective and Adaptive Incremental Transfer Learning with Multiple Datasets for Machine Fault Diagnosis

The visions of Industry 4.0 and 5.0 have reinforced the industrial environment.They have also made artificial intelligence incorporated as a major facilitator.Diagnosing machine faults has become a solid foundation for automatically recognizing machine failure,and thus timely maintenance can ensure safe operations.Transfer learning is a promising solution that can enhance the machine fault diagnosis model by borrowing pre-trained knowledge from the source model and applying it to the target model,which typically involves two datasets.In response to the availability of multiple datasets,this paper proposes using selective and adaptive incremental transfer learning(SA-ITL),which fuses three algorithms,namely,the hybrid selective algorithm,the transferability enhancement algorithm,and the incremental transfer learning algorithm.It is a selective algorithm that enables selecting and ordering appropriate datasets for transfer learning and selecting useful knowledge to avoid negative transfer.The algorithm also adaptively adjusts the portion of training data to balance the learning rate and training time.The proposed algorithm is evaluated and analyzed using ten benchmark datasets.Compared with other algorithms from existing works,SA-ITL improves the accuracy of all datasets.Ablation studies present the accuracy enhancements of the SA-ITL,including the hybrid selective algorithm(1.22%-3.82%),transferability enhancement algorithm(1.91%-4.15%),and incremental transfer learning algorithm(0.605%-2.68%).These also show the benefits of enhancing the target model with heterogeneous image datasets that widen the range of domain selection between source and target domains.

Performance Analysis and Optimization of Energy Harvesting Modulation for Multi-User Integrated Data and Energy Transfer

Integrated data and energy transfer(IDET)enables the electromagnetic waves to transmit wireless energy at the same time of data delivery for lowpower devices.In this paper,an energy harvesting modulation(EHM)assisted multi-user IDET system is studied,where all the received signals at the users are exploited for energy harvesting without the degradation of wireless data transfer(WDT)performance.The joint IDET performance is then analysed theoretically by conceiving a practical time-dependent wireless channel.With the aid of the AO based algorithm,the average effective data rate among users are maximized by ensuring the BER and the wireless energy transfer(WET)performance.Simulation results validate and evaluate the IDET performance of the EHM assisted system,which also demonstrates that the optimal number of user clusters and IDET time slots should be allocated,in order to improve the WET and WDT performance.

Fully polarized Compton scattering in plane waves and its polarization transfer

Fully polarized Compton scattering from a beam of spin-polarized electrons is investigated in plane-wave backgrounds in a broad intensity region from the perturbative to the nonperturbative regimes.In the perturbative regime,polarized linear Compton scattering is considered for investigating polarization transfer from a single laser photon to a scattered photon,and in the high-intensity region,the polarized locally monochromatic approximation and locally constant field approximation are established and are employed to study polarization transfer from an incoming electron to a scattered photon.The numerical results suggest an appreciable improvement of about 10%in the scattering probability in the intermediate-intensity region if the electron’s longitudinal spin is parallel to the laser rotation.The longitudinal spin of the incoming electron can be transferred to the scattered photon with an efficiency that increases with laser intensity and collisional energy.For collision between an optical laser with frequency1 eV and a 10 GeV electron,this polarization transfer efficiency can increase from about 20%in the perturbative regime to about 50%in the nonperturbative regime for scattered photons with relatively high energy.

Efficient energy transfer from self-trapped excitons to Mn^(2+) dopants in CsCdCl_(3):Mn^(2+) perovskite nanocrystals

Mn^(2+)doping has been adopted as an efficient approach to regulating the luminescence properties of halide perovskite nano-crystals(NCs).However,it is still difficult to understand the interplay of Mn^(2+)luminescence and the matrix self-trapped exciton(STE)emission therein.In this study,Mn^(2+)-doped CsCdCl_(3) NCs are prepared by hot injection,in which CsCdCl_(3) is selected because of its unique crystal structure suitable for STE emission.The blue emission at 441 nm of undoped CsCdCl_(3) NCs originates from the defect states in the NCs.Mn^(2+)doping promotes lattice distortion of CsCdCl_(3) and generates bright orange-red light emission at 656 nm.The en-ergy transfer from the STEs of CsCdCl_(3) to the excited levels of the Mn^(2+)ion is confirmed to be a significant factor in achieving efficient luminescence in CsCdCl_(3):Mn^(2+)NCs.This work highlights the crucial role of energy transfer from STEs to Mn^(2+)dopants in Mn^(2+)-doped halide NCs and lays the groundwork for modifying the luminescence of other metal halide perovskite NCs.

P-induced electron transfer interaction for enhanced selective hydrogenation rearrangement of furfural to cyclopentanone

Optimizing the intrinsic activity of non-noble metal by precisely tailoring electronic structure offers an appealing way to construct cost-effective catalysts for selective biomass valorization.Herein,we reported a P-doping bifunctional catalyst(Ni-P/mSiO_(2))that achieved 96.6%yield for the hydrogenation rearrangement of furfural to cyclopentanone at mild conditions(1 MPaH_(2),150°C).The turnover frequency of Ni-P/mSiO_(2)was 411.9 h^(-1),which was 3.2-fold than that of Ni/mSiO_(2)(127.2 h^(-1)).Detailed characterizations and differential charge density calculations revealed that the electron-deficient Niδ+species were generated by the electron transfer from Ni to P,which promoted the ring rearrangement reaction.Density functional theory calculations illustrated that the presence of P atoms endowed furfural tilted adsorb on the Ni surface by the C=O group and facilitated the desorption of cyclopentanone.This work unraveled the connection between the localized electronic structures and the catalytic properties,so as to provide a promising reference for designing advanced catalysts for biomass valorization.

Effect of surfactant frequently used in soil flushing on oxygen mass transfer in micro-nano-bubble aeration system

In-site soil flushing and aeration are the typical synergetic remediation technology for contaminated sites.The surfactant present in flushing solutions is bound to affect the aeration efficiency.The purpose of this study is to evaluate the effect of surfactant frequently used in soil flushing on the oxygen mass transfer in micro-nano-bubble(MNB)aeration system.Firstly,bio-surfactants and chemical surfactants were used to investigate their effects on Sauter mean diameter of bubble(dBS),gas holdup(ε),volumetric mass-transfer coefficient(kLa)and liquid-side mass-transfer coefficient(kL)in the MNB aeration system.Then,based upon the experimental results,the Sardeing's and Frossling's models were modified to describe the effect of surfactant on kL in the MNB aeration.The results showed that,for the twenty aqueous surfactant solutions,with the increase in surfactant concentration,the value of dBS,kLa and kL decreased,while the value ofεand gas-liquid interfacial area(a)increased.These phenomena were mainly attributed to the synergistic effects of immobile bubble surface and the suppression of coalescence in the surfactant solutions.In addition,with the presence of electric charge,MNBs in anionic surfactant solutions were smaller and higher in number than in non-ionic surfactant solutions.Furthermore,the accumulation of surfactant on the gas-liquid interface was more conspicuous for small MNB,so the reduction of kL in anionic surfactant solutions was larger than that in non-ionic surfactant solutions.Besides,the modified Frossling's model predicted the effect of surfactant on kL in MNB aeration system with reasonable accuracy.

Robust free-space optical frequency transfer in time-varying link distances conditions

Future inter-satellite clock comparison on high orbit will require optical time and frequency transmission technology between moving objects.Here,we demonstrate robust optical frequency transmission under the condition of variable link distance.This variable link is accomplished by the relative motion of a single telescope fixed on the experimental platform to a corner-cube reflector(CCR)installed on a sliding guide.Two acousto–optic modulators with different frequencies are used to separate forward signal from backward signal.With active phase noise suppression,when the CCR moves back and forth at a constant velocity of 20 cm/s and an acceleration of 20 cm/s^(2),we achieve the best frequency stability of 1.9×10^(-16) at 1 s and 7.9×10^(-19) at 1000 s indoors.This work paves the way for future studying optical frequency transfer between ultra-high-orbit satellites.

Robust Information Hiding Based on Neural Style Transfer with Artificial Intelligence

This paper proposes an artificial intelligence-based robust information hiding algorithm to address the issue of confidential information being susceptible to noise attacks during transmission.The algorithm we designed aims to mitigate the impact of various noise attacks on the integrity of secret information during transmission.The method we propose involves encoding secret images into stylized encrypted images and applies adversarial transfer to both the style and content features of the original and embedded data.This process effectively enhances the concealment and imperceptibility of confidential information,thereby improving the security of such information during transmission and reducing security risks.Furthermore,we have designed a specialized attack layer to simulate real-world attacks and common noise scenarios encountered in practical environments.Through adversarial training,the algorithm is strengthened to enhance its resilience against attacks and overall robustness,ensuring better protection against potential threats.Experimental results demonstrate that our proposed algorithm successfully enhances the concealment and unknowability of secret information while maintaining embedding capacity.Additionally,it ensures the quality and fidelity of the stego image.The method we propose not only improves the security and robustness of information hiding technology but also holds practical application value in protecting sensitive data and ensuring the invisibility of confidential information.

Image Recognition Model of Fraudulent Websites Based on Image Leader Decision and Inception-V3 Transfer Learning

The fraudulent website image is a vital information carrier for telecom fraud.The efficient and precise recognition of fraudulent website images is critical to combating and dealing with fraudulent websites.Current research on image recognition of fraudulent websites is mainly carried out at the level of image feature extraction and similarity study,which have such disadvantages as difficulty in obtaining image data,insufficient image analysis,and single identification types.This study develops a model based on the entropy method for image leader decision and Inception-v3 transfer learning to address these disadvantages.The data processing part of the model uses a breadth search crawler to capture the image data.Then,the information in the images is evaluated with the entropy method,image weights are assigned,and the image leader is selected.In model training and prediction,the transfer learning of the Inception-v3 model is introduced into image recognition of fraudulent websites.Using selected image leaders to train the model,multiple types of fraudulent websites are identified with high accuracy.The experiment proves that this model has a superior accuracy in recognizing images on fraudulent websites compared to other current models.

Effects of projectile parameters on the momentum transfer and projectile melting during hypervelocity impact

The effects of projectile/target impedance matching and projectile shape on energy,momentum transfer and projectile melting during collisions are investigated by numerical simulation.By comparing the computation results with the experimental results,the correctness of the calculation and the statistical method of momentum transfer coefficient is verified.Different shapes of aluminum,copper and heavy tungsten alloy projectiles striking aluminum,basalt,and pumice target for impacts up to 10 km/s are simulated.The influence mechanism of the shape of the projectile and projectile/target density on the momentum transfer was obtained.With an increase in projectile density and length-diameter ratio,the energy transfer time between the projectile and targets is prolonged.The projectile decelerates slowly,resulting in a larger cratering depth.The energy consumed by the projectile in the excavation stage increased,resulting in lower mass-velocity of ejecta and momentum transfer coefficient.The numerical simulation results demonstrated that for different projectile/target combinations,the higher the wave impedance of the projectile,the higher the initial phase transition velocity and the smaller the mass of phase transition.The results can provide theoretical guidance for kinetic impactor design and material selection.

Quick Weighing of Passing Vehicles Using the Transfer-Learning-Enhanced Convolutional Neural Network

Transfer learning could reduce the time and resources required by the training of new models and be therefore important for generalized applications of the trainedmachine learning algorithms.In this study,a transfer learningenhanced convolutional neural network(CNN)was proposed to identify the gross weight and the axle weight of moving vehicles on the bridge.The proposed transfer learning-enhanced CNN model was expected to weigh different bridges based on a small amount of training datasets and provide high identification accuracy.First of all,a CNN algorithm for bridge weigh-in-motion(B-WIM)technology was proposed to identify the axle weight and the gross weight of the typical two-axle,three-axle,and five-axle vehicles as they crossed the bridge with different loading routes and speeds.Then,the pre-trained CNN model was transferred by fine-tuning to weigh themoving vehicle on another bridge.Finally,the identification accuracy and the amount of training data required were compared between the two CNN models.Results showed that the pre-trained CNN model using transfer learning for B-WIM technology could be successfully used for the identification of the axle weight and the gross weight for moving vehicles on another bridge while reducing the training data by 63%.Moreover,the recognition accuracy of the pre-trained CNN model using transfer learning was comparable to that of the original model,showing its promising potentials in the actual applications.

Knowledge Reasoning Method Based on Deep Transfer Reinforcement Learning:DTRLpath

In recent years,with the continuous development of deep learning and knowledge graph reasoning methods,more and more researchers have shown great interest in improving knowledge graph reasoning methods by inferring missing facts through reasoning.By searching paths on the knowledge graph and making fact and link predictions based on these paths,deep learning-based Reinforcement Learning(RL)agents can demonstrate good performance and interpretability.Therefore,deep reinforcement learning-based knowledge reasoning methods have rapidly emerged in recent years and have become a hot research topic.However,even in a small and fixed knowledge graph reasoning action space,there are still a large number of invalid actions.It often leads to the interruption of RL agents’wandering due to the selection of invalid actions,resulting in a significant decrease in the success rate of path mining.In order to improve the success rate of RL agents in the early stages of path search,this article proposes a knowledge reasoning method based on Deep Transfer Reinforcement Learning path(DTRLpath).Before supervised pre-training and retraining,a pre-task of searching for effective actions in a single step is added.The RL agent is first trained in the pre-task to improve its ability to search for effective actions.Then,the trained agent is transferred to the target reasoning task for path search training,which improves its success rate in searching for target task paths.Finally,based on the comparative experimental results on the FB15K-237 and NELL-995 datasets,it can be concluded that the proposed method significantly improves the success rate of path search and outperforms similar methods in most reasoning tasks.

Coherent optical frequency transfer via 972-km fiber link

We demonstrate coherent optical frequency dissemination over a distance of 972 km by cascading two spans where the phase noise is passively compensated for.Instead of employing a phase discriminator and a phase locking loop in the conventional active phase control scheme,the passive phase noise cancellation is realized by feeding double-trip beat-note frequency to the driver of the acoustic optical modulator at the local site.This passive scheme exhibits fine robustness and reliability,making it suitable for long-distance and noisy fiber links.An optical regeneration station is used in the link for signal amplification and cascaded transmission.The phase noise cancellation and transfer instability of the 972-km link is investigated,and transfer instability of 1.1×10^(-19)at 10^(4)s is achieved.This work provides a promising method for realizing optical frequency distribution over thousands of kilometers by using fiber links.

Optimal and robust control of population transfer in asymmetric quantum-dot molecules

We present an optimal and robust quantum control method for efficient population transfer in asymmetric double quantum-dot molecules.We derive a long-duration control scheme that allows for highly efficient population transfer by accurately controlling the amplitude of a narrow-bandwidth pulse.To overcome fluctuations in control field parameters,we employ a frequency-domain quantum optimal control theory method to optimize the spectral phase of a single pulse with broad bandwidth while preserving the spectral amplitude.It is shown that this spectral-phase-only optimization approach can successfully identify robust and optimal control fields,leading to efficient population transfer to the target state while concurrently suppressing population transfer to undesired states.The method demonstrates resilience to fluctuations in control field parameters,making it a promising approach for reliable and efficient population transfer in practical applications.

Interpolated Bumpless Transfer Control for Asynchronously Switched Linear Systems

This paper revisits the problem of bumpless transfer control(BTC) for discrete-time nondeterministic switched linear systems. The general case of asynchronous switching is considered for the first time in the field of BTC for switched systems. A new approach called interpolated bumpless transfer control(IBTC) is proposed, where the bumpless transfer controllers are formulated with the combination of the two adjacent modedependent controller gains, and are interpolated for finite steps once the switching is detected. In contrast with the existing approaches, IBTC does not necessarily run through the full interval of subsystems, as well as possesses the time-varying controller gains(with more flexibility and less conservatism) achieved from a control synthesis allowing for the stability and other performance of the whole switched system. Sufficient conditions ensuring stability and H_(∞) performance of the underlying system by IBTC are developed, and numerical examples verify the theoretical findings.