With the rapid advancement of visual generative models such as Generative Adversarial Networks(GANs)and stable Diffusion,the creation of highly realistic Deepfake through automated forgery has significantly progressed...With the rapid advancement of visual generative models such as Generative Adversarial Networks(GANs)and stable Diffusion,the creation of highly realistic Deepfake through automated forgery has significantly progressed.This paper examines the advancements inDeepfake detection and defense technologies,emphasizing the shift from passive detection methods to proactive digital watermarking techniques.Passive detection methods,which involve extracting features from images or videos to identify forgeries,encounter challenges such as poor performance against unknown manipulation techniques and susceptibility to counter-forensic tactics.In contrast,proactive digital watermarking techniques embed specificmarkers into images or videos,facilitating real-time detection and traceability,thereby providing a preemptive defense againstDeepfake content.We offer a comprehensive analysis of digitalwatermarking-based forensic techniques,discussing their advantages over passivemethods and highlighting four key benefits:real-time detection,embedded defense,resistance to tampering,and provision of legal evidence.Additionally,the paper identifies gaps in the literature concerning proactive forensic techniques and suggests future research directions,including cross-domain watermarking and adaptive watermarking strategies.By systematically classifying and comparing existing techniques,this review aims to contribute valuable insights for the development of more effective proactive defense strategies in Deepfake forensics.展开更多
Gas content serves as a critical indicator for assessing the resource potential of deep coal mines and forecasting coal mine gas outburst risks.However,existing sampling technologies face challenges in maintaining the...Gas content serves as a critical indicator for assessing the resource potential of deep coal mines and forecasting coal mine gas outburst risks.However,existing sampling technologies face challenges in maintaining the integrity of gas content within samples and are often constrained by estimation errors inherent in empirical formulas,which results in inaccurate gas content measurements.This study introduces a lightweight,in-situ pressure-and gas-preserved corer designed to collect coal samples under the pressure conditions at the sampling point,effectively preventing gas loss during transfer and significantly improving measurement accuracy.Additionally,a gas migration model for deep coal mines was developed to elucidate gas migration characteristics under pressure-preserved coring conditions.The model offers valuable insights for optimizing coring parameters,demonstrating that both minimizing the coring hole diameter and reducing the pressure difference between the coring-point pressure and the original pore pressure can effectively improve the precision of gas content measurements.Coring tests conducted at an experimental base validated the performance of the corer and its effectiveness in sample collection.Furthermore,successful horizontal coring tests conducted in an underground coal mine roadway demonstrated that the measured gas content using pressure-preserved coring was 34%higher than that obtained through open sampling methods.展开更多
The rapid evolution of malware presents a critical cybersecurity challenge,rendering traditional signature-based detection methods ineffective against novel variants.This growing threat affects individuals,organizatio...The rapid evolution of malware presents a critical cybersecurity challenge,rendering traditional signature-based detection methods ineffective against novel variants.This growing threat affects individuals,organizations,and governments,highlighting the urgent need for robust malware detection mechanisms.Conventional machine learning-based approaches rely on static and dynamicmalware analysis and often struggle to detect previously unseen threats due to their dependency on predefined signatures.Although machine learning algorithms(MLAs)offer promising detection capabilities,their reliance on extensive feature engineering limits real-time applicability.Deep learning techniques mitigate this issue by automating feature extraction but may introduce computational overhead,affecting deployment efficiency.This research evaluates classical MLAs and deep learningmodels to enhance malware detection performance across diverse datasets.The proposed approach integrates a novel text and imagebased detection framework,employing an optimized Support Vector Machine(SVM)for textual data analysis and EfficientNet-B0 for image-based malware classification.Experimental analysis,conducted across multiple train-test splits over varying timescales,demonstrates 99.97%accuracy on textual datasets using SVM and 96.7%accuracy on image-based datasets with EfficientNet-B0,significantly improving zero-day malware detection.Furthermore,a comparative analysis with existing competitive techniques,such as Random Forest,XGBoost,and CNN-based(Convolutional Neural Network)classifiers,highlights the superior performance of the proposed model in terms of accuracy,efficiency,and robustness.展开更多
In recent years,Speech Emotion Recognition(SER)has developed into an essential instrument for interpreting human emotions from auditory data.The proposed research focuses on the development of a SER system employing d...In recent years,Speech Emotion Recognition(SER)has developed into an essential instrument for interpreting human emotions from auditory data.The proposed research focuses on the development of a SER system employing deep learning and multiple datasets containing samples of emotive speech.The primary objective of this research endeavor is to investigate the utilization of Convolutional Neural Networks(CNNs)in the process of sound feature extraction.Stretching,pitch manipulation,and noise injection are a few of the techniques utilized in this study to improve the data quality.Feature extraction methods including Zero Crossing Rate,Chroma_stft,Mel⁃scale Frequency Cepstral Coefficients(MFCC),Root Mean Square(RMS),and Mel⁃Spectogram are used to train a model.By using these techniques,audio signals can be transformed into recognized features that can be utilized to train the model.Ultimately,the study produces a thorough evaluation of the models performance.When this method was applied,the model achieved an impressive accuracy of 94.57%on the test dataset.The proposed work was also validated on the EMO⁃BD and IEMOCAP datasets.These consist of further data augmentation,feature engineering,and hyperparameter optimization.By following these development paths,SER systems will be able to be implemented in real⁃world scenarios with greater accuracy and resilience.展开更多
Many bioinformatics applications require determining the class of a newly sequenced Deoxyribonucleic acid(DNA)sequence,making DNA sequence classification an integral step in performing bioinformatics analysis,where la...Many bioinformatics applications require determining the class of a newly sequenced Deoxyribonucleic acid(DNA)sequence,making DNA sequence classification an integral step in performing bioinformatics analysis,where large biomedical datasets are transformed into valuable knowledge.Existing methods rely on a feature extraction step and suffer from high computational time requirements.In contrast,newer approaches leveraging deep learning have shown significant promise in enhancing accuracy and efficiency.In this paper,we investigate the performance of various deep learning architectures:Convolutional Neural Network(CNN),CNN-Long Short-Term Memory(CNNLSTM),CNN-Bidirectional Long Short-Term Memory(CNN-BiLSTM),Residual Network(ResNet),and InceptionV3 for DNA sequence classification.Various numerical and visual data representation techniques are utilized to represent the input datasets,including:label encoding,k-mer sentence encoding,k-mer one-hot vector,Frequency Chaos Game Representation(FCGR)and 5-Color Map(ColorSquare).Three datasets are used for the training of the models including H3,H4 and DNA Sequence Dataset(Yeast,Human,Arabidopsis Thaliana).Experiments are performed to determine which combination of DNA representation and deep learning architecture yields improved performance for the classification task.Our results indicate that using a hybrid CNN-LSTM neural network trained on DNA sequences represented as one-hot encoded k-mer sequences yields the best performance,achieving an accuracy of 92.1%.展开更多
In this investigation,we meticulously annotated a corpus of 21,174 auroral images captured by the THEMIS All-Sky Imager across diverse temporal instances.These images were categorized using an array of descriptors suc...In this investigation,we meticulously annotated a corpus of 21,174 auroral images captured by the THEMIS All-Sky Imager across diverse temporal instances.These images were categorized using an array of descriptors such as'arc','ab'(aurora but bright),'cloudy','diffuse','discrete',and'clear'.Subsequently,we utilized a state-of-the-art convolutional neural network,ConvNeXt(Convolutional Neural Network Next),deploying deep learning techniques to train the model on a dataset classified into six distinct categories.Remarkably,on the test set our methodology attained an accuracy of 99.4%,a performance metric closely mirroring human visual observation,thereby underscoring the classifier’s competence in paralleling human perceptual accuracy.Building upon this foundation,we embarked on the identification of large-scale auroral optical data,meticulously quantifying the monthly occurrence and Magnetic Local Time(MLT)variations of auroras from stations at different latitudes:RANK(high-latitude),FSMI(mid-latitude),and ATHA(low-latitude),under different solar wind conditions.This study paves the way for future explorations into the temporal variations of auroral phenomena in diverse geomagnetic contexts.展开更多
Deep learning(DL)has revolutionized time series forecasting(TSF),surpassing traditional statistical methods(e.g.,ARIMA)and machine learning techniques in modeling complex nonlinear dynamics and long-term dependencies ...Deep learning(DL)has revolutionized time series forecasting(TSF),surpassing traditional statistical methods(e.g.,ARIMA)and machine learning techniques in modeling complex nonlinear dynamics and long-term dependencies prevalent in real-world temporal data.This comprehensive survey reviews state-of-the-art DL architectures forTSF,focusing on four core paradigms:(1)ConvolutionalNeuralNetworks(CNNs),adept at extracting localized temporal features;(2)Recurrent Neural Networks(RNNs)and their advanced variants(LSTM,GRU),designed for sequential dependency modeling;(3)Graph Neural Networks(GNNs),specialized for forecasting structured relational data with spatial-temporal dependencies;and(4)Transformer-based models,leveraging self-attention mechanisms to capture global temporal patterns efficiently.We provide a rigorous analysis of the theoretical underpinnings,recent algorithmic advancements(e.g.,TCNs,attention mechanisms,hybrid architectures),and practical applications of each framework,supported by extensive benchmark datasets(e.g.,ETT,traffic flow,financial indicators)and standardized evaluation metrics(MAE,MSE,RMSE).Critical challenges,including handling irregular sampling intervals,integrating domain knowledge for robustness,and managing computational complexity,are thoroughly discussed.Emerging research directions highlighted include diffusion models for uncertainty quantification,hybrid pipelines combining classical statistical and DL techniques for enhanced interpretability,quantile regression with Transformers for riskaware forecasting,and optimizations for real-time deployment.This work serves as an essential reference,consolidating methodological innovations,empirical resources,and future trends to bridge the gap between theoretical research and practical implementation needs for researchers and practitioners in the field.展开更多
DeepSeek Chinese artificial intelligence(AI)open-source model,has gained a lot of attention due to its economical training and efficient inference.DeepSeek,a model trained on large-scale reinforcement learning without...DeepSeek Chinese artificial intelligence(AI)open-source model,has gained a lot of attention due to its economical training and efficient inference.DeepSeek,a model trained on large-scale reinforcement learning without supervised fine-tuning as a preliminary step,demonstrates remarkable reasoning capabilities of performing a wide range of tasks.DeepSeek is a prominent AI-driven chatbot that assists individuals in learning and enhances responses by generating insightful solutions to inquiries.Users possess divergent viewpoints regarding advanced models like DeepSeek,posting both their merits and shortcomings across several social media platforms.This research presents a new framework for predicting public sentiment to evaluate perceptions of DeepSeek.To transform the unstructured data into a suitable manner,we initially collect DeepSeek-related tweets from Twitter and subsequently implement various preprocessing methods.Subsequently,we annotated the tweets utilizing the Valence Aware Dictionary and sentiment Reasoning(VADER)methodology and the lexicon-driven TextBlob.Next,we classified the attitudes obtained from the purified data utilizing the proposed hybrid model.The proposed hybrid model consists of long-term,shortterm memory(LSTM)and bidirectional gated recurrent units(BiGRU).To strengthen it,we include multi-head attention,regularizer activation,and dropout units to enhance performance.Topic modeling employing KMeans clustering and Latent Dirichlet Allocation(LDA),was utilized to analyze public behavior concerning DeepSeek.The perceptions demonstrate that 82.5%of the people are positive,15.2%negative,and 2.3%neutral using TextBlob,and 82.8%positive,16.1%negative,and 1.2%neutral using the VADER analysis.The slight difference in results ensures that both analyses concur with their overall perceptions and may have distinct views of language peculiarities.The results indicate that the proposed model surpassed previous state-of-the-art approaches.展开更多
Addressing plant diseases and pests is not just crucial;it’s a matter of utmost importance for enhancing crop production and preventing economic losses. Recent advancements in artificial intelligence, machine learnin...Addressing plant diseases and pests is not just crucial;it’s a matter of utmost importance for enhancing crop production and preventing economic losses. Recent advancements in artificial intelligence, machine learning, and deep learning have revolutionised the precision and efficiency of this process, surpassing the limitations of manual identification. This study comprehensively reviews modern computer-based techniques, including recent advances in artificial intelligence, for detecting diseases and pests through images. This paper uniquely categorises methodologies into hyperspectral imaging, non-visualisation techniques, visualisation approaches, modified deep learning architectures, and transformer models, helping researchers gain detailed, insightful understandings. The exhaustive survey of recent works and comparative studies in this domain guides researchers in selecting appropriate and advanced state-of-the-art methods for plant disease and pest detection. Additionally, this paper highlights the consistent superiority of modern AI-based approaches, which often outperform older image analysis methods in terms of speed and accuracy. Further, this survey focuses on the efficiency of vision transformers against well-known deep learning architectures like MobileNetV3, which shows that Hierarchical Vision Transformer (HvT) can achieve accuracy upwards of 99.3% in plant disease detection. The study concludes by addressing the challenges of designing the systems, proposing potential solutions, and outlining directions for future research in this field.展开更多
Automated cartoon character recognition is crucial for applications in content indexing,filtering,and copyright protection,yet it faces a significant challenge in animated media due to high intra-class visual variabil...Automated cartoon character recognition is crucial for applications in content indexing,filtering,and copyright protection,yet it faces a significant challenge in animated media due to high intra-class visual variability,where characters frequently alter their appearance.To address this problem,we introduce the novel Kral Sakir dataset,a public benchmark of 16,725 images specifically curated for the task of multi-label cartoon character classification under these varied conditions.This paper conducts a comprehensive benchmark study,evaluating the performance of state-of-the-art pretrained Convolutional Neural Networks(CNNs),including DenseNet,ResNet,and VGG,against a custom baseline model trained from scratch.Our experiments,evaluated using metrics of F1-Score,accuracy,and Area Under the ROC Curve(AUC),demonstrate that fine-tuning pretrained models is a highly effective strategy.The best-performing model,DenseNet121,achieved an F1-Score of 0.9890 and an accuracy of 0.9898,significantly outperforming our baseline CNN(F1-Score of 0.9545).The findings validate the power of transfer learning for this domain and establish a strong performance benchmark.The introduced dataset provides a valuable resource for future research into developing robust and accurate character recognition systems.展开更多
The 3GPP standard defines the requirements for next-generation wireless networks,with particular attention to Ultra-Reliable Low-Latency Communications(URLLC),critical for applications such as Unmanned Aerial Vehicles...The 3GPP standard defines the requirements for next-generation wireless networks,with particular attention to Ultra-Reliable Low-Latency Communications(URLLC),critical for applications such as Unmanned Aerial Vehicles(UAVs).In this context,Non-Orthogonal Multiple Access(NOMA)has emerged as a promising technique to improve spectrum efficiency and user fairness by allowing multiple users to share the same frequency resources.However,optimizing key parameters–such as beamforming,rate allocation,and UAV trajectory–presents significant challenges due to the nonconvex nature of the problem,especially under stringent URLLC constraints.This paper proposes an advanced deep learning-driven approach to address the resulting complex optimization challenges.We formulate a downlink multiuser UAV,Rate-Splitting Multiple Access(RSMA),and Multiple Input Multiple Output(MIMO)system aimed at maximizing the achievable rate under stringent constraints,including URLLC quality-of-service(QoS),power budgets,rate allocations,and UAV trajectory limitations.Due to the highly nonconvex nature of the optimization problem,we introduce a novel distributed deep reinforcement learning(DRL)framework based on dual-agent deep deterministic policy gradient(DA-DDPG).The proposed framework leverages inception-inspired and deep unfolding architectures to improve feature extraction and convergence in beamforming and rate allocation.For UAV trajectory optimization,we design a dedicated actor-critic agent using a fully connected deep neural network(DNN),further enhanced through incremental learning.Simulation results validate the effectiveness of our approach,demonstrating significant performance gains over existing methods and confirming its potential for real-time URLLC in next-generation UAV communication networks.展开更多
The increased interest in geothermal energy is evident,along with the exploitation of traditional hydrothermal systems,in the growing research and projects developing around the reuse of already-drilled oil,gas,and ex...The increased interest in geothermal energy is evident,along with the exploitation of traditional hydrothermal systems,in the growing research and projects developing around the reuse of already-drilled oil,gas,and exploration wells.The Republic of Croatia has around 4000 wells,however,due to a long period since most of these wells were drilled and completed,there is uncertainty about how many are available for retrofitting as deep-borehole heat exchangers.Nevertheless,as hydrocarbon production decreases,it is expected that the number of wells available for the revitalization and exploitation of geothermal energy will increase.The revitalization of wells via deep-borehole heat exchangers involves installing a coaxial heat exchanger and circulating the working fluid in a closed system,during which heat is transferred from the surrounding rock medium to the circulating fluid.Since drilled wells are not of uniformdepth and are located in areas with different thermal rock properties and geothermal gradients,an analysis was conducted to determine available thermal energy as a function of well depth,geothermal gradient,and circulating fluid flow rate.Additionally,an economic analysis was performed to determine the benefits of retrofitting existing assets,such as drilled wells,compared to drilling new wells to obtain the same amount of thermal energy.展开更多
At present,energy consumption is one of the main bottlenecks in autonomous mobile robot development.To address the challenge of high energy consumption in path planning for autonomous mobile robots navigating unknown ...At present,energy consumption is one of the main bottlenecks in autonomous mobile robot development.To address the challenge of high energy consumption in path planning for autonomous mobile robots navigating unknown and complex environments,this paper proposes an Attention-Enhanced Dueling Deep Q-Network(ADDueling DQN),which integrates a multi-head attention mechanism and a prioritized experience replay strategy into a Dueling-DQN reinforcement learning framework.A multi-objective reward function,centered on energy efficiency,is designed to comprehensively consider path length,terrain slope,motion smoothness,and obstacle avoidance,enabling optimal low-energy trajectory generation in 3D space from the source.The incorporation of a multihead attention mechanism allows the model to dynamically focus on energy-critical state features—such as slope gradients and obstacle density—thereby significantly improving its ability to recognize and avoid energy-intensive paths.Additionally,the prioritized experience replay mechanism accelerates learning from key decision-making experiences,suppressing inefficient exploration and guiding the policy toward low-energy solutions more rapidly.The effectiveness of the proposed path planning algorithm is validated through simulation experiments conducted in multiple off-road scenarios.Results demonstrate that AD-Dueling DQN consistently achieves the lowest average energy consumption across all tested environments.Moreover,the proposed method exhibits faster convergence and greater training stability compared to baseline algorithms,highlighting its global optimization capability under energy-aware objectives in complex terrains.This study offers an efficient and scalable intelligent control strategy for the development of energy-conscious autonomous navigation systems.展开更多
Unmanned Aerial Vehicle(UAV)plays a prominent role in various fields,and autonomous navigation is a crucial component of UAV intelligence.Deep Reinforcement Learning(DRL)has expanded the research avenues for addressin...Unmanned Aerial Vehicle(UAV)plays a prominent role in various fields,and autonomous navigation is a crucial component of UAV intelligence.Deep Reinforcement Learning(DRL)has expanded the research avenues for addressing challenges in autonomous navigation.Nonetheless,challenges persist,including getting stuck in local optima,consuming excessive computations during action space exploration,and neglecting deterministic experience.This paper proposes a noise-driven enhancement strategy.In accordance with the overall learning phases,a global noise control method is designed,while a differentiated local noise control method is developed by analyzing the exploration demands of four typical situations encountered by UAV during navigation.Both methods are integrated into a dual-model for noise control to regulate action space exploration.Furthermore,noise dual experience replay buffers are designed to optimize the rational utilization of both deterministic and noisy experience.In uncertain environments,based on the Twin Delay Deep Deterministic Policy Gradient(TD3)algorithm with Long Short-Term Memory(LSTM)network and Priority Experience Replay(PER),a Noise-Driven Enhancement Priority Memory TD3(NDE-PMTD3)is developed.We established a simulation environment to compare different algorithms,and the performance of the algorithms is analyzed in various scenarios.The training results indicate that the proposed algorithm accelerates the convergence speed and enhances the convergence stability.In test experiments,the proposed algorithm successfully and efficiently performs autonomous navigation tasks in diverse environments,demonstrating superior generalization results.展开更多
With the expansion of peanut planting area year by year,film mulching cultivation has become increasingly important in peanut production due to its unique advantages in enhancing both yield per unit area and overall e...With the expansion of peanut planting area year by year,film mulching cultivation has become increasingly important in peanut production due to its unique advantages in enhancing both yield per unit area and overall economic benefits.Based on the varietal characteristics of‘Zhouhua 5’and addressing practical issues in peanut production,this paper summarized key techniques for high-yield and high-efficiency film mulching cultivation of this variety.These techniques cover all critical stages,including land preparation and fertilization,seed preparation,sowing methods,field management,and timely harvesting,providing technical guidance for varietal promotion and peanut production.展开更多
The solar cycle(SC),a phenomenon caused by the quasi-periodic regular activities in the Sun,occurs approximately every 11 years.Intense solar activity can disrupt the Earth’s ionosphere,affecting communication and na...The solar cycle(SC),a phenomenon caused by the quasi-periodic regular activities in the Sun,occurs approximately every 11 years.Intense solar activity can disrupt the Earth’s ionosphere,affecting communication and navigation systems.Consequently,accurately predicting the intensity of the SC holds great significance,but predicting the SC involves a long-term time series,and many existing time series forecasting methods have fallen short in terms of accuracy and efficiency.The Time-series Dense Encoder model is a deep learning solution tailored for long time series prediction.Based on a multi-layer perceptron structure,it outperforms the best previously existing models in accuracy,while being efficiently trainable on general datasets.We propose a method based on this model for SC forecasting.Using a trained model,we predict the test set from SC 19 to SC 25 with an average mean absolute percentage error of 32.02,root mean square error of 30.3,mean absolute error of 23.32,and R^(2)(coefficient of determination)of 0.76,outperforming other deep learning models in terms of accuracy and training efficiency on sunspot number datasets.Subsequently,we use it to predict the peaks of SC 25 and SC 26.For SC 25,the peak time has ended,but a stronger peak is predicted for SC 26,of 199.3,within a range of 170.8-221.9,projected to occur during April 2034.展开更多
This study aimed to integrate Monte Carlo(MC)simulation with deep learning(DL)-based denoising techniques to achieve fast and accurate prediction of high-quality electronic portal imaging device(EPID)transmission dose...This study aimed to integrate Monte Carlo(MC)simulation with deep learning(DL)-based denoising techniques to achieve fast and accurate prediction of high-quality electronic portal imaging device(EPID)transmission dose(TD)for patientspecific quality assurance(PSQA).A total of 100 lung cases were used to obtain the noisy EPID TD by the ARCHER MC code under four kinds of particle numbers(1×10^(6),1×10^(7),1×10^(8)and 1×10^(9)),and the original EPID TD was denoised by the SUNet neural network.The denoised EPID TD was assessed both qualitatively and quantitatively using the structural similarity(SSIM),peak signal-to-noise ratio(PSNR),and gamma passing rate(GPR)with respect to 1×10^(9)as a reference.The computation times for both the MC simulation and DL-based denoising were recorded.As the number of particles increased,both the quality of the noisy EPID TD and computation time increased significantly(1×10^(6):1.12 s,1×10^(7):1.72 s,1×10^(8):8.62 s,and 1×10^(9):73.89 s).In contrast,the DL-based denoising time remained at 0.13-0.16 s.The denoised EPID TD shows a smoother visual appearance and profile curves,but differences between 1×10^(6)and 1×10^(9)still remain.SSIM improves from 0.61 to 0.95 for 1×10^(6),0.70 to 0.96 for 1×10^(7),and 0.90 to 0.97 for 1×10^(8).PSNR increases by>20%for 1×10^(6)and 1×10^(7),and>10%for 1×10^(8).GPR improves from 48.47%to 89.10%for 1×10^(6),61.04%to 94.35%for 1×10^(7),and 91.88%to 99.55%for 1×10^(8).The method that combines MC simulation with DL-based denoising for EPID TD generation can accelerate TD prediction and maintain high accuracy,offering a promising solution for efficient PSQA.展开更多
基金supported by the National Fund Cultivation Project from China People’s Police University(Grant Number:JJPY202402)National Natural Science Foundation of China(Grant Number:62172165).
文摘With the rapid advancement of visual generative models such as Generative Adversarial Networks(GANs)and stable Diffusion,the creation of highly realistic Deepfake through automated forgery has significantly progressed.This paper examines the advancements inDeepfake detection and defense technologies,emphasizing the shift from passive detection methods to proactive digital watermarking techniques.Passive detection methods,which involve extracting features from images or videos to identify forgeries,encounter challenges such as poor performance against unknown manipulation techniques and susceptibility to counter-forensic tactics.In contrast,proactive digital watermarking techniques embed specificmarkers into images or videos,facilitating real-time detection and traceability,thereby providing a preemptive defense againstDeepfake content.We offer a comprehensive analysis of digitalwatermarking-based forensic techniques,discussing their advantages over passivemethods and highlighting four key benefits:real-time detection,embedded defense,resistance to tampering,and provision of legal evidence.Additionally,the paper identifies gaps in the literature concerning proactive forensic techniques and suggests future research directions,including cross-domain watermarking and adaptive watermarking strategies.By systematically classifying and comparing existing techniques,this review aims to contribute valuable insights for the development of more effective proactive defense strategies in Deepfake forensics.
基金supported by the National Natural Science Foundation of China(Nos.51827901,42477191,and 52304033)the Fundamental Research Funds for the Central Universities(No.YJ202449)+1 种基金the Open Research Fund of State Key Laboratory of Geomechanics and Geotechnical Engineering,Institute of Rock and Soil Mechanics,Chinese Academy of Sciences(No.SKLGME022009)the China Postdoctoral Science Foundation(No.2023M742446).
文摘Gas content serves as a critical indicator for assessing the resource potential of deep coal mines and forecasting coal mine gas outburst risks.However,existing sampling technologies face challenges in maintaining the integrity of gas content within samples and are often constrained by estimation errors inherent in empirical formulas,which results in inaccurate gas content measurements.This study introduces a lightweight,in-situ pressure-and gas-preserved corer designed to collect coal samples under the pressure conditions at the sampling point,effectively preventing gas loss during transfer and significantly improving measurement accuracy.Additionally,a gas migration model for deep coal mines was developed to elucidate gas migration characteristics under pressure-preserved coring conditions.The model offers valuable insights for optimizing coring parameters,demonstrating that both minimizing the coring hole diameter and reducing the pressure difference between the coring-point pressure and the original pore pressure can effectively improve the precision of gas content measurements.Coring tests conducted at an experimental base validated the performance of the corer and its effectiveness in sample collection.Furthermore,successful horizontal coring tests conducted in an underground coal mine roadway demonstrated that the measured gas content using pressure-preserved coring was 34%higher than that obtained through open sampling methods.
基金supported and funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University(IMSIU)(grant number IMSIU-DDRSP2504).
文摘The rapid evolution of malware presents a critical cybersecurity challenge,rendering traditional signature-based detection methods ineffective against novel variants.This growing threat affects individuals,organizations,and governments,highlighting the urgent need for robust malware detection mechanisms.Conventional machine learning-based approaches rely on static and dynamicmalware analysis and often struggle to detect previously unseen threats due to their dependency on predefined signatures.Although machine learning algorithms(MLAs)offer promising detection capabilities,their reliance on extensive feature engineering limits real-time applicability.Deep learning techniques mitigate this issue by automating feature extraction but may introduce computational overhead,affecting deployment efficiency.This research evaluates classical MLAs and deep learningmodels to enhance malware detection performance across diverse datasets.The proposed approach integrates a novel text and imagebased detection framework,employing an optimized Support Vector Machine(SVM)for textual data analysis and EfficientNet-B0 for image-based malware classification.Experimental analysis,conducted across multiple train-test splits over varying timescales,demonstrates 99.97%accuracy on textual datasets using SVM and 96.7%accuracy on image-based datasets with EfficientNet-B0,significantly improving zero-day malware detection.Furthermore,a comparative analysis with existing competitive techniques,such as Random Forest,XGBoost,and CNN-based(Convolutional Neural Network)classifiers,highlights the superior performance of the proposed model in terms of accuracy,efficiency,and robustness.
文摘In recent years,Speech Emotion Recognition(SER)has developed into an essential instrument for interpreting human emotions from auditory data.The proposed research focuses on the development of a SER system employing deep learning and multiple datasets containing samples of emotive speech.The primary objective of this research endeavor is to investigate the utilization of Convolutional Neural Networks(CNNs)in the process of sound feature extraction.Stretching,pitch manipulation,and noise injection are a few of the techniques utilized in this study to improve the data quality.Feature extraction methods including Zero Crossing Rate,Chroma_stft,Mel⁃scale Frequency Cepstral Coefficients(MFCC),Root Mean Square(RMS),and Mel⁃Spectogram are used to train a model.By using these techniques,audio signals can be transformed into recognized features that can be utilized to train the model.Ultimately,the study produces a thorough evaluation of the models performance.When this method was applied,the model achieved an impressive accuracy of 94.57%on the test dataset.The proposed work was also validated on the EMO⁃BD and IEMOCAP datasets.These consist of further data augmentation,feature engineering,and hyperparameter optimization.By following these development paths,SER systems will be able to be implemented in real⁃world scenarios with greater accuracy and resilience.
基金funded by the Researchers Supporting Project number(RSPD2025R857),King Saud University,Riyadh,Saudi Arabia.
文摘Many bioinformatics applications require determining the class of a newly sequenced Deoxyribonucleic acid(DNA)sequence,making DNA sequence classification an integral step in performing bioinformatics analysis,where large biomedical datasets are transformed into valuable knowledge.Existing methods rely on a feature extraction step and suffer from high computational time requirements.In contrast,newer approaches leveraging deep learning have shown significant promise in enhancing accuracy and efficiency.In this paper,we investigate the performance of various deep learning architectures:Convolutional Neural Network(CNN),CNN-Long Short-Term Memory(CNNLSTM),CNN-Bidirectional Long Short-Term Memory(CNN-BiLSTM),Residual Network(ResNet),and InceptionV3 for DNA sequence classification.Various numerical and visual data representation techniques are utilized to represent the input datasets,including:label encoding,k-mer sentence encoding,k-mer one-hot vector,Frequency Chaos Game Representation(FCGR)and 5-Color Map(ColorSquare).Three datasets are used for the training of the models including H3,H4 and DNA Sequence Dataset(Yeast,Human,Arabidopsis Thaliana).Experiments are performed to determine which combination of DNA representation and deep learning architecture yields improved performance for the classification task.Our results indicate that using a hybrid CNN-LSTM neural network trained on DNA sequences represented as one-hot encoded k-mer sequences yields the best performance,achieving an accuracy of 92.1%.
基金supported by the General Program of the National Natural Science Foundation of China(Grant No.42374212)the National Magnetic Confinement Fusion Energy Research and Development Program of China(Grant No.2024YFE03020004).
文摘In this investigation,we meticulously annotated a corpus of 21,174 auroral images captured by the THEMIS All-Sky Imager across diverse temporal instances.These images were categorized using an array of descriptors such as'arc','ab'(aurora but bright),'cloudy','diffuse','discrete',and'clear'.Subsequently,we utilized a state-of-the-art convolutional neural network,ConvNeXt(Convolutional Neural Network Next),deploying deep learning techniques to train the model on a dataset classified into six distinct categories.Remarkably,on the test set our methodology attained an accuracy of 99.4%,a performance metric closely mirroring human visual observation,thereby underscoring the classifier’s competence in paralleling human perceptual accuracy.Building upon this foundation,we embarked on the identification of large-scale auroral optical data,meticulously quantifying the monthly occurrence and Magnetic Local Time(MLT)variations of auroras from stations at different latitudes:RANK(high-latitude),FSMI(mid-latitude),and ATHA(low-latitude),under different solar wind conditions.This study paves the way for future explorations into the temporal variations of auroral phenomena in diverse geomagnetic contexts.
基金funded by Natural Science Foundation of Heilongjiang Province,grant number LH2023F020.
文摘Deep learning(DL)has revolutionized time series forecasting(TSF),surpassing traditional statistical methods(e.g.,ARIMA)and machine learning techniques in modeling complex nonlinear dynamics and long-term dependencies prevalent in real-world temporal data.This comprehensive survey reviews state-of-the-art DL architectures forTSF,focusing on four core paradigms:(1)ConvolutionalNeuralNetworks(CNNs),adept at extracting localized temporal features;(2)Recurrent Neural Networks(RNNs)and their advanced variants(LSTM,GRU),designed for sequential dependency modeling;(3)Graph Neural Networks(GNNs),specialized for forecasting structured relational data with spatial-temporal dependencies;and(4)Transformer-based models,leveraging self-attention mechanisms to capture global temporal patterns efficiently.We provide a rigorous analysis of the theoretical underpinnings,recent algorithmic advancements(e.g.,TCNs,attention mechanisms,hybrid architectures),and practical applications of each framework,supported by extensive benchmark datasets(e.g.,ETT,traffic flow,financial indicators)and standardized evaluation metrics(MAE,MSE,RMSE).Critical challenges,including handling irregular sampling intervals,integrating domain knowledge for robustness,and managing computational complexity,are thoroughly discussed.Emerging research directions highlighted include diffusion models for uncertainty quantification,hybrid pipelines combining classical statistical and DL techniques for enhanced interpretability,quantile regression with Transformers for riskaware forecasting,and optimizations for real-time deployment.This work serves as an essential reference,consolidating methodological innovations,empirical resources,and future trends to bridge the gap between theoretical research and practical implementation needs for researchers and practitioners in the field.
文摘DeepSeek Chinese artificial intelligence(AI)open-source model,has gained a lot of attention due to its economical training and efficient inference.DeepSeek,a model trained on large-scale reinforcement learning without supervised fine-tuning as a preliminary step,demonstrates remarkable reasoning capabilities of performing a wide range of tasks.DeepSeek is a prominent AI-driven chatbot that assists individuals in learning and enhances responses by generating insightful solutions to inquiries.Users possess divergent viewpoints regarding advanced models like DeepSeek,posting both their merits and shortcomings across several social media platforms.This research presents a new framework for predicting public sentiment to evaluate perceptions of DeepSeek.To transform the unstructured data into a suitable manner,we initially collect DeepSeek-related tweets from Twitter and subsequently implement various preprocessing methods.Subsequently,we annotated the tweets utilizing the Valence Aware Dictionary and sentiment Reasoning(VADER)methodology and the lexicon-driven TextBlob.Next,we classified the attitudes obtained from the purified data utilizing the proposed hybrid model.The proposed hybrid model consists of long-term,shortterm memory(LSTM)and bidirectional gated recurrent units(BiGRU).To strengthen it,we include multi-head attention,regularizer activation,and dropout units to enhance performance.Topic modeling employing KMeans clustering and Latent Dirichlet Allocation(LDA),was utilized to analyze public behavior concerning DeepSeek.The perceptions demonstrate that 82.5%of the people are positive,15.2%negative,and 2.3%neutral using TextBlob,and 82.8%positive,16.1%negative,and 1.2%neutral using the VADER analysis.The slight difference in results ensures that both analyses concur with their overall perceptions and may have distinct views of language peculiarities.The results indicate that the proposed model surpassed previous state-of-the-art approaches.
文摘Addressing plant diseases and pests is not just crucial;it’s a matter of utmost importance for enhancing crop production and preventing economic losses. Recent advancements in artificial intelligence, machine learning, and deep learning have revolutionised the precision and efficiency of this process, surpassing the limitations of manual identification. This study comprehensively reviews modern computer-based techniques, including recent advances in artificial intelligence, for detecting diseases and pests through images. This paper uniquely categorises methodologies into hyperspectral imaging, non-visualisation techniques, visualisation approaches, modified deep learning architectures, and transformer models, helping researchers gain detailed, insightful understandings. The exhaustive survey of recent works and comparative studies in this domain guides researchers in selecting appropriate and advanced state-of-the-art methods for plant disease and pest detection. Additionally, this paper highlights the consistent superiority of modern AI-based approaches, which often outperform older image analysis methods in terms of speed and accuracy. Further, this survey focuses on the efficiency of vision transformers against well-known deep learning architectures like MobileNetV3, which shows that Hierarchical Vision Transformer (HvT) can achieve accuracy upwards of 99.3% in plant disease detection. The study concludes by addressing the challenges of designing the systems, proposing potential solutions, and outlining directions for future research in this field.
文摘Automated cartoon character recognition is crucial for applications in content indexing,filtering,and copyright protection,yet it faces a significant challenge in animated media due to high intra-class visual variability,where characters frequently alter their appearance.To address this problem,we introduce the novel Kral Sakir dataset,a public benchmark of 16,725 images specifically curated for the task of multi-label cartoon character classification under these varied conditions.This paper conducts a comprehensive benchmark study,evaluating the performance of state-of-the-art pretrained Convolutional Neural Networks(CNNs),including DenseNet,ResNet,and VGG,against a custom baseline model trained from scratch.Our experiments,evaluated using metrics of F1-Score,accuracy,and Area Under the ROC Curve(AUC),demonstrate that fine-tuning pretrained models is a highly effective strategy.The best-performing model,DenseNet121,achieved an F1-Score of 0.9890 and an accuracy of 0.9898,significantly outperforming our baseline CNN(F1-Score of 0.9545).The findings validate the power of transfer learning for this domain and establish a strong performance benchmark.The introduced dataset provides a valuable resource for future research into developing robust and accurate character recognition systems.
基金supported by the Deputyship of Research&Innovation,Ministry of Education in Saudi Arabia for funding this research work through the project number RI-44-0291.
文摘The 3GPP standard defines the requirements for next-generation wireless networks,with particular attention to Ultra-Reliable Low-Latency Communications(URLLC),critical for applications such as Unmanned Aerial Vehicles(UAVs).In this context,Non-Orthogonal Multiple Access(NOMA)has emerged as a promising technique to improve spectrum efficiency and user fairness by allowing multiple users to share the same frequency resources.However,optimizing key parameters–such as beamforming,rate allocation,and UAV trajectory–presents significant challenges due to the nonconvex nature of the problem,especially under stringent URLLC constraints.This paper proposes an advanced deep learning-driven approach to address the resulting complex optimization challenges.We formulate a downlink multiuser UAV,Rate-Splitting Multiple Access(RSMA),and Multiple Input Multiple Output(MIMO)system aimed at maximizing the achievable rate under stringent constraints,including URLLC quality-of-service(QoS),power budgets,rate allocations,and UAV trajectory limitations.Due to the highly nonconvex nature of the optimization problem,we introduce a novel distributed deep reinforcement learning(DRL)framework based on dual-agent deep deterministic policy gradient(DA-DDPG).The proposed framework leverages inception-inspired and deep unfolding architectures to improve feature extraction and convergence in beamforming and rate allocation.For UAV trajectory optimization,we design a dedicated actor-critic agent using a fully connected deep neural network(DNN),further enhanced through incremental learning.Simulation results validate the effectiveness of our approach,demonstrating significant performance gains over existing methods and confirming its potential for real-time URLLC in next-generation UAV communication networks.
文摘The increased interest in geothermal energy is evident,along with the exploitation of traditional hydrothermal systems,in the growing research and projects developing around the reuse of already-drilled oil,gas,and exploration wells.The Republic of Croatia has around 4000 wells,however,due to a long period since most of these wells were drilled and completed,there is uncertainty about how many are available for retrofitting as deep-borehole heat exchangers.Nevertheless,as hydrocarbon production decreases,it is expected that the number of wells available for the revitalization and exploitation of geothermal energy will increase.The revitalization of wells via deep-borehole heat exchangers involves installing a coaxial heat exchanger and circulating the working fluid in a closed system,during which heat is transferred from the surrounding rock medium to the circulating fluid.Since drilled wells are not of uniformdepth and are located in areas with different thermal rock properties and geothermal gradients,an analysis was conducted to determine available thermal energy as a function of well depth,geothermal gradient,and circulating fluid flow rate.Additionally,an economic analysis was performed to determine the benefits of retrofitting existing assets,such as drilled wells,compared to drilling new wells to obtain the same amount of thermal energy.
文摘At present,energy consumption is one of the main bottlenecks in autonomous mobile robot development.To address the challenge of high energy consumption in path planning for autonomous mobile robots navigating unknown and complex environments,this paper proposes an Attention-Enhanced Dueling Deep Q-Network(ADDueling DQN),which integrates a multi-head attention mechanism and a prioritized experience replay strategy into a Dueling-DQN reinforcement learning framework.A multi-objective reward function,centered on energy efficiency,is designed to comprehensively consider path length,terrain slope,motion smoothness,and obstacle avoidance,enabling optimal low-energy trajectory generation in 3D space from the source.The incorporation of a multihead attention mechanism allows the model to dynamically focus on energy-critical state features—such as slope gradients and obstacle density—thereby significantly improving its ability to recognize and avoid energy-intensive paths.Additionally,the prioritized experience replay mechanism accelerates learning from key decision-making experiences,suppressing inefficient exploration and guiding the policy toward low-energy solutions more rapidly.The effectiveness of the proposed path planning algorithm is validated through simulation experiments conducted in multiple off-road scenarios.Results demonstrate that AD-Dueling DQN consistently achieves the lowest average energy consumption across all tested environments.Moreover,the proposed method exhibits faster convergence and greater training stability compared to baseline algorithms,highlighting its global optimization capability under energy-aware objectives in complex terrains.This study offers an efficient and scalable intelligent control strategy for the development of energy-conscious autonomous navigation systems.
基金the Collaborative Innovation Project of Shanghai,China for the financial support。
文摘Unmanned Aerial Vehicle(UAV)plays a prominent role in various fields,and autonomous navigation is a crucial component of UAV intelligence.Deep Reinforcement Learning(DRL)has expanded the research avenues for addressing challenges in autonomous navigation.Nonetheless,challenges persist,including getting stuck in local optima,consuming excessive computations during action space exploration,and neglecting deterministic experience.This paper proposes a noise-driven enhancement strategy.In accordance with the overall learning phases,a global noise control method is designed,while a differentiated local noise control method is developed by analyzing the exploration demands of four typical situations encountered by UAV during navigation.Both methods are integrated into a dual-model for noise control to regulate action space exploration.Furthermore,noise dual experience replay buffers are designed to optimize the rational utilization of both deterministic and noisy experience.In uncertain environments,based on the Twin Delay Deep Deterministic Policy Gradient(TD3)algorithm with Long Short-Term Memory(LSTM)network and Priority Experience Replay(PER),a Noise-Driven Enhancement Priority Memory TD3(NDE-PMTD3)is developed.We established a simulation environment to compare different algorithms,and the performance of the algorithms is analyzed in various scenarios.The training results indicate that the proposed algorithm accelerates the convergence speed and enhances the convergence stability.In test experiments,the proposed algorithm successfully and efficiently performs autonomous navigation tasks in diverse environments,demonstrating superior generalization results.
基金Supported by Zhoukou Key Science and Technology Research Project(20200816).
文摘With the expansion of peanut planting area year by year,film mulching cultivation has become increasingly important in peanut production due to its unique advantages in enhancing both yield per unit area and overall economic benefits.Based on the varietal characteristics of‘Zhouhua 5’and addressing practical issues in peanut production,this paper summarized key techniques for high-yield and high-efficiency film mulching cultivation of this variety.These techniques cover all critical stages,including land preparation and fertilization,seed preparation,sowing methods,field management,and timely harvesting,providing technical guidance for varietal promotion and peanut production.
基金supported by the Academic Research Projects of Beijing Union University(ZK20202204)the National Natural Science Foundation of China(12250005,12073040,12273059,11973056,12003051,11573037,12073041,11427901,11572005,11611530679 and 12473052)+1 种基金the Strategic Priority Research Program of the China Academy of Sciences(XDB0560000,XDA15052200,XDB09040200,XDA15010700,XDB0560301,and XDA15320102)the Chinese Meridian Project(CMP).
文摘The solar cycle(SC),a phenomenon caused by the quasi-periodic regular activities in the Sun,occurs approximately every 11 years.Intense solar activity can disrupt the Earth’s ionosphere,affecting communication and navigation systems.Consequently,accurately predicting the intensity of the SC holds great significance,but predicting the SC involves a long-term time series,and many existing time series forecasting methods have fallen short in terms of accuracy and efficiency.The Time-series Dense Encoder model is a deep learning solution tailored for long time series prediction.Based on a multi-layer perceptron structure,it outperforms the best previously existing models in accuracy,while being efficiently trainable on general datasets.We propose a method based on this model for SC forecasting.Using a trained model,we predict the test set from SC 19 to SC 25 with an average mean absolute percentage error of 32.02,root mean square error of 30.3,mean absolute error of 23.32,and R^(2)(coefficient of determination)of 0.76,outperforming other deep learning models in terms of accuracy and training efficiency on sunspot number datasets.Subsequently,we use it to predict the peaks of SC 25 and SC 26.For SC 25,the peak time has ended,but a stronger peak is predicted for SC 26,of 199.3,within a range of 170.8-221.9,projected to occur during April 2034.
基金supported by National Key R&D Program of China(No.2022YFC2404604)Chongqing Research Institution Performance Incentive Guidance Special Project(No.CSTB2023JXJL-YFX0080)Chongqing Medical Scientific Research Project(Joint project of Chongqing Health Commission and Science and Technology Bureau)(No.2022DBXM005)。
文摘This study aimed to integrate Monte Carlo(MC)simulation with deep learning(DL)-based denoising techniques to achieve fast and accurate prediction of high-quality electronic portal imaging device(EPID)transmission dose(TD)for patientspecific quality assurance(PSQA).A total of 100 lung cases were used to obtain the noisy EPID TD by the ARCHER MC code under four kinds of particle numbers(1×10^(6),1×10^(7),1×10^(8)and 1×10^(9)),and the original EPID TD was denoised by the SUNet neural network.The denoised EPID TD was assessed both qualitatively and quantitatively using the structural similarity(SSIM),peak signal-to-noise ratio(PSNR),and gamma passing rate(GPR)with respect to 1×10^(9)as a reference.The computation times for both the MC simulation and DL-based denoising were recorded.As the number of particles increased,both the quality of the noisy EPID TD and computation time increased significantly(1×10^(6):1.12 s,1×10^(7):1.72 s,1×10^(8):8.62 s,and 1×10^(9):73.89 s).In contrast,the DL-based denoising time remained at 0.13-0.16 s.The denoised EPID TD shows a smoother visual appearance and profile curves,but differences between 1×10^(6)and 1×10^(9)still remain.SSIM improves from 0.61 to 0.95 for 1×10^(6),0.70 to 0.96 for 1×10^(7),and 0.90 to 0.97 for 1×10^(8).PSNR increases by>20%for 1×10^(6)and 1×10^(7),and>10%for 1×10^(8).GPR improves from 48.47%to 89.10%for 1×10^(6),61.04%to 94.35%for 1×10^(7),and 91.88%to 99.55%for 1×10^(8).The method that combines MC simulation with DL-based denoising for EPID TD generation can accelerate TD prediction and maintain high accuracy,offering a promising solution for efficient PSQA.
