Accurate wind speed measurements on maritime vessels are crucial for weather forecasting,sea state prediction,and safe ***,vessel motion and challenging environmental conditions often affect measurement *** address th...
详细信息
Accurate wind speed measurements on maritime vessels are crucial for weather forecasting,sea state prediction,and safe ***,vessel motion and challenging environmental conditions often affect measurement *** address this issue,this study proposes an innovative framework for correcting and predicting shipborne wind *** integrating a main network with a momentum updating network,the proposed framework effectively extracts features from the time and frequency domains,thereby allowing for precise adjustments and predictions of shipborne wind speed *** using real sensor data collected at the Qingdao Oceanographic Institute demonstrates that the proposed method outperforms existing approaches in single-and multi-step predictions compared to existing methods,achieving higher accuracy in wind speed *** proposed innovative approach offers a promising direction for future validation in more realistic maritime onboard scenarios.
A novel color image encryption scheme is developed to enhance the security of encryption without increasing the complexity. Firstly, the plain color image is decomposed into three grayscale plain images, which are con...
详细信息
A novel color image encryption scheme is developed to enhance the security of encryption without increasing the complexity. Firstly, the plain color image is decomposed into three grayscale plain images, which are converted into the frequency domain coefficient matrices(FDCM) with discrete cosine transform(DCT) operation. After that, a twodimensional(2D) coupled chaotic system is developed and used to generate one group of embedded matrices and another group of encryption matrices, respectively. The embedded matrices are integrated with the FDCM to fulfill the frequency domain encryption, and then the inverse DCT processing is implemented to recover the spatial domain signal. Eventually,under the function of the encryption matrices and the proposed diagonal scrambling algorithm, the final color ciphertext is obtained. The experimental results show that the proposed method can not only ensure efficient encryption but also satisfy various sizes of image encryption. Besides, it has better performance than other similar techniques in statistical feature analysis, such as key space, key sensitivity, anti-differential attack, information entropy, noise attack, etc.
Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series *** to the challenges associated with annotating anomaly events,time series reconstructi...
详细信息
Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series *** to the challenges associated with annotating anomaly events,time series reconstruction has become a prevalent approach for unsupervised anomaly ***,effectively learning representations and achieving accurate detection results remain challenging due to the intricate temporal patterns and dependencies in real-world time *** this paper,we propose a cross-dimension attentive feature fusion network for time series anomaly detection,referred to as ***,a series and feature mixing block is introduced to learn representations in 1D ***,a fast Fourier transform is employed to convert the time series into 2D space,providing the capability for 2D feature ***,a cross-dimension attentive feature fusion mechanism is designed that adaptively integrates features across different dimensions for anomaly *** results on real-world time series datasets demonstrate that CAFFN performs better than other competing methods in time series anomaly detection.
Modern recommendation systems are widely used in modern data *** random and sparse embedding lookup operations are the main performance bottleneck for processing recommendation systems on traditional platforms as they...
详细信息
Modern recommendation systems are widely used in modern data *** random and sparse embedding lookup operations are the main performance bottleneck for processing recommendation systems on traditional platforms as they induce abundant data movements between computing units and ***-based processing-in-memory(PIM)can resolve this problem by processing embedding vectors where they are ***,the embedding table can easily exceed the capacity limit of a monolithic ReRAM-based PIM chip,which induces off-chip accesses that may offset the PIM ***,we deploy the decomposed model on-chip and leverage the high computing efficiency of ReRAM to compensate for the decompression performance *** this paper,we propose ARCHER,a ReRAM-based PIM architecture that implements fully yon-chip recommendations under resource ***,we make a full analysis of the computation pattern and access pattern on the decomposed *** on the computation pattern,we unify the operations of each layer of the decomposed model in multiply-and-accumulate *** on the access observation,we propose a hierarchical mapping schema and a specialized hardware design to maximize resource *** the unified computation and mapping strategy,we can coordinatethe inter-processing elements *** evaluation shows that ARCHER outperforms the state-of-the-art GPU-based DLRM system,the state-of-the-art near-memory processing recommendation system RecNMP,and the ReRAM-based recommendation accelerator REREC by 15.79×,2.21×,and 1.21× in terms of performance and 56.06×,6.45×,and 1.71× in terms of energy savings,respectively.
This study applies single-valued neutrosophic sets, which extend the frameworks of fuzzy and intuitionistic fuzzy sets, to graph theory. We introduce a new category of graphs called Single-Valued Heptapartitioned Neut...
详细信息
A credit risk prediction model named KM-ADASYN-TL-FLLightGBM(KADT-FLightGBM)is proposed in this ***,to overcome the limitation of traditional sampling methods in dealing with imbalanced datasets,an improved ADASYN sam...
详细信息
A credit risk prediction model named KM-ADASYN-TL-FLLightGBM(KADT-FLightGBM)is proposed in this ***,to overcome the limitation of traditional sampling methods in dealing with imbalanced datasets,an improved ADASYN sampling with K-means clustering algorithm is ***,the Tomek Links method is used to filter the generated ***,an utilized an optimized LightGBM algorithm with the Focal Loss is employed to training the model using the datasets obtained by the improved ADASYN ***,the comparative analysis between the ensemble model and other different sampling methodologies is conducted on the Lending Club *** results demonstrate that the proposed model effectively minimizes the misclassification of minority classes in credit risk prediction and can be used as a reference for similar studies.
Graphs that are used to model real-world entities with vertices and relationships among entities with edges,have proven to be a powerful tool for describing real-world problems in *** most real-world scenarios,entitie...
详细信息
Graphs that are used to model real-world entities with vertices and relationships among entities with edges,have proven to be a powerful tool for describing real-world problems in *** most real-world scenarios,entities and their relationships are subject to constant *** that record such changes are called dynamic *** recent years,the widespread application scenarios of dynamic graphs have stimulated extensive research on dynamic graph processing systems that continuously ingest graph updates and produce up-to-date graph analytics *** the scale of dynamic graphs becomes larger,higher performance requirements are demanded to dynamic graph processing *** the massive parallel processing power and high memory bandwidth,GPUs become mainstream vehicles to accelerate dynamic graph processing ***-based dynamic graph processing systems mainly address two challenges:maintaining the graph data when updates occur(i.e.,graph updating)and producing analytics results in time(i.e.,graph computing).In this paper,we survey GPU-based dynamic graph processing systems and review their methods on addressing both graph updating and graph *** comprehensively discuss existing dynamic graph processing systems on GPUs,we first introduce the terminologies of dynamic graph processing and then develop a taxonomy to describe the methods employed for graph updating and graph *** addition,we discuss the challenges and future research directions of dynamic graph processing on GPUs.
With the development of artificial intelligence, deep-learning-based log anomaly detection proves to be an important research topic. In this paper, we propose LogCSS, a novel log anomaly detection framework based on t...
详细信息
Federated Graph Neural Networks (FedGNNs) have achieved significant success in representation learning for graph data, enabling collaborative training among multiple parties without sharing their raw graph data and so...
详细信息
Federated Graph Neural Networks (FedGNNs) have achieved significant success in representation learning for graph data, enabling collaborative training among multiple parties without sharing their raw graph data and solving the data isolation problem faced by centralized GNNs in data-sensitive scenarios. Despite the plethora of prior work on inference attacks against centralized GNNs, the vulnerability of FedGNNs to inference attacks has not yet been widely explored. It is still unclear whether the privacy leakage risks of centralized GNNs will also be introduced in FedGNNs. To bridge this gap, we present PIAFGNN, the first property inference attack (PIA) against FedGNNs. Compared with prior works on centralized GNNs, in PIAFGNN, the attacker can only obtain the global embedding gradient distributed by the central server. The attacker converts the task of stealing the target user’s local embeddings into a regression problem, using a regression model to generate the target graph node embeddings. By training shadow models and property classifiers, the attacker can infer the basic property information within the target graph that is of interest. Experiments on three benchmark graph datasets demonstrate that PIAFGNN achieves attack accuracy of over 70% in most cases, even approaching the attack accuracy of inference attacks against centralized GNNs in some instances, which is much higher than the attack accuracy of the random guessing method. Furthermore, we observe that common defense mechanisms cannot mitigate our attack without affecting the model’s performance on mainly classification tasks.
In recent years,with the rapid development of deepfake technology,a large number of deepfake videos have emerged on the Internet,which poses a huge threat to national politics,social stability,and personal *** many ex...
详细信息
In recent years,with the rapid development of deepfake technology,a large number of deepfake videos have emerged on the Internet,which poses a huge threat to national politics,social stability,and personal *** many existing deepfake detection methods exhibit excellent performance for known manipulations,their detection capabilities are not strong when faced with unknown ***,in order to obtain better generalization ability,this paper analyzes global and local inter-frame dynamic inconsistencies from the perspective of spatial and frequency domains,and proposes a Local region Frequency Guided Dynamic Inconsistency Network(LFGDIN).The network includes two parts:Global SpatioTemporal Network(GSTN)and Local Region Frequency Guided Module(LRFGM).The GSTN is responsible for capturing the dynamic information of the entire face,while the LRFGM focuses on extracting the frequency dynamic information of the eyes and *** LRFGM guides the GTSN to concentrate on dynamic inconsistency in some significant local regions through local region alignment,so as to improve the model's detection *** on the three public datasets(FF++,DFDC,and Celeb-DF)show that compared with many recent advanced methods,the proposed method achieves better detection results when detecting deepfake videos of unknown manipulation types.
暂无评论