Due to the advantages of high volume of transactions and low resource consumption,Directed Acyclic Graph(DAG)-based Distributed Ledger technology(DLT)has been considered a possible next-generation alternative to ***,t...
详细信息
Due to the advantages of high volume of transactions and low resource consumption,Directed Acyclic Graph(DAG)-based Distributed Ledger technology(DLT)has been considered a possible next-generation alternative to ***,the security of the DAG-based system has yet to be comprehensively *** at verifying and evaluating the security of DAG-based DLT,we develop a Multi-Agent based IOTA Simulation platform called *** MAIOTASim,we model honest and malicious nodes and simulate the configurable network environment,including network topology and *** double-spending attack is a particular security issue related to *** perform the security verification of the consensus algorithms under multiple double-spending attack *** simulations show that the consensus algorithms can resist the parasite chain attack and partially resist the splitting attack,but they are ineffective under the large weight *** take the cumulative weight difference of transactions as the evaluation criterion and analyze the effect of different consensus algorithms with parameters under each attack ***,MAIOTASim enables users to perform largescale simulations with multiple nodes and tens of thousands of transactions more efficiently than state-of-the-art ones.
This study presents a revolutionary deep-learning architecture that focuses on feature extraction, feature selection, and sales forecasting. The technique begins with a pre-processing step using median imputation and ...
详细信息
From first-principles calculations we reveal that beryllium has the highest lattice thermal conductivity (κph) among all elemental metals at room temperature. Specifically, the calculated κph is 104(125) Wm−1K−1, co...
详细信息
From first-principles calculations we reveal that beryllium has the highest lattice thermal conductivity (κph) among all elemental metals at room temperature. Specifically, the calculated κph is 104(125) Wm−1K−1, contributing ∼50% (60%) to the total thermal conductivity along the a(c) axis, contrary to the common belief that κph is negligible in metals. κph reach the maxima with values of ∼210 Wm−1K−1 for both axes at 125 K. The unusually high κph is related to the weak three-phonon scattering with a dip in the intermediate-frequency region, which arises from its high Debye temperature and bunched phonon dispersions. Another consequence of the weak three-phonon scattering is the strong effect of higher-order (fourth-order) anharmonicity and electron-phonon coupling on κph. We also predict that κph increases significantly with pressure, mainly due to the weakening of four-phonon scattering, and consequently exceeds the electronic contribution κe by more than one third in both axes at 20 GPa. Our work deepens the understanding of thermal transport in metals, and can benefit the search of metals with high thermal conductivity.
The attention mechanism has become a pivotal component in artificial intelligence, significantly enhancing the performance of deep learning applications. However, its quadratic computational complexity and intricate c...
详细信息
The attention mechanism has become a pivotal component in artificial intelligence, significantly enhancing the performance of deep learning applications. However, its quadratic computational complexity and intricate computations lead to substantial inefficiencies when processing long sequences. To address these challenges, we introduce Attar, a resistive random access memory(RRAM)-based in-memory accelerator designed to optimize attention mechanisms through software-hardware co-optimization. Attar leverages efficient Top-k pruning and quantization strategies to exploit the sparsity and redundancy of attention matrices, and incorporates an RRAM-based in-memory softmax engine by harnessing the versatility of the RRAM crossbar. Comprehensive evaluations demonstrate that Attar achieves a performance improvement of up to 4.88× and energy saving of 55.38% over previous computing-in-memory(CIM)-based accelerators across various models and datasets while maintaining comparable accuracy. This work underscores the potential of in-memory computing to enhance the efficiency of attention-based models without compromising their effectiveness.
The secure and normal operation of distributed networks is crucial for accurate parameter ***,distributed networks are frequently susceptible to Byzantine *** real-life scenarios,this paper investigates a probability ...
详细信息
The secure and normal operation of distributed networks is crucial for accurate parameter ***,distributed networks are frequently susceptible to Byzantine *** real-life scenarios,this paper investigates a probability Byzantine(PB)attack,utilizing a Bernoulli distribution to simulate the attack ***,additional detection mechanisms are used to mitigate such attacks,leading to increased energy consumption and burdens on distributed nodes,consequently diminishing operational *** from these approaches,an adaptive updating distributed estimation algorithm is proposed to mitigate the impact of PB *** the proposed algorithm,a penalty strategy is initially incorporated during data updates to weaken the influence of the ***,an adaptive fusion weight is employed during data fusion to merge the ***,the reason why this penalty term weakens the attack has been analyzed,and the performance of the proposed algorithm is validated through simulation experiments.
Deep convolutional neural networks,particularly large models with large kernels(3x3 or more),have achieved significant progress in single image super-resolution(SISR)***,the heavy computational footprint of such model...
详细信息
Deep convolutional neural networks,particularly large models with large kernels(3x3 or more),have achieved significant progress in single image super-resolution(SISR)***,the heavy computational footprint of such models prevents their de-ployment in real-time,resource-constrained ***,1×1 convolutions have substantial computational efficiency,but struggle with aggregating local spatial representations,which is an essential capability for SISR *** response to this dichotomy,we propose to harmonize the merits of both 3x3 and 1×1 kernels,and exploit their great potential for lightweight SISR ***-ally,we propose a simple yet effective fully 1×1 convolutional network,named shift-Conv-based network(SCNet).By incorporating a parameter-free spatial-shift operation,the fully 1×1 convolutional network is equipped with a powerful representation capability and impressive computational *** experiments demonstrate that SCNets,despite their fully 1×1 convolutional structure,consistently match or even surpass the performance of existing lightweight SR models that employ regular *** code and pretrained models can be found at .
Deep convolutional neural networks with high performance are hard to be deployed in many real world applications, since the computing resources of edge devices such as smart phones or embedded GPU are limited. To alle...
详细信息
Deep convolutional neural networks with high performance are hard to be deployed in many real world applications, since the computing resources of edge devices such as smart phones or embedded GPU are limited. To alleviate this hardware limitation, the compression of deep neural networks from the model side becomes important. As one of the most popular methods in the spotlight, channel pruning of the deep convolutional model can effectively remove redundant convolutional channels from the CNN (convolutional neural network) without affecting the network’s performance remarkably. Existing methods focus on pruning design, evaluating the importance of different convolutional filters in the CNN model. A fast and effective fine-tuning method to restore accuracy is urgently needed. In this paper, we propose a fine-tuning method KDFT (Knowledge Distillation Based Fine-Tuning), which improves the accuracy of fine-tuned models with almost negligible training overhead by introducing knowledge distillation. Extensive experimental results on benchmark datasets with representative CNN models show that up to 4.86% accuracy improvement and 79% time saving can be obtained.
Network anomaly detection plays a vital role in safeguarding network ***,the existing network anomaly detection task is typically based on the one-class zero-positive *** approach is susceptible to overfitting during ...
详细信息
Network anomaly detection plays a vital role in safeguarding network ***,the existing network anomaly detection task is typically based on the one-class zero-positive *** approach is susceptible to overfitting during the training process due to discrepancies in data distribution between the training set and the test *** phenomenon is known as prediction ***,the rarity of anomaly data,often masked by normal data,further complicates network anomaly *** address these challenges,we propose the PUNet network,which ingeniously combines the strengths of traditional machine learning and deep learning techniques for anomaly ***,PUNet employs a reconstruction-based autoencoder to pre-train normal data,enabling the network to capture potential features and correlations within the ***,PUNet integrates a sampling algorithm to construct a pseudo-label candidate set among the outliers based on the reconstruction loss of the *** approach effectively mitigates the prediction drift problem by incorporating abnormal ***,PUNet utilizes the CatBoost classifier for anomaly detection to tackle potential data imbalance issues within the candidate *** experimental evaluations demonstrate that PUNet effectively resolves the prediction drift and data imbalance problems,significantly outperforming competing methods.
The existing Low-Earth-Orbit(LEO) positioning performance cannot meet the requirements of Unmanned Aerial Vehicle(UAV) clusters for high-precision real-time positioning in the Global Navigation Satellite System(GNSS) ...
详细信息
The existing Low-Earth-Orbit(LEO) positioning performance cannot meet the requirements of Unmanned Aerial Vehicle(UAV) clusters for high-precision real-time positioning in the Global Navigation Satellite System(GNSS) denial conditions. Therefore, this paper proposes a UAV Clusters Information Geometry Fusion Positioning(UC-IGFP) method using pseudoranges from the LEO satellites. A novel graph model for linking and computing between the UAV clusters and LEO satellites was established. By utilizing probability to describe the positional states of UAVs and sensor errors, the distributed multivariate Probability Fusion Cooperative Positioning(PF-CP) algorithm is proposed to achieve high-precision cooperative positioning and integration of the cluster. Criteria to select the centroid of the cluster were set. A new Kalman filter algorithm that is suitable for UAV clusters was designed based on the global benchmark and Riemann information geometry theory, which overcomes the discontinuity problem caused by the change of cluster centroids. Finally, the UC-IGFP method achieves the LEO continuous highprecision positioning of UAV clusters. The proposed method effectively addresses the positioning challenges caused by the strong direction of signal beams from LEO satellites and the insufficient constraint quantity of information sources at the edge nodes of the cluster. It significantly improves the accuracy and reliability of LEO-UAV cluster positioning. The results of comprehensive simulation experiments show that the proposed method has a 30.5% improvement in performance over the mainstream positioning methods, with a positioning error of 14.267 m.
Residential burglary is a severe crime that affects millions of residents each year. It is critical to analyze patterns of human behavior in surveillance video data and discover suspicious actions to avoid and deter t...
详细信息
暂无评论