With the development of deep learning in recent years, code representation learning techniques have become the foundation of many software engineering tasks such as program classification [1] and defect detection. Ear...
With the development of deep learning in recent years, code representation learning techniques have become the foundation of many software engineering tasks such as program classification [1] and defect detection. Earlier approaches treat the code as token sequences and use CNN, RNN, and the Transformer models to learn code representations.
Owing to the extensive applications in many areas such as networked systems,formation flying of unmanned air vehicles,and coordinated manipulation of multiple robots,the distributed containment control for nonlinear m...
Owing to the extensive applications in many areas such as networked systems,formation flying of unmanned air vehicles,and coordinated manipulation of multiple robots,the distributed containment control for nonlinear multiagent systems (MASs) has received considerable attention,for example [1,2].Although the valued studies in [1,2] investigate containment control problems for MASs subject to nonlinearities,the proposed distributed nonlinear protocols only achieve the asymptotic *** a crucial performance indicator for distributed containment control of MASs,the fast convergence is conducive to achieving better control accuracy [3].The work in [4] first addresses the backstepping-based adaptive fuzzy fixed-time containment tracking problem for nonlinear high-order MASs with unknown external ***,the designed fixedtime control protocol [4] cannot escape the singularity problem in the backstepping-based adaptive control *** is well known,the singularity problem has become an inherent problem in the adaptive fixed-time control design,which may cause the unbounded control inputs and even the instability of controlled ***,how to solve the nonsingular fixed-time containment control problem for nonlinear MASs is still open and awaits breakthrough to the best of our knowledge.
False data injection attack(FDIA)can affect the state estimation of the power grid by tampering with the measured value of the power grid data,and then destroying the stable operation of the smart *** work usually tra...
详细信息
False data injection attack(FDIA)can affect the state estimation of the power grid by tampering with the measured value of the power grid data,and then destroying the stable operation of the smart *** work usually trains a detection model by fusing the data-driven features from diverse power data ***-driven features,however,cannot effectively capture the differences between noisy data and attack *** a result,slight noise disturbances in the power grid may cause a large number of false detections for FDIA *** address this problem,this paper designs a deep collaborative self-attention network to achieve robust FDIA detection,in which the spatio-temporal features of cascaded FDIA attacks are fully ***,a high-order Chebyshev polynomials-based graph convolution module is designed to effectively aggregate the spatio information between grid nodes,and the spatial self-attention mechanism is involved to dynamically assign attention weights to each node,which guides the network to pay more attention to the node information that is conducive to FDIA ***,the bi-directional Long Short-Term Memory(LSTM)network is introduced to conduct time series modeling and long-term dependence analysis for power grid data and utilizes the temporal self-attention mechanism to describe the time correlation of data and assign different weights to different time *** designed deep collaborative network can effectively mine subtle perturbations from spatiotemporal feature information,efficiently distinguish power grid noise from FDIA attacks,and adapt to diverse attack *** experiments demonstrate that our method can obtain an efficient detection performance over actual load data from New York Independent System Operator(NYISO)in IEEE 14,IEEE 39,and IEEE 118 bus systems,and outperforms state-of-the-art FDIA detection schemes in terms of detection accuracy and robustness.
1 Introduction The Internet of Things(IoT)has facilitated the development of numerous fields in our ***,some equipment in IoT environment lacks sufficient storage and data processing capabilities[1].A feasible strateg...
详细信息
1 Introduction The Internet of Things(IoT)has facilitated the development of numerous fields in our ***,some equipment in IoT environment lacks sufficient storage and data processing capabilities[1].A feasible strategy is to leverage the powerful computing capabilities of cloud servers to process the data within the IoT devices.
With the recent increase in the risks and attacks facing our daily lives and digital environment around us, the trend towards securing data has become inevitable. Block ciphers play a crucial role in modern crypto-app...
详细信息
In the era of large-scale pretrained models, artificial neural networks（ANNs） have excelled in natural language understanding（NLU） tasks. However, their success often necessitates substantial computational resourc...
详细信息
In the era of large-scale pretrained models, artificial neural networks（ANNs） have excelled in natural language understanding（NLU） tasks. However, their success often necessitates substantial computational resources and energy consumption. To address this, we explore the potential of spiking neural networks（SNNs） in NLU——a promising avenue with demonstrated advantages, including reduced power consumption and improved efficiency due to their event-driven characteristics. We propose the SpikingMiniLM,a novel spiking Transformer model tailored for natural language understanding. We first introduce a multi-step encoding method to convert text embeddings into spike trains. Subsequently, we redesign the attention mechanism and residual connections to make our model operate on the pure spike-based paradigm without any normalization technique. To facilitate stable and fast convergence, we propose a general parameter initialization method grounded in the stable firing rate principle. Furthermore, we apply an ANN-to-SNN knowledge distillation to overcome the challenges of pretraining SNNs. Our approach achieves a macro-average score of 75.5 on the dev sets of the GLUE benchmark, retaining 98% of the performance exhibited by the teacher model MiniLMv2. Our smaller model also achieves similar performance to BERTMINIwith fewer parameters and much lower energy consumption, underscoring its competitiveness and resource efficiency in NLU tasks.
This paper presents our research in the area of medical imaging diagnostics, focusing specifically on countering the devastating impact of the COVID-19 pandemic and numerous pulmonary pathologies. Using new deep-learn...
详细信息
Obfuscation techniques are frequently used in malicious programs to evade detection. However, current effective methods often require much memory space during training. This paper proposes a machine-learning-based sol...
详细信息
Locating multiple objects has become an important task in multimedia research and applications due to the common nature of real-world images. Object localization requires a large number of visual annotations, such as ...
详细信息
Due to the unclear distribution characteristics and causes of fluoride in groundwater of Mihe-Weihe River Basin(China),there is a higher risk for the future development and utilization of ***,based on the systematic s...
详细信息
Due to the unclear distribution characteristics and causes of fluoride in groundwater of Mihe-Weihe River Basin(China),there is a higher risk for the future development and utilization of ***,based on the systematic sampling and analysis,the distribution features and enrichment mechanism for fluoride in groundwater were studied by the graphic method,hydrogeochemical modeling,the proportionality factor between conventional ions and factor *** results show that the fluorine content in groundwater is generally on the high side,with a large area of medium-fluorine water(0.5–1.0 mg/L),and high-fluorine water is chiefly in the interfluvial lowlands and alluvial-marine plain,which mainly contains HCO_(3)·Cl-Na-and HCO_(3)^(-)Na-type *** vertical zonation characteristics of the fluorine content decrease with increasing depth to the water *** high flouride groundwater during the wet season is chiefly controlled by the weathering and dissolution of fluorine-containing minerals,as well as the influence of rock weathering,evaporation and *** weak alkaline environment that is rich in sodium and poor in calcium during the dry season is the main reason for the enrichment of ***,an integrated assessment model is established using rough set theory and an improved matter element extension model,and the level of groundwater pollution caused by fluoride in the Mihe-Weihe River Basin during the wet and dry seasons in the Shandong Peninsula is defined to show the necessity for local management measures to reduce the potential risks caused by groundwater quality.
暂无评论