With the widespread adoption of traffic encryption technologies, detecting attack behaviors in encrypted malware traffic has become a critical and challenging problem. The encrypted malware traffic contains a lot of r...
详细信息
ISBN:
(纸本)9798350391367;9798350391374
With the widespread adoption of traffic encryption technologies, detecting attack behaviors in encrypted malware traffic has become a critical and challenging problem. The encrypted malware traffic contains a lot of redundant information and noise, which necessitates additional computational resources. In addition, new attack categories continue to emerge over time, resulting in traditional detection methods losing effectiveness in identifying these new attacks. To handle the above challenge, in this paper, we propose CIL4EMTD, a novel Class Incremental Learning method targeted for Encrypted Malware Traffic Detection. Our method leverages clustering techniques to enrich the extraction of dataset features, while specifically customizing LwF for detecting encrypted malware to optimize the stability of model training via efficient knowledge distillation. To verify the effectiveness of CIL4EMTD, we conduct experiments comparing it with other class incremental learning methods. The experiment results show that CIL4EMTD demonstrates state-of-the-art performance on a real-world dataset, achieving a recognition accuracy of 94.34% for new categories while maintaining the average accuracy for known categories within a margin of less than a 10% decline.
The classification of low permeability-tight reservoirs is the premise of development. The deep reservoir of Shahejie 3 member contains rich low permeability-tight reserves, but the strong heterogeneity and complex mi...
详细信息
The classification of low permeability-tight reservoirs is the premise of development. The deep reservoir of Shahejie 3 member contains rich low permeability-tight reserves, but the strong heterogeneity and complex micro pore structure make the main controlling factors subjective and the classification boundaries unclear. Therefore, a new indicator considering the interaction between fluid and rock named Threshold Flow Zone Indicator(TFZI) is proposed, it can be used as the main sequence of correlation analysis to screen the main controlling factors, and the clustering algorithm is optimized combined with probability distribution to determine the classification boundaries. The sorting coefficient, main throat radius, movable fluid saturation and displacement pressure are screened as the representative parameters for the following four key aspects: rock composition, microstructure, flow capacity and the interaction between rock and fluid. Compared with the traditional probability distribution and clustering algorithm, the boundary of the optimized clustering algorithm proposed in this paper is more *** classification results are consistent with sedimentary facies, oil levels and oil production *** method provides an important basis for the development of low permeability-tight reservoirs.
clustering is an important algorithm for data mining. FSC is a kind of clustering algorithm based on density, which has been proposed in the journal Science in 2014. FSC only requires one input parameter and has a hig...
详细信息
ISBN:
(纸本)9781509018949
clustering is an important algorithm for data mining. FSC is a kind of clustering algorithm based on density, which has been proposed in the journal Science in 2014. FSC only requires one input parameter and has a higher practicability. RFSC, which is an improved algorithm of FSC algorithm, is less sensitive to the input parameters and faster. However, neither RFSC nor FSC can deal with uneven density data sets. In order to solve that problem, we propose an improved algorithm KFSC in this paper by dynamically controlling of the width of the kernel function. KFSC uses the idea of attractor of the DENCLUE and can customize their own personalized attraction for each point. The experimental results on synthetic data sets show that KFSC has a better performance on uneven density data sets than FSC and RFSC.
As artificial intelligence and human life become increasingly inseparable, the legal or ethical issues faced by artificial intelligence systems in autonomous decision-making are also increasing. During the training pr...
详细信息
As artificial intelligence and human life become increasingly inseparable, the legal or ethical issues faced by artificial intelligence systems in autonomous decision-making are also increasing. During the training process, the algorithms may be influenced by human biases such as gender, race, and other factors, leading to discrimination and affecting fairness. To establish secure intelligent systems, fair machine learning has become a popular research direction. This work demonstrates the existing definitions of fairness and designs experiments to show that combining clustering algorithms into the data handling process can effectively improve the classification accuracy and fairness on bank loan dataset. In the case study, K-means clustering, hierarchical clustering and Gaussian Mixture Model are used, proving that the clustering algorithms can significantly improve the accuracy of the model and ensure the relative fairness of the classification results.
The Russia-Ukraine conflict has demonstrated that urban combat capability will become a core element determining the outcome of local wars. With the intelligent transformation of urban combat systems, their highly rel...
详细信息
ISBN:
(纸本)9798350379860;9798350379877
The Russia-Ukraine conflict has demonstrated that urban combat capability will become a core element determining the outcome of local wars. With the intelligent transformation of urban combat systems, their highly reliable, anti-interference, and robust communication networks have become the premise for instant "seamless communication" connecting various equipment platforms on the battlefield. Due to the characteristics of wireless self-organizing networks, such as decentralized networking, multi-hop long-distance transmission, and support for node mobility, they are widely used in the construction of terminal subnets for urban combat systems, enabling significant enhancements in human-computer interaction and collaborative reconnaissance and strike capabilities. This paper proposes an elastic networking topology control mechanism based on the Grey Wolf Optimizer algorithm for the network layer of self-organizing networks, and conducts simulation and comparative analysis. The results indicate that this method enhances the networking flexibility and network lifespan of self-organizing networks, ensuring reliable communication for urban combat.
It is challenging to detect small targets in aerial images captured by drones due to variations in target sizes and occlusions arising from the surrounding environment. This study proposes an optimized object detectio...
详细信息
It is challenging to detect small targets in aerial images captured by drones due to variations in target sizes and occlusions arising from the surrounding environment. This study proposes an optimized object detection algorithm based on YOLOv7 to address the above-mentioned challenges. The proposed method comprises the design of a Genetic Kmeans (1IoU) clustering algorithm to obtain customized anchor boxes that more significantly apply to the dataset. Moreover, the SPPFCSPC_group structure is optimized using group convolutions to reduce model parameters. The fusion of Spatial Pyramid Pooling-Fast (SPPF) and Cross Stage Partial (CSP) structures leads to increased detection accuracy and enhanced multi-scale feature fusion network. Furthermore, a Detect Head is incorporated into the classification phase for more accurate position and class predictions. According to experimental findings, the optimized YOLOv7 algorithm performs quite well on the VisDrone2019 dataset in terms of detection accuracy. Compared with the original YOLOv7 algorithm, the optimized version shows a 0.18% increase in the Average Precision (AP), a reduction of 5.7 M model parameters, and a 1.12 Frames Per Second (FPS) improvement in the frame rate. With the above described enhancements in AP and parameter reduction, the precision of small target detection and the real-time detection speed are increased notably. In general, the optimized YOLOv7 algorithm offers superior accuracy and real-time capability, thus making it well-suited for small target detection tasks in real-time drone aerial photography.
To address the poor performance of commonly used intelligent optimization algorithms in solving location problems—specifically regarding effectiveness,efficiency,and stability—this study proposes a novel location al...
详细信息
To address the poor performance of commonly used intelligent optimization algorithms in solving location problems—specifically regarding effectiveness,efficiency,and stability—this study proposes a novel location allocation method for the delivery sites to deliver daily necessities during epidemic *** establishing the optimization objectives and constraints,we developed a relevant mathematical model based on the collected data and utilized traditional intelligent optimization algorithms to obtain Pareto optimal *** on the characteristics of these Pareto front solutions,we introduced an improved clustering algorithm and conducted simulation experiments using data from Changchun *** results demonstrate that the proposed algorithm outperforms traditional intelligent optimization algorithms in terms of effectiveness,efficiency,and stability,achieving reductions of approximately 12%and 8%in time and labor costs,respectively,compared to the baseline algorithm.
Recently, a variety of medical imaging technologies have been used widely in clinical diagnosis. As a large number of medical images are produced everyday, it becomes a hot issue of data mining on medical image in cur...
详细信息
ISBN:
(纸本)9781467376839
Recently, a variety of medical imaging technologies have been used widely in clinical diagnosis. As a large number of medical images are produced everyday, it becomes a hot issue of data mining on medical image in current that how to make full use of these medical images and cluster efficiently to help doctors to diagnose. In this paper, we propose a medical image clustering method. Firstly, medical image dataset is represented as a weighted, undirected and completed graph. Secondly, the graph is sparsified and pruned. This model can describe the similarity between medical images very well. Last, weighted and undirected graph clustering method based on graph entropy is proposed to cluster these medical images. The experimental results show that this method can cluster medical images efficiently and run well in time complexity and clustering results.
3D object instance segmentation plays a vital role in various applications such as autonomous driving, robotics and virtual reality. However, tabletop scenes exhibit diverse object complexities and size variations. Th...
详细信息
3D object instance segmentation plays a vital role in various applications such as autonomous driving, robotics and virtual reality. However, tabletop scenes exhibit diverse object complexities and size variations. The challenge is to enhance the accuracy of segmenting these scenes for multiple object instances. This limitation directly impacts robots' capabilities to effectively grasp and manipulate objects. In this paper, we propose a multi-scale deep learning and clustering-based approach for object instance segmentation in tabletop scenes. Our approach incorporates a multi-scale neighborhood feature sampling (MNFS) module specifically designed to extract local features, and a clustering algorithm to eliminate noise and preserve instance integrity. Furthermore, we combine the strength of both methods through ScoreNet and non-maximal suppression. We conducted extensive experiments on TO-Scene, the first large-scale dataset of 3D tabletop scenes, and observed an average mIoU improvement of approximately 4.07% compared to existing methods. This highlights the superior performance of our proposed method. In addition, we tested our algorithm on a real-scene robotics platform and showed that it has good performance and generalization capabilities to support future applications such as robot grasping.
This paper proposes a distributed task allocation algorithm based on game theory to solve the complex task allocation optimization problem when UAV clusters carry heterogeneous resources and tasks have heterogeneous d...
详细信息
This paper proposes a distributed task allocation algorithm based on game theory to solve the complex task allocation optimization problem when UAV clusters carry heterogeneous resources and tasks have heterogeneous demands. Considering the heterogeneity of resources,two pre-processing methods are proposed: one is the grouping algorithm that combines greedy algorithm with simulated annealing algorithm, and the other is the improved K-medoids clustering algorithm based on heterogeneous resources. These pre-process methods, through grouping and clustering, can reduce the complexity of task allocation. The entropy weight method is utilized to prioritize tasks based on multiple metrics. Considering task demands,airborne resources and path cost, a coalition formation game model is established, which is proved to be a potential game. Then a distributed task allocation algorithm based on coalition formation game is designed to address the task allocation problem. Finally, the simulation involving 30 tasks with heterogeneous requirements assigned to 100 UAVs validates the effectiveness of the proposed algorithm, showing that it can achieve good task allocation results with great real-time performance.
暂无评论