检索结果-内蒙古大学图书馆

Evaluating the performance of an advanced train dispatching system

Evaluating the performance of an advanced train dispatching ...

International conference on Infrastructure Systems and Services: Developing 21st Century Infrastructure Networks (INFRA)

作者： Andrea D'Ariano Francesco Corman Ingo A. Hansen Delft University of Technology Postbus Delft GA The Netherlands

ISBN: (纸本)9781424468874

In the last years, real-time railway traffic optimization experienced an increasing interest due to the expected growth of traffic and the limited possibilities of enhancing the infrastructure, which ask for a more efficient use of resources and the application of more advanced decision support tools. This paper presents a computerized train dispatching system, called ROMA (Railway traffic optimization by Means of Alternative graphs), for supporting railway traffic controllers during operations. Innovative scheduling and rerouting algorithms have been developed in order to globally optimize disturbed railway traffic conditions. ROMA can anticipate the evolution of traffic, including the propagation of delays in a regional railway network, and can estimate the effects of different dispatching measures during a period of about 15 minutes ahead. Therefore, ROMA would enable traffic controllers to frequently perform incremental changes to the actual timetable to accommodate changes in traffic patterns due to disturbances, such as train delays and blocked tracks. An extensive computational study is carried out, based on a dispatching area of the Dutch railway network, to show the high potential of our train dispatching system as a support tool to improve punctuality.

关键词： Dispatching Rail transportation Communication system traffic control Delay estimation Application software Control systems Processor scheduling Scheduling algorithm Delay effects Propagation delay

来源：评论

学校读者我要写书评

暂无评论

Accelerating Communication for Distributed Training with Collaborative In-network Aggregation

Accelerating Communication for Distributed Training with Col...

引用

International conference on Communication Technology (ICCT)

作者： Long Luo Xixi Chen Shulin Yang Wenqi Fan HongFang Yu University of Electronic Science and Technology of China

ISBN: (数字)9798350363760

ISBN: (纸本)9798350363777

Distributed training (DT) has emerged as a crucial and popular practice for training high-quality machine learning (ML) models. However, the communication efficiency of gradient aggregation during the training process has become the primary performance bottleneck. Advanced programmable switches with in-network computing capabilities offer a promising solution to improve the communication efficiency of DT by offloading partial gradient aggregation tasks from servers to switches within the network. In this paper, we propose CINA (Collaborative In-network Aggregation), a novel approach that harnesses the in-network computing capabilities of programmable switches and allows multiple switches and servers to collaboratively perform gradient aggregation tasks, thereby improving the communication efficiency of distributed machine learning training. CINA aims to minimize the aggregation completion time by jointly optimizing the aggregation task assignment among switches and the gradient routing of aggregation requests. We formulate this joint optimization problem as an integer nonlinear programming problem under multi-dimensional resource constraints and design an efficient two-stage random rounding algorithm to compute satisfactory solutions rapidly. Extensive experimental results demonstrate that CINA significantly outperforms other state-of-the-art in-network gradient aggregation solutions, reducing the aggregation completion time by up to 75%.

关键词： Training Machine learning algorithms Simulation Collaboration Machine learning Life estimation Programming Routing Servers optimization

来源：评论

学校读者我要写书评

暂无评论

ML-Driven Audit Risk Assessment with Differential Privacy

ML-Driven Audit Risk Assessment with Differential Privacy

引用

International conference on Soft Computing and Machine Intelligence (ISCMI)

作者： Zikun Zhang Ghulam Mohi-Ud-Din Yang Xiong Xu Zhang Xia Ling Lin Chen Ai Hu Min School of Information Engineering Nanchang Hangkong University Nanchang P.R China School of Software Nanchang University Nanchang P.R China College of Computer and Information Engineering Jiangxi Normal University Nanchang P.R China Network and Information Technology Center Jiangxi University of Traditional Chinese Medicine Nanchang P.R China

ISBN: (数字)9798331518127

ISBN: (纸本)9798331518134

In contemporary auditing practices, the ability to effectively identify and assess potential fraudulent companies is crucial for maintaining market fairness and transparency. Previous research has leveraged various machine learning techniques to detect fraudulent activities in financial data. However, these models often lack robustness and fail to protect the privacy of the financial information used for training. Here we introduces a novel approach by incorporating differential privacy into the training process, ensuring data protection without compromising model performance. To enhance model performance, we employed interquartile range filtering for outlier removal and optimized feature selection using Genetic Algorithm (GA), Particle Swarm optimization (PSO), and Principal Component Analysis (PCA). For model training, we employed Logistic Regression, Random Forest, and Decision Trees, with hyperparameters meticulously fine-tuned through grid search and Bayesian optimization techniques to achieve optimal performance. To address privacy concerns, we implemented differential privacy using the Laplace mechanism, effectively safeguarding sensitive financial data. Our empirical results demonstrate that the enhanced models maintain high accuracy and robustness, providing a reliable tool for fraud detection while ensuring financial data privacy.

关键词： Training Differential privacy Analytical models Adaptation models Predictive models Feature extraction Robustness Random forests Principal component analysis Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Real-Time NetFlow-based Intrusion Detection System with Improved BBNN and high-Frequency Field Programmable Gate Arrays

A Real-Time NetFlow-based Intrusion Detection System with Im...

引用

IEEE International conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Quang Anh Tran Frank Jiang JIankun Hu Faculty of Information Technology Hanoi University Hanoi Vietnam School of Engineering University of New South Wales Canberra Australia

Future large-scale complex computing environments present challenges to the real-time intrusion detection systems (IDSs). In this paper, we design a prototype with hybrid software-enabled detection engine on the basis of our improved block-based neural network (BBNN), and integrate it with a high-frequency FPGA board to form a real-time intrusion detection system. The established prototype can seamlessly feed the large-scale NetFlow data obtained from Cisco routers directly into the improved BBNN based IDS. The corresponding BBNN structure and parameter settings have been improved and experimentally tested. Experimental performance comparisons have been conducted against four major schemes of Support Vector Machine (SVM) and Naive Bayes algorithm. The results show that the improved BBNN outperforms other algorithms with respect to the classification and detection performances. The false alarm rate is successfully reduced as low as 5.14% while the genuine detection rate 99.92% is still maintained.

关键词： Field programmable gate arrays Real time systems optimization Artificial neural networks Feature extraction Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Towards an SDN-based Reconfigurable Edge Architecture for Railway Environment

Towards an SDN-based Reconfigurable Edge Architecture for Ra...

引用

International conference on Advanced Communication Technologies and Networking (CommNet)

作者： Radheshyam Singh Mohamed Aymen Chalouf Leo Mendiboure Michael Berger Lars Dittmann DTU Electro Technical University of Denmark Lyngby Denmark IRISA Lab University of Rennes 1 Lannion France COSYS-ERENA Univ. Gustave Eiffel Marne-la-Vallée France

ISBN: (数字)9798350367027

ISBN: (纸本)9798350367034

This paper presents a software-Defined Networking (SDN)-based reconfigurable edge architecture designed to optimize the allocation of services across multiple edge servers in a railway environment. The proposed system, named the ‘Intelligent Traffic Router,” dynamically assigns primary, secondary, and tertiary edge servers based on real-time load and capacity, ensuring optimal resource utilization and maintaining Quality of Service (QoS) for critical services such as autonomous and teleoperated driving. A novel mathematical model and optimization algorithm are introduced to formalize the service allocation process, considering factors such as service priority, train mobility, and server capacity. The SDN controller continuously monitors server load and capacity, reallocating resources as needed to prevent overload and maintain service continuity. performance evaluation using Mininet-WiFi and the Open Network Operating System (ONOS) SDN controller demonstrates the system’s effectiveness in dynamically managing server resources, handling edge server disconnections, and prioritizing high-priority services under heavy load conditions. Notably, the system successfully reroutes traffic to available edge servers when CPU usage exceeds 85%, ensuring uninterrupted service. The results highlight the system’s ability to enhance network stability, reliability, and efficiency, making it a viable solution for future railway transport systems.

关键词： performance evaluation Heuristic algorithms Quality of service Stability analysis Real-time systems Mathematical models Servers Resource management Reliability optimization

来源：评论

学校读者我要写书评

暂无评论

An optimal software-pipelining method for instruction-level parallel processors based on scaled retiming

An optimal software-pipelining method for instruction-level ...

引用

International Symposium on Image and Signal Processing and Analysis

作者： F. Fernandez A. Sanchez A. Duarte Dept. Fotónica FI-UPM Campus Montegancedo Madrid Spain ESCET-URJC Campus de Móstoles Madrid Spain

ISBN: (纸本)9539676940

software pipelining is an instruction-level loop scheduling method for achieving high performance fine-grain parallelism on VLIW (very long instruction word) processors. This paper presents a novel software pipelining method for non-pipelining parallel processors based on integer scaling and retiming transformations. This approach generalises and simplifies the analogous extended retiming model of T.W. O'Neil et al. (see Proc. ISCA 12th Int. Conf. Parallel & Distributed Computing Syst., p.292-7, 1999; Proc. of ICASSP'99 Conf., vol.4 p.2001-4, 1999). Matrix techniques are used in order to simplify the corresponding graph transformations. Some general properties taken from algebraic graph theory are applied in order to obtain general scheduling techniques: node and cycle methods. The two-phase scheduling method considered is first defined by means of two standard linear programming problems. We transform the corresponding problems into some variants of the maximum cost-to-time ratio problem and shortest path problem, in order to obtain efficient polynomial time algorithms. An example of software pipelining optimization of a digital correlator is also given.

关键词： Pipeline processing Processor scheduling VLIW software performance Parallel processing Distributed computing Graph theory Linear programming Shortest path problem Polynomials

来源：评论

学校读者我要写书评

暂无评论

Control Architecture for Autonomous RF Cavity Filter and Multiplexer Tuning

Control Architecture for Autonomous RF Cavity Filter and Mul...

引用

International Automatic Testing conference, AUTOTESTCON

作者： Yarkin Yigit Onder Suvak Department of Electronics Engineering Gebze Technical University ASELSAN INC. ANKARA Turkey Department of Electronics Engineering Gebze Technical University Gebze Turkey

ISBN: (数字)9781728154008

ISBN: (纸本)9781728154015

The method of tuning a cavity filter and multiplexer is a stringent process since material and manufacturing tolerances. The post-production process is not only time consuming but also expensive, especially for high-order narrowband complex filters which include coupling and cross-coupling parts. In addition to manual tuning of these filters limits precise tuning and production volumes and it increases manufacturing costs. In this scope, it is inevitable to replace this traditional manual tuning task with some more advanced and automatic methods. In order to overcome these problems, software controlled robotic tuning system is implemented. This paper introduces robotic control architecture for cavity filter and multiplexer tuning based on intelligence computer-aided tuning. The system is specially designed for miniaturized tuning screw filters. It works fully autonomously and its members are COBOT, single and multi-axis robotic arms, and a cartesian platform. Also, it includes a pattern recognition system and force-torque sensors to sense and measure all relevant data during the operation process. Rf tuning and control algorithms architectures are built on data driven model which fed and learned from data derived during the test with optimization approaches. The system works with soft locking principle to prevent damage to tuning screws. In the end, experimental automated tuned filter performance and improvement of tuning iteration times are given.

关键词： Radio frequency Multiplexing Computer architecture Filtering algorithms Fasteners software Sensor systems

来源：评论

学校读者我要写书评

暂无评论

Partial Multi-label Learning using Label Compression

Partial Multi-label Learning using Label Compression

引用

IEEE International conference on Data Mining (ICDM)

作者： Tingting Yu Guoxian Yu Jun Wang Carlotta Domeniconi Xiangliang Zhang School of Software Shandong University Jinan China College of Computer and Information Sciences Southwest University Chongqing China Joint SDU-NTU Centre for Artificial Intelligence Research Shandong University Jinan China CEMSE King Abdullah University of Science and Technology SA Department of Computer Science George Mason University VA USA

ISBN: (数字)9781728183169

ISBN: (纸本)9781728183176

Partial multi-label learning (PML) aims at learning a robust multi-label classifier from partial multi-label data, where a sample is annotated with a set of candidate labels, while only a subset of those labels is valid. The existing PML algorithms generally suffer from the high computational cost when learning with large label spaces. In this paper, we introduce a PML approach (PML-LCom) that uses Label Compression to efficiently learn from partial multi-label data. PML-LCom firstly splits the observed label data matrix into a latent relevant label matrix and an irrelevant one, and then factorizes the relevant label matrix into two low-rank matrices, one encodes the compressed labels of samples, and the other explores the underlying label correlations. Next, it optimizes the coefficient matrix of the multi-label predictor with respect to the compressed label matrix. In addition, it regularizes the compressed label matrix with respect to the feature similarity of samples, and optimizes the label matrix and predictor in a coherent manner. Experimental results on both semi-synthetic and real-world PML datasets show that PML-LCom achieves a performance superior to the state-of-the-art solutions on predicting the labels of unlabeled samples with a large label space. The label compression improves both the effectiveness and efficiency, and the coherent optimization mutually benefits the label matrix and predictor.

关键词： Correlation conferences Computational efficiency Classification algorithms Data mining optimization

来源：评论

学校读者我要写书评

暂无评论

PCAFP for Solving CNOP in Double-Gyre Variation and its Parallelization on Clusters

PCAFP for Solving CNOP in Double-Gyre Variation and its Para...

引用

IEEE International conference on high performance Computing and Communications

作者： Shijin Yuan Mi Li Bin Mu Jingpeng Wang School of Software Engineering Tongji University Shanghai China

ISBN: (纸本)9781509042982

Double-gyre ocean circulation is a typical phenomenon in the northern mid-latitude ocean basins. Its low-frequency variability significantly influences on both ocean and climate. To enhance its predictability, the finding of optimal initial perturbation which can trigger the double-gyre variation is important. CNOP method is adopted to calculate the optimal initial perturbation and this method has already been widely applied. Previous studies show that intelligent algorithms are effective methods to solve CNOP on ENSO event in ZC model. In this paper, it is the first time that intelligent algorithm is used to solve CNOP in ROMS for double-gyre variation. The dimension of the objective function is much higher than that of the ZC model and the calculation time increases dramatically, therefore effective result may not be able to be acquired in acceptable time. We propose an improved intelligent algorithm in accompany with the principal component analysis to solve CNOP, which is called principal component analysis based flower pollination (PCAFP) algorithm. To speed up furtherly, we complete both the parallelization of the nonlinear process of ROMS and the PCAFP algorithm. Different frameworks like OpenMP, MPI and CUDA on GPU are utilized and their performances are compared. Using a 20 nodes' cluster (12 cores in each node) on TH-1A supercomputer system, the computation time is reduced from 324.4 hours (about 13.5 days) to 3.71 hours, and the 87.44x speedup demonstrates that our parallelization can remarkably reduce the time cost. Hence, the proposed PCAFP with its parallelization on clusters can not only obtain optimal initial perturbation that can trigger the double-gyre variation, but also solve CNOP effectively and efficiently.

关键词： CUDA double-gyre variation ROMS CNOP PCAFP cluster parallelization OpenMP MPI

来源：评论

学校读者我要写书评

暂无评论

SBGen: A high-performance library for rapid generation of cryptographic S-boxes

引用

softwareX 2024年 27卷

作者： Kuznetsov, Alexandr Kandii, Serhii Frontoni, Emanuele Poluyanenko, Nikolay Univ Macerata Dept Polit Sci Commun & Int Relat Via Crescimbeni 30-32 I-62100 Macerata Italy eCampus Univ Fac Engn Via Isimbardi 10 I-22060 Novedrate CO Italy V N Karazin Kharkiv Natl Univ Fac Comupter Sci Dept Informat & Commun Syst Secur 4 Svobody Sq UA-61022 Kharkiv Ukraine JSC Inst Informat Technol Bakulin St 12 UA-61166 Kharkiv Ukraine Marche Polytech Univ Dept Informat Engn Via Brecce Bianche 12 I-60131 Ancona Italy

In the realm of cryptographic research, the generation of S-boxes with high nonlinearity and optimal cryptographic properties remains a critical challenge. This paper presents a novel approach to S-box generation, leveraging the strengths of heuristic optimization methods. Through a meticulous integration of Simulated Annealing (SA) and Hill Climbing (HC) algorithms with sophisticated cost functions, we introduce an innovative software tool that significantly advances the efficiency of generating highly nonlinear S-boxes. Our methodology is distinguished by its ability to consistently produce S-boxes that meet stringent security criteria, with a remarkable 100 % success rate and minimized computational overhead. A comparative analysis reveals that our approach outperforms existing methods in terms of the probability of generating target S-boxes and the average number of iterations required. The software's practical implications extend beyond theoretical advancements, offering a valuable resource for cryptographic system designers in their quest to fortify cipher systems against linear and differential cryptanalysis. By setting new benchmarks for nonlinearity and search efficiency, our work paves the way for future research in cryptographic S-box generation, highlighting the potential of combining heuristic techniques with domain-specific cost functions to achieve superior security outcomes.

关键词： S-box generation Cryptographic security Heuristic optimization Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：