Automatic driving system mainly includes four modules: perception, decision-making, planning and control. Path planning system finds the best route between the starting point and the end point for autonomous vehicles,...
详细信息
ISBN:
(数字)9781728180281
ISBN:
(纸本)9781728180298
Automatic driving system mainly includes four modules: perception, decision-making, planning and control. Path planning system finds the best route between the starting point and the end point for autonomous vehicles, and its accuracy and real-time directly determine the efficiency and safety of unmanned driving. In this paper, a vehicle model and a high-precision map are built as the precondition of the algorithm. After analyzing and comparing the problems of Floyd algorithm and A* algorithm, a hybrid path planning algorithm is proposed, which can give consideration to both global optimality and real-time. Meanwhile, collision detection rules and trajectory generation strategies are designed. Through the simulation experiment of Matlab/Simulink software platform, it is confirmed that the algorithm can meet the practical application requirements and achieve the expected performance.
Image classification is the most basic task in the field of computer vision, and accuracy is one of the most important metrics for image classification tasks. In the context of the big data era, image data have the ch...
详细信息
ISBN:
(纸本)9781665427104
Image classification is the most basic task in the field of computer vision, and accuracy is one of the most important metrics for image classification tasks. In the context of the big data era, image data have the characteristics of large data volume and complex and diverse data types. The traditional methods for image classification have a large workload and the accuracy rate is not satisfactory. In order to improve the accuracy of image classification, this paper combines convolutional neural networks and ensemble learning to propose an integrated network architecture. Compared with the base learner before integration, this structure is used to classify the Fashion-MNIST and CIFAR-10 datasets. The accuracy rate increased by 1.171% and 4.527% averagely.
As random numbers are used in various fields such as cryptography and computer science, research on such topic is essential. In this regard, studies on efficient random number generators have been conducted, and they ...
详细信息
ISBN:
(数字)9781728167589
ISBN:
(纸本)9781728199016
As random numbers are used in various fields such as cryptography and computer science, research on such topic is essential. In this regard, studies on efficient random number generators have been conducted, and they involve developments of both hardware and software aspect of the generator. This paper focuses on investigation of software-based random number generators, which can be applied to resource-limited devices including embedded devices. Studies of different algorithms and analysis of their strength will provide a strong basis of newly developed random generator in future studies.
In computer networks, a centralized control plane model of software Defined Network (SDN) often suffers from congestion because of this centralized characteristic. Fortunately, some congestion avoidance mechanisms hav...
详细信息
ISBN:
(数字)9781728173498
ISBN:
(纸本)9781728173504
In computer networks, a centralized control plane model of software Defined Network (SDN) often suffers from congestion because of this centralized characteristic. Fortunately, some congestion avoidance mechanisms have been introduced, one of which reduces the size of packets to send. However, this is considered less useful because it is longer due to the relatively small number of packets. This paper proposes a route discovery mechanism to find the best routes for packet forwarding to avoid congestion. The method explores Johnson's algorithm because it is able to take advantage of the previous Dijkstra and Bellman-Ford algorithms. The performance of the networks measured by latency, throughput, and response time shows an improvement.
Tensor decomposition models play an increasingly important role in modern data science applications. One problem of particular interest is fitting a low-rank Canonical Polyadic (CP) tensor decomposition model when the...
详细信息
ISBN:
(数字)9781728192192
ISBN:
(纸本)9781728192208
Tensor decomposition models play an increasingly important role in modern data science applications. One problem of particular interest is fitting a low-rank Canonical Polyadic (CP) tensor decomposition model when the tensor has sparse structure and the tensor elements are nonnegative count data. SparTen is a high-performance C++ library which computes a low-rank decomposition using different solvers: a first-order quasi-Newton or a second-order damped Newton method, along with the appropriate choice of runtime parameters. Since default parameters in SparTen are tuned to experimental results in prior published work on a single real-world dataset conducted using MATLAB implementations of these methods, it remains unclear if the parameter defaults in SparTen are appropriate for general tensor data. Furthermore, it is unknown how sensitive algorithm convergence is to changes in the input parameter values. This report addresses these unresolved issues with large-scale experimentation on three benchmark tensor data sets. Experiments were conducted on several different CPU architectures and replicated with many initial states to establish generalized profiles of algorithm convergence behavior.
Project management planning assessment is of great significance in project performance activities. The creation of project management cannot be effectively handled without a practical and rational strategy. This paper...
详细信息
ISBN:
(数字)9781728173108
ISBN:
(纸本)9781728173115
Project management planning assessment is of great significance in project performance activities. The creation of project management cannot be effectively handled without a practical and rational strategy. This paper offers a large-scale review analysis of articles based on machine learning and risk evaluation management for software projects. The reviews are presented and classified into two groups. The first group covers project management analysis and survey articles. The second group contains works on the steps and experimental criteria that are widely used in the management of machine learning projects. The paper provides a deeper insight and an important framework for future work in the project risk assessment, highlights the estimation of project risk using machine-learning is more efficient in reducing the project's fault and provides a further way to reduce the probability chances effectively and to increase the software development performance ratio.
Experienced developers of safety-critical and security-critical systems have long emphasized the importance of applying the highest degree of scrutiny to a system's I/O boundaries. From a safety perspective, input...
详细信息
ISBN:
(数字)9781728153650
ISBN:
(纸本)9781728153667
Experienced developers of safety-critical and security-critical systems have long emphasized the importance of applying the highest degree of scrutiny to a system's I/O boundaries. From a safety perspective, input validation is a traditional “best practice.” For security-critical architecture and design, identification of the attack surface has emerged as a primary analysis technique. One of our current research focus areas concerns the identification of and mitigation against attacks along that surface, using mathematically-based tools. We are motivated in these efforts by emerging application areas, such as assured autonomy, that feature a high degree of network connectivity, require sophisticated algorithms and data structures, are subject to stringent accreditation/certification, and encourage hardware/software co-design approaches. We have conducted several experiments employing a state-of-the-art toolchain, due to Russinoff and O'Leary, and originally designed for use in floating-point hardware verification, to determine its suitability for the creation of safety-critical/security-critical input filters. We focus first on software implementation, but extending to hardware as well as hardware/software co-designs. We have implemented a high-assurance filter for JSON-formatted data used in an Unmanned Aerial Vehicle (UAV) application. Our JSON filter is built using a table-driven lexer/parser, supported by mathematically-proven lexer and parser table generation technology, as well as verified data structures. Filter behavior is expressed in a subset of Algorithmic C, which defines a set of C++ header files providing support for hardware design, including the peculiar bit widths utilized in that discipline, and enables compilation to both hardware and software platforms. The Russinoff-O'Leary Restricted Algorithmic C (RAC) toolchain translates Algorithmic C source to the Common Lisp subset supported by the ACL2 theorem prover; once in ACL2, filter behavior can be
Aiming at the requirements of software radio receiver AGC design and related problems, using the idea of approximate linearization control, an approximate linearization AGC control model is established, and the corres...
详细信息
ISBN:
(数字)9781728152448
ISBN:
(纸本)9781728152455
Aiming at the requirements of software radio receiver AGC design and related problems, using the idea of approximate linearization control, an approximate linearization AGC control model is established, and the corresponding AGC signal processing algorithm is designed. And according to the LMS6002D radio frequency front-end circuit, the relevant working parameters are determined. Based on the software radio platform, the design and verification of the AGC hardware structure, AGC signal processing algorithm and control model are completed. Experiments show that the software radio receiver realizes the function that is high dynamic and fast AGC adjustment. This method has the characteristics of clear hierarchy, simpler implementation, less hardware resources, wide dynamic range and fast adjustment convergence.
Microservices architecture has emerged as an architectural style which focuses on the design and development of software systems as a set of small independent services. Although MSA is inspired by the Service-Oriented...
详细信息
ISBN:
(数字)9781728165790
ISBN:
(纸本)9781728165806
Microservices architecture has emerged as an architectural style which focuses on the design and development of software systems as a set of small independent services. Although MSA is inspired by the Service-Oriented Architecture style (both are service-based architectures), it presents important differences. Likewise, software architecture must evolve as new architectural styles and software frameworks arise, and the evolution of the software architecture is considered as a central feature of any software system. In this way, this paper proposes an approach to evolve SOA to MSA architectures through the use of Sarch language. To accomplish this, the language was extended to allow the modeling of the two architectural styles from the component-and-connector view, the inclusion of a decomposition view for functional properties, and the use of a model-to-model transformation algorithm.
software defined networking (SDN) is the promising technology for the future network with the advantage of isolating the control plane form the data plane. Through SDN, physical network resources can be softwarized an...
详细信息
ISBN:
(数字)9781728186955
ISBN:
(纸本)9781728186962
software defined networking (SDN) is the promising technology for the future network with the advantage of isolating the control plane form the data plane. Through SDN, physical network resources can be softwarized and virtualized easily. In future network scenarios, end users usually have customized resource demands, modeled as virtual network requests (VNRs). Hence, these VNRs need to be allocated and implemented efficiently, called as virtual network embedding (VNE). As one of the key issues in SDN, secure softwarized and virtualized resource allocation, especially in certain network scenarios with high security requirements, calls for significant attention in the literature. In this paper, we research the virtual network embedding for secure SDN, using the blockchain technology. VNE problem model for secure SDN is firstly presented. Then, it is the security model for SDN. Next, we propose our blockchain-based VNE algorithm for secure SDN. Aiming at validating our blockchain-based algorithm efficiency, we execute the experiment evaluation. Experiment results show that our blockchain-based algorithm performs better than its counterpart without blockchain technology, in terms of fault tolerant performance.
暂无评论