Autonomous navigation, as a fundamental problem of intelligent mobile robots' research, is the key technology of mobile robot to realize autonomous and intelligent. A method of combing computer vision and machine ...
详细信息
ISBN:
(纸本)9783319410098;9783319410081
Autonomous navigation, as a fundamental problem of intelligent mobile robots' research, is the key technology of mobile robot to realize autonomous and intelligent. A method of combing computer vision and machine learning for the problem of robot indoor navigation is proposed in the paper. It realizes robot autonomous navigation through imitating the behavior of experts. through a camera to perceive environmental information, expert provides some examples of navigation for robot to learn and robot learns a control strategy based on these samples using imitation learning algorithm. When robot is running, the control strategy learned can infer a corresponding control command based on the current perception of environmental information. therefore, robot is able to mimic the behavior of expert to navigate autonomously.
Hyper-threading (or HT, for short) is a technology used in some Intel CPUs. Intel claims that it can use processor resources more efficiently. Many past studies have evaluated the performance of the technology in HPC ...
详细信息
ISBN:
(纸本)9783319410098;9783319410081
Hyper-threading (or HT, for short) is a technology used in some Intel CPUs. Intel claims that it can use processor resources more efficiently. Many past studies have evaluated the performance of the technology in HPC clusters. In this paper, we discuss the advantages and disadvantages of Hyper-threading using in the cloud computing systems. We evaluate the performance and energy cost of Intel CPU with Hyper-threading enabled and disabled on virtualization environment. Our results show that Hyper-threading technology can get better performance in most cases on a physical machine. the performance of a single core in a virtual machine is slightly lower when HT is enabled. But it doubles the number of available cores.
Agent-based models (ABMs) continue to find uses for simulating many complex systems. Spatial or cellular ABMs are particularly useful when they contain a large number of simple microscopic agents. Visualising such man...
详细信息
ISBN:
(纸本)9780889869790
Agent-based models (ABMs) continue to find uses for simulating many complex systems. Spatial or cellular ABMs are particularly useful when they contain a large number of simple microscopic agents. Visualising such many-component models remains challenging however and while 3D graphical rendering technologies can help considerably, sometimes being able to examine a physical model artifact is a better aid to understanding emergent model properties. Additive manufacturing techniques and platforms are becoming commercially affordable for routine use in 3d-printing model artifacts. We describe how an ABM such as the Eden growth model can generate complex 3D structures-effectively tumorous clusters-that can be 3d-printed as physical artifacts and which can be handled and examined directly. We describe some current 3dprint technologies, and the algorithms and software needed to 3d-print realisations of such simulation cellular models. We discuss the capabilities of present 3d-printing technologies and likely future directions of development, as well as what will be needed to make cellular model printing routine.
the present paper represents a continuation of [3]. there, we studied a new class of variational inequalities involving a pseudomonotone univalued operator and a multivalued operator, for which we obtained an existenc...
详细信息
this study explores best cases how schools use and make benefit of technology investment in Georgia. We consider schools as learning ecosystem of three types of services - Internal, External and Trade-off - in three e...
详细信息
ISBN:
(纸本)9783319474403;9783319474397
this study explores best cases how schools use and make benefit of technology investment in Georgia. We consider schools as learning ecosystem of three types of services - Internal, External and Trade-off - in three educational domains of digital infrastructure, learning facilitation and change management. Multiple case study strategy was used in 15 schools of Georgia with purposive sampling. K-means cluster analysis was applied to group schools based on the grid of services. We built Bayesian Dependency model to find probabilistic dependencies of the services in digitally enhanced schools. the model is explained on the case studies of 3 Georgian schools. the findings suggest that trade-off type of services and change management services are the biggest determinant of the schools belonging to the innovative technology-enhanced learning ecosystems.
the segmentation is the first important step for optical character recognition (OCR) system. It separate the image text documents into line, characters and word. the accuracy of the recognition system mainly rely on t...
详细信息
the security of communication and preservation for digital image has great significance in modern society. In this paper, DNA splicing model was combined with hash function to encrypt grayscale image. In the proposed ...
详细信息
ISBN:
(纸本)9783319410098;9783319410081
the security of communication and preservation for digital image has great significance in modern society. In this paper, DNA splicing model was combined with hash function to encrypt grayscale image. In the proposed algorithm, hash function was used to scramble the positions of pixel values from original image. DNA splicing model and XOR operation were used to diffuse pixel values. Additionally, the chaotic sequences which were generated by the chaotic map were used to encrypt grayscale image. Experiment results and simulation analysis have proved that the algorithm has many advantages. Its key space is huge. It has stronger key sensitivity. It is safe enough to resist all types of recognized attacks including exhaustive attacks, statistical attacks and differential attacks.
Particle swarm optimization (PSO) is one of the most important swarm intelligence optimization algorithms due to its ease of implement and outstanding performance. As an information flow system, PSO is influenced by t...
详细信息
ISBN:
(纸本)9783319410005;9783319409993
Particle swarm optimization (PSO) is one of the most important swarm intelligence optimization algorithms due to its ease of implement and outstanding performance. As an information flow system, PSO is influenced by the population structure to a great extent. While previous works considered several classical structure, such as fully-connected and ring structures, here we systematically explore the impact of population structure, including scale-free and small-world networks that have been found in many real-world complex systems. In particular, we examine the influence of average degree, degree distribution and topological randomness of the networks underlying PSO. Our results are not only useful for developing more effective structures to improve the performance of PSO but also helpful in bridging the two fast-growing fields-network science and swarm intelligence.
We deal with a regularized optimal control problem governed by a nonlinear hyperbolic initial-boundary value problem describing behaviour of a viscoelastic plate vibrating against a rigid obstacle. A variable thicknes...
详细信息
In this paper we present the latest improvements to the Russian spontaneous speech recognition system developed in Speech technology Center (STC). Significant word error rate (WER) reduction was obtained by applying h...
详细信息
ISBN:
(纸本)9783319439587;9783319439570
In this paper we present the latest improvements to the Russian spontaneous speech recognition system developed in Speech technology Center (STC). Significant word error rate (WER) reduction was obtained by applying hypothesis rescoring with sophisticated language models. these were the Recurrent Neural Network Language Model and regularized Long-Short Term Memory Language Model. For acoustic modeling we used the deep neural network (DNN) trained with speaker-dependent bottleneck features, similar to our previous system. this DNN was combined withthe deep Bidirectional Long Short-Term Memory acoustic model by the use of score fusion. the resulting system achieves WER of 16.4%, with an absolute reduction of 8.7% and relative reduction of 34.7% compared to our previous system result on this test set.
暂无评论