The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Studies on nowadays human-machine interface have demonstrated that visual information can enhance speech recognition accuracy especially in noisy environments. Deep learning has been widely used to tackle such audio visual speech recognition (AVSR) problem due to its astonishing achievements in both speech recognition and image recognition. Although existing deep learning models succeed to incorporate...
This paper presents a method for predicting slip using Gaussian process regression. Slip models are learned for visually classified terrain types as a function of terrain geometry. Spatial correlations between terrain properties are leveraged for on-line slip model adaptation. Results show that regression-based modeling using in-situ rover data outperforms the state-of-practice, terrestrially-calibrated...
A key challenge in scaling up robot learning to many skills and environments is removing the need for human supervision, so that robots can collect their own data and improve their own performance without being limited by the cost of requesting human feedback. Model-based reinforcement learning holds the promise of enabling an agent to learn to predict the effects of its actions, which could provide...
Recently, end-to-end learning frameworks are gaining prevalence in the field of robot control. These frameworks input states/images and directly predict the torques or the action parameters. However, these approaches are often critiqued due to their huge data requirements for learning a task. The argument of the difficulty in scalability to multiple tasks is well founded, since training these tasks...
Traditional software engineering programming paradigms are mostly object or procedure oriented, driven by deterministic algorithms. With the advent of deep learning and cognitive sciences there is an emerging trend for data-driven programming, creating a shift in the programming paradigm among the software engineering communities. Visualizing and interpreting the execution of a current large scale...
The Big data challenge includes dealing with a big number of heterogeneous and multidimensional datasets of all possible sizes not only with data of big size. As a result a huge number of Machine Learning (ML) tasks, which must be solved dramatically exceeds the number of data scientists who can solve these tasks. Next many ML tasks require critical input from subject matter experts (SME) and end...
Impact crater is the major geomorphic feature on the lunar surface. More than 8.2 million valid data samples were obtained by the Chang'E-l Laster Altimeter(LAM) and the craters are hidden among them. In order to visualize the topographical structure of these craters with high accuracy and computational stability, a novel scattered data fitting method was proposed in this paper. Based on the characteristics...
Uncertain data visualization plays a fundamental role in many applications such as weather forecast and analysis of fluid flows. Exploring scalar uncertain data modeled as probability distribution fields is a challenging task because the underlying features are often more complex, and the data associated with each grid point are high dimensional. In this work, we present a compact and effective representation,...
In this paper, we provide an insight of visual saliency modeling from the perspective of simulating visual information manipulation process in human vision system. For humans, visual stimuli are converted into spike trains by retina, and the spike signals are then transferred to brain areas for further analysis. Therefore, we propose to estimate image saliency based on a retina neural network, which...
Microscopic analysis of histological sections is considered the “gold standard” to verify structural parcellations in the human brain. Its high resolution allows the study of laminar and columnar patterns of cell distributions, which build an important basis for the simulation of cortical areas and networks. However, such cytoarchitectonic mapping is a semiautomatic, time consuming process that does...
Technology management data refers to all the data which is produced in the process of research and has witnessed rapid development in the literature. However, there lacks mapping and visualization of it in global scope. To identify the state and trend of technology management data, the paper uses Citespace to conduct a series of analysis, including the distribution of core authors, journal, countries...
In software engineering, project scheduling is an essential factor that determines success of projects. Success is influenced by various project scheduling estimates, such as accurate estimates of project's duration and budget. These estimates highly depend on uncertainties related to commonly occurring unpredictable events during a project's duration. Furthermore, budget and duration estimates depend...
There is an increasing demand to explore similar entities in big graphs. For example, in domains like biomedical science, identifying similar entities may contribute to developing new drugs or discovering new diseases. In this paper, we demonstrate a graph exploration system, called GQFast, which provides a graphical interface to help users efficiently explore similar entities. Methodologically, GQFast...
Kernel function implicitly maps data from its original space to a higher dimensional feature space. Kernel based machine learning algorithms are typically applied to data that is not linearly separable in its original space. Although kernel methods are among the most elegant part of machine learning, it is challenging for users to define or select a proper kernel function with optimized parameter...
In various data of network intrusion detection used for classification algorithm's learning, a great deal of noise and outlier data are mixed. In case of a learning performed by using data of high impurities, no matter how the performance of classification algorithm is outstanding, any network intrusion detection model of high performance becomes hard to anticipate. To increase the accuracy of network...
The applied research for visualization methods in recommendation systems are demonstrated from the data analysis, results and explanation of the recommendations and human-computer interaction. First, various categories of visualization methods thoughts are described, and their characteristics, pros and cons are analyzed. Second, the typical application applying visualization methods are listed. Finally,...
We study the problem of zero-shot classification in which we don't have labeled data in target domain. Existing approaches learn a model from source domain and apply it without adaptation to target domain, which is prone to domain shift problem. To solve the problem, we propose a novel Learning Discriminative Instance Attribute(LDIA) method. Specifically, we learn a projection matrix for both the...
During the teleoperation of construction machines, it is highly needed to visualize the machine body itself. This is because the operator needs to perform a visual confirmation of the construction machine. In addition, information of crawler parts' shoe slip is indispensable. Therefore, not only the surrounding environment but also the vehicle body are needed to be visualized. This paper proposes...
Exponential growth in data volume originating from Internet of Things sources and information services drives the industry to develop new models and distributed tools to handle big data. In order to achieve strategic advantages, effective use of these tools and integrating results to their business processes are critical for enterprises. While there is an abundance of tools available in the market,...
Computational visual aesthetics has recently become an active research area. Existing state-of-art methods formulate this as a binary classification task where a given image is predicted to be beautiful or not. In many applications such as image retrieval and enhancement, it is more important to rank images based on their aesthetic quality instead of binary-categorizing them. Furthermore, in such...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.