Recurrent and convolutional neural networks for deep terrain classification by autonomous robots

The future challenge for field robots is to increase the level of autonomy towards long distance (>1 km) and duration (>1h) applications. One of the key technologies is the ability to accurately estimate the properties of the traversed terrain to optimize onboard control strategies and energy efficient path-planning, ensuring safety and avoiding possible immobilization conditions that would lead to mission failure. Two main hypotheses are put forward in this research. The first hypothesis is that terrain can be effectively detected by relying exclusively on the measurement of quantities that pertain to the robot-ground interaction, i.e., on proprioceptive signals. Therefore, no visual or depth information is required. Then, artificial deep neural networks can provide an accurate and robust solution to the classification problem of different terrain types. Under these hypotheses, sensory signals are classified as time series directly by a Recurrent Neural Network or by a Convolutional Neural Network in the form of higher-level features or spectrograms resulting from additional processing. In both cases, results obtained from real experiments show comparable or better performance when contrasted with standard Support Vector Machine with the additional advantage of not requiring an a priori definition of the feature space.     

Hierarchical Model-Based Clustering for Large Datasets

In recent years, hierarchical model-based clustering has provided promising results in a variety of applications. However, its use with large datasets has been hindered by a time and memory complexity that are at least quadratic in the number of observations. To overcome this difficulty, this article proposes to start the hierarchical agglomeration from an efficient classification of the data in many classes rather than from the usual set of singleton clusters. This initial partition is derived from a subgraph of the minimum spanning tree associated with the data. To this end, we develop graphical tools that assess the presence of clusters in the data and uncover observations difficult to classify. We use this approach to analyze two large, real datasets: a multiband MRI image of the human brain and data on global precipitation climatology. We use the real datasets to discuss ways of integrating the spatial information in the clustering analysis. We focus on two-stage methods, in which a second stage of processing using established methods is applied to the output from the algorithm presented in this article, viewed as a first stage.     

Object and Mathematical Simulation of Ammonium Hexafluorosilicate Sublimation

An integration of different modelling methods including object and mathematical simulation are suggested for sublimation processes of inorganic fluorides to optimally simulate the real technological conditions. The paper presents the results of testing this methodology on ammonium hexafluorosilicate sublimation.     

Hierarchical Implicit Shape Modeling

In this paper, a new hierarchical approach for object detection is proposed. Object detection methods based on Implicit Shape Model (ISM) efficiently handle deformable objects, occlusions and clutters. The structure of each object in ISM is defined by a spring like graph. We introduce hierarchical ISM in which structure of each object is defined by a hierarchical star graph. Hierarchical ISM has two layers. In the first layer, a set of local ISMs are used to model object parts. In the second layer, structure of parts with respect to the object center is modeled by global ISM. In the proposed approach, the obtained parts for each object category have high discriminative ability. Therefore, our approach does not require a verification stage. We applied the proposed approach to some datasets and compared the performance of our algorithm to comparable methods. The results show that our method has a superior performance.     

Linguistic cost-sensitive learning of genetic fuzzy classifiers for imprecise data

Cost-sensitive classification is based on a set of weights defining the expected cost of misclassifying an object. In this paper, a Genetic Fuzzy Classifier, which is able to extract fuzzy rules from interval or fuzzy valued data, is extended to this type of classification. This extension consists in enclosing the estimation of the expected misclassification risk of a classifier, when assessed on low quality data, in an interval or a fuzzy number. A cooperative-competitive genetic algorithm searches for the knowledge base whose fitness is primal with respect to a precedence relation between the values of this interval or fuzzy valued risk. In addition to this, the numerical estimation of this risk depends on the entrywise product of cost and confusion matrices. These have been, in turn, generalized to vague data. The flexible assignment of values to the cost function is also tackled, owing to the fact that the use of linguistic terms in the definition of the misclassification cost is allowed.     

Constructing the Co cyclic Structures for Crossed Copro duct Coalgebras

In this paper, we construct a cocylindrical object associated to two coal-gebras and a cotwisted map. It is shown that there exists an isomorphism between the cocyclic object of the crossed coproduct c...     

An improved ensemble learning machine for biological activity prediction of tyrosine kinase inhibitors

Boosting is one of the most important strategies in ensemble learning because of its ability to improve the stability and performance of weak learners. It is nonparametric, multivariate, fast and interpretable but is not robust against outliers. To enhance its prediction accuracy as well as immunize it against outliers, a modified version of a boosting algorithm (AdaBoost R2) was developed and called AdaBoost R3. In the sampling step, extremum samples were added to the boosting set. In the robustness step, a modified Huber loss function was applied to overcome the outlier problem. In the output step, a deterministic threshold was used to guarantee that bad predictions do not participate in the final output. The performance of the modified algorithm was investigated with two anticancer data sets of tyrosine kinase inhibitors, and the mechanism of inhibition was studied using the relative weighted variable importance procedure. Investigating the effect of base learner's strength reveals that boosting is only successful using the classification and regression tree method (a weak to moderate learner) and does not have a significant effect using the radial basis functions partial least square method (a strong base learners). Copyright © 2015 John Wiley & Sons, Ltd.     

基于DM8148的警戒区域告警算法的实现

智能视频监控作为安全防范的一种有效手段,有广阔的应用前景。针对这一需求,提出了一种基于DM8148平台的警戒区域告警算法。该算法采用混合高斯模型,结合背景减法检测移动目标,线性预测结合Blob匹配跟踪运动轨迹,分析目标行为判断是否存在警戒区域入侵现象。通过实验验证,该算法所具备的低误报率和高报警精度能满足智能监控对高效率、高实时性要求。