Mapping of soil nutrients in an abandoned Chinese coal mine and waste disposal site

The present paper attempts to identify the spatial patterns of soil nutrients in the abandoned Haizhou opencast coal mine and waste disposal site, in China. A geostatistical approach was used to overcome problems due to the heterogeneity of the site (some parts have been abandoned for more than 30 years, lack of clean soil, presence of overburden and low-grade ore, co-disposal of wastes from adjacent sites) and the limited number of available samples. One hundred and eight soil samples were collected from an area of 332 ha and analyzed for pH, organic matter (OM), NH₄–N, available phosphorus (AP) and available potassium (AK). The results indicate that nutrients exhibit different spatial distribution and only NH₄–N showed strong spatial dependence and a relatively large nugget effect. Relatively high content of OM, NH₄–N, AP and AK was seen in the northeastern part, whereas pH was higher in central north and southern parts of the site. The determination of the spatial variability and heterogeneity of nutrients in mining and waste disposal sites assesses the need for amendments and assists in the selection of the most feasible revegetation scheme.     

Design of efficient shape feature for object-based watermarking technology

Multimedia Tools and Applications - The accelerated development of IT technologies on the Internet for fast provision of commercial multimedia services has stimulated an urgent demand for reliable...     

Multi-robot multiple hypothesis tracking for pedestrian tracking

In this paper the problem of tracking walking people with multiple moving robots is tackled. For this purpose we present an adaptation to the Multiple Hypothesis Tracking method, which unlike classic MHT, allows for one-to-many associations between targets and measurements in each hypothesis production cycle and is thus capable of operating in a scenario involving multiple sensors. Derivation of hypotheses probabilities accounts for the continuously changing overlapping areas in fields of view of the robots sensors and for detection uncertainty. In the context of three experiments involving people walking among moving robots, the successful integration of our tracking algorithm to a real-world setup is assessed.     

Game-based e-retailing in GOLEM agent environments

We present a prototype multi-agent system whose goal is to support a 3D application for e-retailing. The prototype demonstrates how the use of agent environments can be amongst the most promising and flexible approaches to engineer e-retailing applications. We illustrate this point by showing how the agent environment GOLEM supports social interactions and how it combines them with semantic-web technologies to develop the e-retailing application. We also describe the features of GOLEM that allow a user to engage in e-retailing activities in order to explore the virtual social environment by searching and dynamically discovering new agents, products and services.     

Correction to: Automatic stress analysis from facial videos based on deep facial action units recognition

Pattern Analysis and Applications - A correction to this paper has been published: 10.1007/s10044-021-01012-9     

Self-Organizing Maps for advanced learning in cognitive radio systems

Modern everyday life keeps making wireless communications more and more popular. The wireless communications landscape is highly varying and its success depends on the efficient provision of a physically limited natural source namely, radio spectrum. Cognitive radio systems (CRSs) have been proposed as a very promising technology for addressing this situation by facilitating more flexible and intelligent spectrum management. However, the processes of a CRS are often proved to be rather arduous and time consuming. Accordingly, a learning mechanism, capable of building knowledge to the system can speed up the whole cognition process. Framed within this statement, this paper introduces and evaluates a mechanism which is based on the well-known unsupervised learning technique, called Self-Organizing Maps (SOMs), and is used for assisting a CRS to predict the raw data rate that can be obtained, when it senses specific input data from its environment. Results show that the proposed method can provide predictions which are correct up to a percentage of 78.9% while exhibiting performance comparable to other supervised neural network-based learning schemes.     

Mine maintenance analysis through Markov chain schemes

ABSTRACT

This paper shows how Markov chain schemes can be used for analyzing equipment availability problems, forecasting the number of dozer engines replacements, studying hoist traffic pattern between various levels in an underground mine and modelling the occurence of good and defective idlers along a conveyor.     

The Stratosphere platform for big data analytics

We present Stratosphere, an open-source software stack for parallel data analysis. Stratosphere brings together a unique set of features that allow the expressive, easy, and efficient programming of analytical applications at very large scale. Stratosphere’s features include “in situ” data processing, a declarative query language, treatment of user-defined functions as first-class citizens, automatic program parallelization and optimization, support for iterative programs, and a scalable and efficient execution engine. Stratosphere covers a variety of “Big Data” use cases, such as data warehousing, information extraction and integration, data cleansing, graph analysis, and statistical analysis applications. In this paper, we present the overall system architecture design decisions, introduce Stratosphere through example queries, and then dive into the internal workings of the system’s components that relate to extensibility, programming model, optimization, and query execution. We experimentally compare Stratosphere against popular open-source alternatives, and we conclude with a research outlook for the next years.