A flexible infrastructure for distributed deployment in adaptive sensor webs

Abstract. Global hydrological models (GHMs) are a useful tool in the assessment of the land surface water balance. They are used to further the understanding of interactions between water balance components as well as their past evolution and potential future development under various scenarios. While GHMs are a part of the Hydrologist's toolbox since several decades, the models are continuously developed. In our study, we present the HydroPy model, a revised version of an established GHM, the Max-Planck Institute for Meteorology's Hydrology Model (MPI-HM). Being rewritten in Python, the new model requires much less effort in maintenance and due to its flexible infrastructure, new processes can be easily implemented. Besides providing a thorough documentation of the processes currently implemented in HydroPy, we demonstrate the skill of the model in simulating the land surface water balance. We find that evapotranspiration is reproduced realistically for the majority of the land surface but is underestimated in the tropics. The simulated river discharge correlates well with observations. Biases are evident for the annual accumulated discharge, however they can – at least to some part – be attributed to discrepancies between the meteorological model forcing data and the observations. Finally, we show that HydroPy performs very similar to MPI-HM and, thus, conclude the successful transition from MPI-HM to HydroPy.

Download Full-text

Data Mining and Cloud Computing

JITA - Journal of Information Technology and Applications (Banja Luka) - APEIRON ◽

10.7251/jit1202075v ◽

2012 ◽

Vol 4 (2) ◽

Cited By ~ 2

Author(s):

Robert Vrbić

Keyword(s):

Data Mining ◽

Cloud Computing ◽

Big Data ◽

Data Warehouses ◽

Cloud Data ◽

Big Data Mining ◽

New Knowledge ◽

Flexible Infrastructure

Cloud computing provides a powerful, scalable and flexible infrastructure into which one can integrate, previously known, techniques and methods of Data Mining. The result of such integration should be strong and capacitive platform that will be able to deal with the increasing production of data, or that will create the conditions for the efficient mining of massive amounts of data from various data warehouses with the aim of creating (useful) information or the production of new knowledge. This paper discusses such technology - the technology of big data mining, known as Cloud Data Mining (CDM).

Download Full-text

BCEAD: A Blockchain-Empowered Ensemble Anomaly Detection for Wireless Sensor Network via Isolation Forest

Security and Communication Networks ◽

10.1155/2021/9430132 ◽

2021 ◽

Vol 2021 ◽

pp. 1-10

Author(s):

Xiong Yang ◽

Yuling Chen ◽

Xiaobin Qian ◽

Tao Li ◽

Xiao Lv

Keyword(s):

Anomaly Detection ◽

Block Structure ◽

Detection Algorithm ◽

Wireless Sensor ◽

Detection Systems ◽

Blockchain Technology ◽

The Internet Of Things ◽

Isolation Forest ◽

Distributed Deployment ◽

Internal Attacks

The distributed deployment of wireless sensor networks (WSNs) makes the network more convenient, but it also causes more hidden security hazards that are difficult to be solved. For example, the unprotected deployment of sensors makes distributed anomaly detection systems for WSNs more vulnerable to internal attacks, and the limited computing resources of WSNs hinder the construction of a trusted environment. In recent years, the widely observed blockchain technology has shown the potential to strengthen the security of the Internet of Things. Therefore, we propose a blockchain-based ensemble anomaly detection (BCEAD), which stores the model of a typical anomaly detection algorithm (isolated forest) in the blockchain for distributed anomaly detection in WSNs. By constructing a suitable block structure and consensus mechanism, the global model for detection can iteratively update to enhance detection performance. Moreover, the blockchain guarantees the trust environment of the network, making the detection algorithm resistant to internal attacks. Finally, compared with similar schemes, in terms of performance, cost, etc., the results prove that BCEAD performs better.

Download Full-text