Data Mining Practical Machine Learning Tools and Techniques

Review: A systematic review on clustering and routing techniques based upon LEACH protocol for wireless sensor networks

LNBIP reports state-of-the-art results in areas related to business information systems and industrial application software development – timely, at a high level, and in both printed and electronic form.  The type of material published includes  • Proceedings (published in time for the respective event) • Postproceedings (consisting of thoroughly revised and/or extended final papers) • Other edited monographs (such as, for example, project reports or invited volumes) • Tutorials (coherently integrated collections of lectures given at advanced courses, seminars, schools, etc.) • Award-winning or exceptional theses LNBIP is abstracted/indexed in DBLP, EI and Scopus. LNBIP volumes are also submitted for the inclusion in ISI Proceedings.

Lecture notes in business information processing

Eutrophication, harmful algae and biodiversity - Challenging paradigms in a world of complex nutrient changes.

[1] Poised at the interface of rivers, ocean, atmosphere and dense human settlement, estuaries are driven by a large array of natural and anthropogenic forces San Francisco Bay exemplifies the fast-paced change occurring in many of the world's estuaries, bays, and inland seas in response to these diverse forces We use observations from this particularly well-studied estuary to illustrate responses to six drivers that are common agents of change where land and sea meet: water consumption and diversion, human modification of sediment supply, introduction of nonnative species, sewage input, environmental policy, and climate shifts In San Francisco Bay, responses to these drivers include, respectively, shifts in the timing and extent of freshwater inflow and salinity intrusion, decreasing turbidity, restructuring of plankton communities, nutrient enrichment, elimination of hypoxia and reduced metal contamination of biota, and food web changes that decrease resistance of the estuary to nutrient pollution Detection of these changes and discovery of their causes through environmental monitoring have been essential for establishing and measuring outcomes of environmental policies that aim to maintain high water quality and sustain services provided by estuarine-coastal ecosystems The many time scales of variability and the multiplicity of interacting drivers place heavy demands on estuarine monitoring programs, but the San Francisco Bay case study illustrates why the imperative for monitoring has never been greater

https://agupubs.onlinelibrary.wiley.com/doi/pdf/10.1029/2012RG000397

Drivers of change in estuarine-coastal ecosystems: Discoveries from four decades of study in San Francisco Bay

A eutrophication assessment method was developed as part of the National Estuarine Eutrophication Assessment (NEEA) Program. The program is designed to improve monitoring and assessment of eutrophication in the estuaries and coastal bays of the United States with the intent to guide management plans and develop analytical and research models and tools for managers. These tools will help guide and improve management success for estuaries and coastal resources. The assessment method, a Pressure-State-Response approach, uses a simple model to determine Pressure and statistical criteria for indicator variables (where applicable) to determine State. The Response determination is mostly heuristic, although research models are being developed to improve that component. The three components are determined individually and then combined into a single rating. Application to several systems in the European Union (E.U.), specifically in Portugal, shows that the method is transferable, and thus is useful for development of management measures in both the Unites States and E.U. This approach identifies and quantifies the key anthropogenic nutrient input sources to estuaries so that management measures can target inputs for maximum effect. Because nitrogen is often the limiting nutrient in estuarine systems, examples of source identification and quantification for nitrogen have been developed for 11 coastal watersheds on the U.S. east coast using the WATERSN model. In general, estuaries in the Northeastern United States receive most of their nitrogen from human sewage, followed by atmospheric deposition. This is in contrast to some watersheds in the Mid-Atlantic (Chesapeake Bay) and South Atlantic (Pamlico Sound), which receive most of their nitrogen from agricultural runoff. Source identification is important for implementing effective management measures that should be monitored for success using assessment methods, as described herein. For instance, these results suggest that Northeastern estuaries would likely benefit most from improved sewage treatment, where as the Mid and South Atlantic systems would benefit most from agricultural runoff reductions.

/pdf/assessment-of-eutrophication-in-estuaries-pressure-state-2eiirzg3wf.pdf

Assessment of Eutrophication in Estuaries: Pressure–State–Response and Nitrogen Source Apportionment

Our work proposes a hardware architecture for a Long Short-Term Memory (LSTM) Neural Network, aiming to outperform software implementations, by exploiting its inherent parallelism. The main design decisions are presented, along with the proposed network architecture. A description of the main building blocks of the network is also presented. The network is synthesized for various sizes and platforms, and the performance results are presented and analyzed. Our synthesized network achieves a 251 times speed-up over a custom-built software network, running on an i7–3770k Desktop computer, proving the benefits of parallel computation for this kind of network.

/pdf/an-fpga-implementation-of-a-long-short-term-memory-neural-xk43ajoaa4.pdf

An FPGA implementation of a long short-term memory neural network

Support for partial run-time reconfiguration of platform FPGAs

BST is a well established standard and testability framework for digital ICs and boards. The paper presents a test support IC controlled by an IEEE1149.1 interface, capable of providing access to analog nodes in mixed-signal boards. The proposed architecture (ABSINT - Analog to Boundary Scan Interface) is described and relevant implementation issues are discussed. A demonstrator IC implementing the ABSINT architecture is presented, and it is shown how it can be used to provide analog test channels under control of IEEE1149.1. >

Control and observation of analog nodes in mixed-signal boards

Sequential Minimal Optimization (SMO) is the traditional training algorithm for Support Vector Machines (SVMs). However, SMO does not scale well with the size of the training set. For that reason, Stochastic Gradient Descent (SGD) algorithms, which have better scalability, are a better option for massive data mining applications. Furthermore, even with the use of SGD, training times can become extremely large depending on the data set. For this reason, accelerators such as Field-programmable Gate Arrays (FPGAs) are used. This work describes an implementation in hardware, using FPGA, of a fully parallel SVM using Stochastic Gradient Descent. The proposed FPGA implementation of an SVM with SGD presents speedups of more than 10,000× relative to software implementations running on a quad-core processor and up to 319× compared to state-of-the-art FPGA implementations while requiring fewer hardware resources. The results show that the proposed architecture is a viable solution for highly demanding problems such as those present in big data analysis.

https://www.mdpi.com/2079-9292/8/6/631/pdf

João Canas Ferreira

Papers

Assessment of Eutrophication in Estuaries: Pressure–State–Response and Nitrogen Source Apportionment

An FPGA implementation of a long short-term memory neural network

Support for partial run-time reconfiguration of platform FPGAs

Control and observation of analog nodes in mixed-signal boards

Parallel Implementation on FPGA of Support Vector Machines Using Stochastic Gradient Descent