Peter RaethSenior Research Engineer
Peter Raeth
Ph.D. Computer Science; MS Computer Engineering; BS Electrical Engineering; AS Electronics Engineering Technology
About
48
Publications
6,384
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
103
Citations
Citations since 2017
Introduction
Assist domain experts to transition theory to industrial application, evolving theory so it can be actualized for human benefit. Have worked in the areas of remote sensing, human factors, precision agriculture, anomaly detection in datastreams, integration of diverse systems, pattern recognition. Service as adjunct faculty at universities in America, Ethiopia, Zimbabwe, and Surinam. At UZ I mentor two doctoral candidates. Specialist in computational science and distributed systems.
Education
June 2003 - June 2008
Publications
Publications (48)
In Sub-Saharan Africa, where most irrigation systems are manually operated, water allocation and irrigation scheduling are often based on uniform application irrespective of crop needs and growth stages, which results in nonoptimal water use. Recently, a lot of research has been carried out to improve irrigation water use efficiency through automat...
Water stress continues to be a major factor that affects agricultural productivity in arid and semi-arid regions, which are characterized by high annual rainfall variability. Water-saving practices and sound water management strategies are urgently required to ensure the long-term viability of the agricultural industry in these regions. Automated i...
There is a growing interest in context-aware recommendation systems (CARS) due to their ability to enable novelty, dynamism and serendipity in resulting recommendations. The incorporation of different user-contextual parameters is important in CARS. However, the problem of identifying the most optimal subset of user-contextual parameters that add r...
Information filtering on the World Wide Web has grown widely since information overload has become a serious problem. Recommendation systems, the topic of this thesis, filter and apply the mass of available information to help users make personalised selections of products and services. However, algorithms of today lack dynamism, user-focus, and an...
This technical note speaks to a data-driven next-day precipitation predictor. The use of the term "precipitation" is important since it includes rain, hail, and snow. C5.0 is used to build and test the prediction model. The US National Oceanic and Atmospheric Administration, National Centers for Environmental Information is the source of historical...
This present work provides a proof-of-concept for an adaptive process that combines an embedded version of UN-FAO’s moisture-loss equations with weather data feeds. The aim is to create a human-supervised fully-automatic approach to irrigation based on estimated crop moisture needs. The author looks forward to collaboration with interested parties...
This paper "looks across the river" to explore computer engineering applied within agriculture, particularly precision irrigation. It begins with work by the United Nations Food and Agriculture Organization (FAO). They developed guidelines for estimating a crop's water requirements. These guidelines describe a set of equations (Penman-Monteith form...
There is a growing interest in context-aware recommendation systems (CARS) due to their ability to enable novelty, dynamism and serendipity in resulting recommendations. The incorporation of different user-contextual parameters is important in CARS. However, the problem of determining the most optimal subset of user-contextual parameters that add r...
Existing recommender algorithms lack dynamism, human focus, and serendipitous recommendations. The literature indicates that the context of a user influences user decisions, and when incorporated in recommender systems (RSs), novel and serendipitous recommendations can be realized. This article shows that social, cultural, psychological, and econom...
Commercial control of the world's published literature has grown to the point where costs are prohibitive for developing nations. This article describes a computer engineer's response to this problem. The result is a publicly-accessible meta-search engine that focuses on open-access sources. With one set of keywords, this engine searches many engin...
Information filtering for web service using machine learning has recently grown widely , since information overload has also becoming a serious problem on the World Wide Web. Recommender systems were designed to cater for this problem, but published recommender systems still fail to to cope with changes of user’s preferences. This paper summarizes...
Researchers have worked on-finding e-commerce recommender systems evaluation methods that contribute to an optimal solution. However, existing evaluations methods lack the assessment of user-centric factors such as buying decisions, user experience and user interactions resulting in less than optimum recommender systems. This paper investigates the...
Digital natives — the generation for whom the Internet has always existed — have embraced the medium as one of choice. They use social computing applications as a medium for many activities, including receiving and giving product advice (ratings, comments), meeting with and talking to friends (social networking, chat), organizing events (social net...
Traditionally, applications written in MATLAB are oriented to single-processor systems. However, by applying standard parallel processing techniques and Message Passing Interface (MPI) implementations, these applications can benefit from the advantages of parallel computing. bcMPI facilitates this approach by providing MATLAB wrappers for calls to...
Spectral Fingerprint Identification (SFI) attempts to incorporate feature finding, text matching, and data fusion techniques for fast whole cube material identification. In operation, the SFI algorithm translates spectral data into a feature space where fast text matching between all pixels in a data cube and a preprocessed SFI spectral library can...
Earlier, we reported on predictive anomaly detection (PAD) for nominating targets within data streams generated by persistent sensing and surveillance. This technique is purely temporal and does not directly depend on the physics attendant on the sensed environment. Since PAD adapts to evolving data streams, there are no determinacy assumptions. We...
Abstract Text: This paper describes a means of achieving fault-tolerance and architecture extensibility for parallel/distributed systems that support spectral analysis. These attributes are essential to critical 24/7/366 operations and they improve upon systems that only enhance throughput. They also address the single-point-of-failure issues atten...
This paper discusses a method for searching a database of known material signatures to find the closest match with an unknown signature. This database search method combines fuzzy logic and voting methods to achieve a high level of classification accuracy with the signatures and data cubes tested. This paper discusses the method in detail to includ...
This paper describes a means of achieving fault-tolerance and architecture extensibility for parallel/distributed systems that support spectral analysis. These attributes are essential to critical 24/7/366 operations and they improve upon systems that only enhance throughput. They also address the single-point-of-failure issues attendant upon archi...
This paper offers an approach to detecting unspecified anomalies
and events in unspecified data streams. The underlying technology is
spectrum independent and also does not depend on correlated pixels or
other data to achieve accurate event detection and extraction in highly
robust environments. The technical approach presented here uses a
network...
For pilots to accept active decision aids during complex flight scenarios, it is essential that the automation work in synergy with the aircrew. To accomplish this, the automation must go well beyond menu and macro selections, where the pilot explicitly tells the automation what to do and when to do it. It must also transcend “mother may I” approac...
Practical Application": That should be the goal of all theory and technology development. This review offers opinions written from that perspective. The review started with the question, "Can this book be used as a guide to implementing a new technology by someone with related knowledge?" Generally, the reader will find a very useful book with appl...
For pilots to accept active decision aids during complex flight scenarios, it is essential that the automation work is in synergy with aircrew. To accomplish this, the automation must go well beyond menu and macro selections, where the pilot must explicitly tell the automation what to do and when to do it. It must also transcend "mother may I" appr...
For pilots to accept active decision aids during complex flight
scenarios, it is essential that the automation work is in synergy with
the aircrew. To accomplish this, the automation must go beyond menu
selections, where the pilot explicitly tells the automation what to do
and when to do it. It must also transcend “mother may I”
approaches, where t...
The rapid technology development in the past two decades has made
today's combat a complicated task. A large amount of information can be
available in a mission from both on-board and off-board sources.
Effectively utilizing the information is necessary to achieve successful
and optimal results. Decision aids that operate in real-time are an
import...
Vehicle systems operations, from automobiles, to airliners, through craft for sea and space, are heavily dependent on automated uses of data generated by both on-board and off-board sources. Not only are vehicles affected, but so are diverse systems such as process, manufacturing, and power generation plants. Historically, the volume of data in eac...
This study concerns the survivability of an airship that is under
attack by a missile. The pilot may employ an appropriate manoeuvre or
countermeasure at the right moment to escape from the attack. Real-time
prediction of the missile trajectory will help prepare the pilot to take
action at the right moment to survive. The missiles considered have a...
Many types of operation are heavily dependent on automated use of data generated both on-board and off-board. Historically, the volume of data and the required response rates keep growing because of such factors as task and system complexity. This reality pushes human operators to their limits of cognition and memory, causing systems to be difficul...
Voting is one method available to knowledge-based systems for dealing with selection uncertainty. Evidence on the validity of one or more selections is collected. Each piece of evidence then casts a “vote” for the defended selection. In this way, evidence in favor of various alternatives is accumulated. The numeric value of each vote depends on the...
Experience has brought to light certain differences between what
the research community produces and what technology users need. These
differences may be caused by a divergence in the standards held by users
and practitioners. The divergence exists in four major areas: education,
means of implementation, communication with appropriate parties, and...
The purpose of this project is to investigate neural networks for specific applications in passive electronic warfare (EW) involving restoration of deinterleaved pulse trains to their original broadcast form. The project took a generic event-train approach and focused on event-train recognition. It was determined that back propagation neural networ...
A hypersurface stretch and hammer neural network has been developed that generalize data from processes that have one output variable and one or more input variables. This network achieves several desirable properties through a novel combination of standard methods. The methods incorporate principal components, linear least squares, Gaussian radial...
A possible means for evaluating the performance of neural networks from a global perspective in parameter-space is suggested. An organized experimental method that identifies network configuration and parameter value choices which are not sensitive to minor variations for a standard training metric is described. Convergence maps are n-dimensional p...
This project is investigating backpropagation neural networks for specific applications in passive electronic warfare involving restoration of deinterleaved event trains to their original broadcast form. This is different from traditional bit-error detection/correction which relies on a prior knowledge of what the original bit stream looked liked....
An approach to the use of raw data that greatly reduces the volume of data while increasing its value for analysis and decision-making is considered. Consistent application of an analyst's knowledge in an automated environment readily transforms raw data into information and the information into recommendations. The approach concentrates first on c...
As digital integrated circuits become more complex, Computer Aided Design (CAD) must support more hierarchical design methods. Top-down design is supported in logic simulators by the inclusion of functional models. The SAndia LOGic Simulator (SALOGS) has functional modelling capability but until now only as FORTRAN subroutines. The new Structural I...
While good gate level and register transfer level digital simulators exist, one can not easily integrate the two due to their inherent limitations. A given simulation can not be described partially in gate level and partially in a higher level. A solution is to create a functional level preprocessor and a library of functional device models linked...
The study investigated the feasibility of adapting the coefficient k introduced by Cohen (1960) and elaborated by Swaminathan, Hambleton, and Algina (1974) to an internal consistency estimate for criterion referenced tests in single test administrations. The authors proposed the use of k as an internal consistency estimate by logically dividing cri...
This paper reviews an approach to detecting unexpected events in data streams from staring continuous- dwell sources. The underlying technology is spectrum independent. It also does not depend on correlated pixels or other cooperative data to achieve accurate event detection and extraction in robust applications. The technical approach uses a netwo...
Questions
Questions (5)
With this question, I am asking for volunteer assistance with an open-source project, LoRaBinaryFloodMessaging within https://github.com/SoothingMist/Scalable-Point-to-Point-LoRa-Sensor-Network/tree/main. Allow me to explain.
Many applications, including precision irrigation, require remote sensing of data generated by various pieces of equipment. The project at hand uses LoRa point-to-point flood messaging to accomplish data transfer. The complexities and costs of LoRaWAN and third-party services are avoided.
The present project phase accommodates cameras and single-value sensors. At issue is that the GUI accommodates only one camera and one sensor. What is needed is an improvement to the GUI so that cameras and sensors are selectable. Was thinking that drop-down lists would do well. However, front-end work is not my specialty. What I have found so far on this topic confuses me.
The GUI is driven by a basestation written in Python. Matplotlib is used to create and continuously update the GUI's two plots. The camera plot is not a picture really, just the display of a numpy matrix that is updated as image segments arrive. How would I add drop-down lists to the GUI? An example of the present state of the GUI is shown in the attached jpg. More detail is in the project’s documentation. Glad for any comments, suggestions, or direct help. Many thanks for your input.
All you out there with Arduino microcontroller experience: Maybe you have some thoughts on the question at this link. I sure am stuck. Thanks Much.
