Engineering & Science Thesis Collectionhttp://hdl.handle.net/10429/3822024-03-28T19:25:23Z2024-03-28T19:25:23ZChagas Disease Vectors Identification using Data Mining and Deep Learning TechniquesGhasemi, Zeinabhttp://hdl.handle.net/10429/21462021-04-23T18:17:50Z2021-04-23T00:00:00ZChagas Disease Vectors Identification using Data Mining and Deep Learning Techniques
Ghasemi, Zeinab
Chagas Disease (CD) is a vector–borne infectious disease transmitted from animals
to humans and reversely. It is caused by the parasite Trypanosoma cruzi (abbv. as
T. cruzi). It is forcing an enormous social burden on public health and counts as one
of the most major threats to human health. Based on WHO statistical analysis in
2019, CD affects about 7 million people and is responsible for nearly 50,000 annual
mortalities around the world. Also an average of 80 million people are living in risky
areas for infection in different parts of the world.
The disease has two phases of acute and chronic. Diagnosing of CD can be
performed at both acute and chronic phases. It invloves analyzing clinical, epidemi ological, and laboratory data. Since controlling and treating CD is easier in the
early stages, detecting it in the acute phase plays an essential role in overcoming
and controlling it.
There are many clinical trials dedicated to this problem, but progress in compu tational research (automatic identification) has been limited. Therefore, this work
presents four automated CD vector identification approaches that classify several
different vectors of kissing bugs with acceptable accuracy rates. Classification of
different CD vectors is important because carriers of CD belong to different species
classes unevenly scattered in different parts of the world. Therefore, differentiating
all species of CD vectors plays an important role in designing a robust global system
for automatic identification.
Three of our proposed methods are composed of preprocessing, feature extraction,
feature selection, data balancing, and classification phases. The preprocessing steps
are background removal, gray–scaling, and down–sizing. The Principal component
analysis (PCA) algorithm is utilized for feature extraction. A correlation–based subset
selection is used for feature selection. The classes are balanced by oversampled the
minority classes. Finally, the employed classification techniques include Decision Tree
(DT), Random Forrest (RF), and Support Vector Machine (SVM). These three methods
are named “PCA+DT”,“PCA+RF”, and “PCA+SVM”. In the fourth approach, we
applied two deep convolutional neural networks (CNN) on our preprocessed datasetiii
and omitted the feature extraction and feature selection steps. Our two convolutional
neural networks VGG16 and 7–layer CNN are trained using the same oversampled
image dataset.
The average accuracy using 150–features dataset for Brazilian vectors is 100% for
PCA+DT and PCA+RF methods; 98.20% for PCA+SVM; 88.60% for VGG16; and
97.57% for 7–layer CNN. Brazilian vectors belong to 39 species of kissing bugs with
1620 images in the utilized dataset. The average accuracy using 150–features dataset
for Mexican vectors is 100% for PCA+DT and PCA+RF; 98.40% for PCA+SVM; 89.20%
for VGG16; and 96.48% for 7–layer CNN. Mexican vectors belong to 12 species of
kissing bugs with 410 images in the utilized dataset.
Our results are promising and outperform previously developed systems. Given
that we have a small dataset, the results of tree–based algorithms (DT and RF) are
better than SVM and convolutional neural networks (CNN). Upon availability of
larger datasets of kissing bugs, the results of SVM and CNN are most likely to
improve.
Department of Electrical and Computer Engineering and Computer Science Thesis
2021-04-23T00:00:00ZAir-Fuel Ratio DeterminationBeneteau, Ronald W.Skillas, Charles W.http://hdl.handle.net/10429/7502015-01-16T21:39:36Z2015-01-16T00:00:00ZAir-Fuel Ratio Determination
Beneteau, Ronald W.; Skillas, Charles W.
“In the beginning there was none and now there.”
Thus spoke an unknown sage centuries ago with regard to our existence in the realm of reality. While he specifically was speaking in reference to material things coming from nothing, he might also, have been looking at the development of the dynamometer laboratory at the University of Detroit. In its own small way, the evolution of this laboratory from a once fond dream of the department heads and members of the administration, to the marvelous example of inspired student ingenuity and workmanship that it is now, probably parallels any other endeavor which men have made in their ever ceaseless making of something, out of' nothing . In referring to nothing " l mean "no thing" with respect to equipment, money and skilled workmen, and not to the absence of existence of' anything tangible. To make a statement like that after having spent five years in a Jesuit institution invites either a longer stay so the venerable fathers could change the way of our thinking, or else, direct excommunication.
Ever since the day when the Mechanical Engineering department was given the "OK" to "go ahead and build your –dynamometer room," there has been an endless array of students who, not knowing anything in particular about dynamometers, have gone ahead under very able leadership to build one of the finest dynamometer laboratories in this part of the country . As has been stated many times by the man who has had the most to do with the lab since its present construction was started, Professor John J. Uicker: “Maybe we haven't as many chromed bolts and nuts and as much cop per tubing, but we can do practically what any of the others can do now, and in a few years we will be able to do anything that they can do." I think that these words have been the watchword of the men who have worked under Professor Uicker’s leadership and will be for those who follow in our footsteps.
It has been the practice of those who have been actively employed by the Mechanical Department, when deciding upon the topic of their senior thesis, to try and solve some of the problems relative to the construction of the laboratory, or in the building of the many pieces of equipment so vital to the functioning of a "working" lab. It is through this kind of thinking by the students who have gone before, those of us of the present and they who will be of the future, that this lab has prospered and this thesis of which we now write was made possible.
When in 1949, Gordon Millar, Albert LaRou, and William Walton submitted their thesis titled, "Utilization Of Air-Flow Measurement As An Aid To Internal Combustion Engine Development" and in 1950, when Henry Fedorchuk built his famous fuel-weighing system, the pattern or mold for our thesis was formed. Through combining both Millar’s and Fedorchuk's thesises into one compact unit and presenting a method, whereby the results of the individual elements could be correlated, a new thesis was born, as was a fine piece of usable equipment. It is this accomplishment that is the thesis of which we write.
When our thesis, which we call “Air-Fuel Ratio Measurement,” had its inception, it was originally planned to have two units, one to measure the air and another to measure the fuel. During its construction, however, it was decided that the two pieces of equipment would take too much room in the already crowded lab, and so the two units were joined in matrimony, as it were, to exist as one. In this respect, the authors owe a great deal of gratitude to two of the young engineers employed by the Department in the dynamometer lab, Mr. Arthur Hammond and Mr. Peter Pentescu, for their very helpful suggestions.
It is sincerely hoped that the development of what we hope to be a very valuable piece of equipment during this project, will materially aid future internal combustion engine work at the University of Detroit.
2015-01-16T00:00:00ZBio-Triz: The combination between Biomimicry and TrizHu, Mingminghttp://hdl.handle.net/10429/7472014-11-19T15:46:30Z2014-11-19T00:00:00ZBio-Triz: The combination between Biomimicry and Triz
Hu, Mingming
2014-11-19T00:00:00ZAn Engineering Design Named Visual Functional Mapping Which Based on Functional basis Applied on Biomimicry FieldJiao, Shijunhttp://hdl.handle.net/10429/7462014-11-19T15:24:11Z2014-11-19T00:00:00ZAn Engineering Design Named Visual Functional Mapping Which Based on Functional basis Applied on Biomimicry Field
Jiao, Shijun
As the development of the engineering field, the characteristic of the modern engineering is accepted by engineering designers. There are Globalization, efficiency and standardization. The translation problem as such as language, culture and expression has been found by engineering designers. This paper introduced a new engineering design tool named visual functional mapping to solve this problem. Based on the functional basis, the paper used symbols to create eight icon, which is branch, channel, connect, control magnitude, convert, provision, signal and support, to represent all kinds of function in engineering design field. According to the research of the icons, the paper expanded the icon to make them more understanding. The biomimicry is becoming a new engineering tendency. This new engineering tools will widely use in the biomimicry and the paper also give some examples to represent how to use visual functional mapping apply in biomimicry field.
2014-11-19T00:00:00Z