76 research outputs found
Where did general motors go wrong with the ignition switch recall?
No full textWhen it comes to purchasing a new car, a buyer expects the car to be safe and reliable. It is the responsibility of the automaker to ensure that those expectations are met. However, to err is humanrecalls are a necessary part of life. When a recall happens, it then becomes the responsibility of the automaker to issue the recall in a timely manner. However, that was not the case with the General Motors (GM) ignition switch recall. The focus of this paper will be on the GM ignition switch, including sections regarding the problem with the switch, who may have been responsible for approving the switch, and possible suggestions on how GM could have prevented the recall
Von-data hybrid system architecture
No full textIn this paper a computing system has been proposed which involves both the principles and the approaches of data flow and Von-Neumann systems. The proposed model incorporates several new features like having a dedicated graphical processor, error correcting algorithms embedded in a systolic array and limiting the addressing mode to improve the execution speed. The proposed architecture can also function as a static and dynamic machine
AlHajj - Hajj app for iOS
No full textThis paper introduces the AlHajj app for iOS which is an interactive guide
to Hajj, like an interactive map allowing users to walk through the process of the Hajj to
develop a better understanding of the obligations, locations, dates and Hajj activities with
the sequence they are performed in. It covers both pre and post Hajj activities. AlHajj has
a very simplistic and clean User Interface (UI). The app is also written for maintainability
and it is free
Power DataMate Tool: Leveraging Logistic Regression Classification for Interactive Data Modeling
No full textThe demand for efficient predictive modeling techniques has become crucial due to the growing occurrence of binary classification problems in diverse fields. Therefore, it is desirable to utilize the logistic regression classification as a potent technique for data modeling, specifically with examining its efficacy in capturing and analyzing correlations across varied datasets, thus, Power DataMate software tool is developed. The promise of logistic regression in modeling complicated data structures is thoroughly examined due to its simplicity, interpretability, and adaptability to binary classification tasks. The choice of this research to focus on logistic regression for inquiry is based on its capability to represent intricate interactions between predictors and the binary response variable. However, the goal is to forecast the likelihood of discovering Primary Keys (PK) and Foreign Keys (FK) among datasets. While many off-the-shelf data analytics software and logistic regression classification research are available, it is found that there is a lack of research or solutions that provide a method where an entity data is analyzed using logistic regression to detect its PKs and features automatically or interactively.The research technique encompasses the acquisition of a combination of fictious and real-world six datasets. Four are in the form of data file while two are in the form of database. The data, then, is preprocessed to verify its quality, followed by the deployment of data training and prediction algorithms. On the other hand, sufficient training and testing datasets were incorporated to efficiently train and evaluate the model performance. Breaking new ground, we allow the users not only to automatically have their data modeled, but also to interactively review and confirm primary keys and features for further data analysis and modeling. While the research entails a comprehensive evaluation of model performance indicators, including accuracy and precision and recall, results show that the accuracy of PK detection is 89% and 82% for the FK. Hence, these results are the first of their kind and could be a starting point for further model enhancements and data analytics research, especially for analyzing data files projects where Power DataMate user has the choice to interactively feed the learning algorithm for better outcomes.Keywords: Data Mining, Data Modeling, Classification Problem, Logistic Regression, Primary Key, Foreign Key.Master of Science (MS)Software Engineering, College of Engineering & Computer ScienceUniversity of Michigan-Dearbornhttp://deepblue.lib.umich.edu/bitstream/2027.42/193121/1/Abu_Alrub_Thesis_Power_DataMate_Tool (1).pdffebc42ae-d444-43ae-98fd-dc98ee638897Description of Abu_Alrub_Thesis_Power_DataMate_Tool (1).pdf : Thesi
ALU and Dependency Manager Using FPGA
No full textIn this project, we have researched the design of high-speed processing units through
parallel processing scheme. Our design will be used for Real – Time applications such as Data Acquisition, DSP, Real – Time Controllers, etc. This project is introducing a new method to handle the parallel processing, this method will process instructions with respect to the dependencies among all instructions. Having a parallel processing capability allows this design to have extremely fast processing speed. In this project we will review every part of the system, and how it contributes to the performance of the
system. Currently FPGAs are used as specialty processing units of systems to boost up the throughput of those systems. Using FPGA to speed up special operations, such as database sorting [1, p. 53], data buffering, and many other function that require either high throughput processing, or low latency processing [2, p. 213], can increase the performance of the system. In addition, the normal design for a processing unit that can be part of a system is pipelining processing scheme. In this project, we present a new processing scheme capable of parallel processing, as well as dependency management, both built in the internal design of the unit. This design will eliminate the need for a dependency management software, which can take extra processing time or force the processor to have to process instruction sequentially. Instead, this design will allow parallel processing and dependency management built in a single integrated processing unit.Master of Science in Engineering (MSE)Computer Engineering, College of Engineering & Computer ScienceUniversity of Michigan-Dearbornhttp://deepblue.lib.umich.edu/bitstream/2027.42/155349/1/Amjad Hashem - Final Thesis.pdfDescription of Amjad Hashem - Final Thesis.pdf : Restricted to UM users only
Fuzzy Inference System for Simulating Ophthalmologists in the Diagnosis of Diabetic Retinopathy
No full textWith the rapid advancement of artificial intelligence (AI) technology, Computer-Assisted Diagnosis (CAD) has emerged as a prominent player in modern medical diagnostics, revolutionizing the way diseases are detected, diagnosed, and assessed. Despite the enthusiasm surrounding CAD, however, there is a noticeable gap in the research landscape - to be specific, a scarcity of thorough studies that rigorously compare its diagnostic capabilities and viewpoints with those of medical experts. This study aims to fill this void by subjecting the innovative fuzzy method, designed to replicate the methodologies of ophthalmologists in diagnosing diabetic retinopathy (DR), one of the leading causes of blindness. Using general case studies, a comprehensive review is conducted regarding the advantages and limitations inherent in each respective methodology. Through this process, the current problem of diagnosis is identified, and by using multiple diagnostic criteria for diabetic retinopathy, a diagnosis system based on a fuzzy inference system is created. Testing using FGADR and APTOS datasets acquired an accuracy of 77.59% and 98% respectively – overall achieving an accuracy of 87.04%. Although its value is lower in comparison to state-of-the-art performance (sensitivity of 91.9% and specificity of 91.3%), the advantages it could provide show promising alternatives that could be researched. While testing through datasets, edge case testing is conducted to check whether the proposed system correctly identifies misidentified data, validating the objectives of the research. This study will provide fresh insights into critically analyzing both the traditional diagnostic approach by human ophthalmologists and the innovative next-generation diagnostic technologies driven by AI, within their respective contexts. The availability of technology that mimics human doctors’ decision-making will ultimately facilitate the analysis of the current state of the technology.Master of Science (MS)Artificial Intelligence, College of Engineering and Computer ScienceUniversity of Michigan-Dearbornhttp://deepblue.lib.umich.edu/bitstream/2027.42/192154/1/JiHo_Han_Masters_Thesis_Final.pdf-1Description of JiHo_Han_Masters_Thesis_Final.pdf : Thesi
- …
