Physical Sciences and Mathematics Commons^™

Scalable Structural Index Construction For Json Analytics, Lin Jiang, Junqiao Qiu, Zhijia Zhao

Michigan Tech Publications

JavaScript Object Notation ( JSON) and its variants have gained great popularity in recent years. Unfortunately, the performance of their analytics is often dragged down by the expensive JSON parsing. To address this, recent work has shown that building bitwise indices on JSON data, called structural indices, can greatly accelerate querying. Despite its promise, the existing structural index construction does not scale well as records become larger and more complex, due to its (inherently) sequential construction process and the involvement of costly memory copies that grow as the nesting level increases. To address the above issues, this work introduces Pison …

Leveraging Very-High Spatial Resolution Hyperspectral And Thermal Uav Imageries For Characterizing Diurnal Indicators Of Grapevine Physiology, Matthew Maimaitiyiming, Vasit Sagan, Paheding Sidike, Maitiniyazi Maimaitijiang, Allison J. Miller, Misha Kwasniewski

Michigan Tech Publications

Efficient and accurate methods to monitor crop physiological responses help growers better understand crop physiology and improve crop productivity. In recent years, developments in unmanned aerial vehicles (UAV) and sensor technology have enabled image acquisition at very-high spectral, spatial, and temporal resolutions. However, potential applications and limitations of very-high-resolution (VHR) hyperspectral and thermal UAV imaging for characterization of plant diurnal physiology remain largely unknown, due to issues related to shadow and canopy heterogeneity. In this study, we propose a canopy zone-weighting (CZW) method to leverage the potential of VHR (≤9 cm) hyperspectral and thermal UAV imageries in estimating physiological indicators, …

Visual Feature Extraction From Dermoscopic Colour Images For Classification Of Melanocytic Skin Lesions, Walid Al-Zyoud, Athar Abu Helou, Eslam Alqasem, Nathir A. Rawashdeh

Michigan Tech Publications

The early diagnosis of Melanoma is a challenging task for dermatologists, because of the characteristic similarities of Melanoma with other skin lesions such as typical moles and dysplastic nevi. Aims: This work aims to help both experienced and non-experienced dermatologists in the early detection of cutaneous Melanoma through the development of a computational helping tool based on the “ABCD” rule of dermoscopy. Moreover, it aims to decrease the need for invasive biopsy procedure for each tested abnormal skin lesion. Methods: This is accomplished through the utilization of MATLAB programming language to build a feature extraction tool for the assessment of …

Text Indexing And Searching In Sublinear Time, J. Ian Munro, Gonzalo Navarro, Yakov Nekrich

Michigan Tech Publications

We introduce the first index that can be built in o(n) time for a text of length n, and can also be queried in o(q) time for a pattern of length q. On an alphabet of size, our index uses O(n log) bits, is built in O(n log f/plog n) deterministic time, and computes the number of occurrences of the pattern in time O(q/logf n+log n logf n). Each such occurrence can then be found in O(log n) time. Other trade-offs between the space usage and the cost of reporting occurrences are also possible. 2012 ACM Subject Classification Theory of …

Machine Learning For The Preliminary Diagnosis Of Dementia, Fubao Zhu, Xiaonan Li, Haipeng Tang, Zhuo He, Chaoyang Zhang, Guang-Uei Hung, Pai-Yi Chiu, Weihua Zhou

Michigan Tech Publications

Objective. The reliable diagnosis remains a challenging issue in the early stages of dementia. We aimed to develop and validate a new method based on machine learning to help the preliminary diagnosis of normal, mild cognitive impairment (MCI), very mild dementia (VMD), and dementia using an informant-based questionnaire. Methods. We enrolled 5,272 individuals who filled out a 37-item questionnaire. In order to select the most important features, three different techniques of feature selection were tested. Then, the top features combined with six classification algorithms were used to develop the diagnostic models. Results. Information Gain was the most …

Analyze Informant-Based Questionnaire For The Early Diagnosis Of Senile Dementia Using Deep Learning, Fubao Zhu, Xiaonan Li, Daniel Mcgonigle, Haipeng Tang, Zhuo He, Chaoyang Zhang, Guang-Uei Hung, Pai-Yi Chiu, Weihua Zhou

Michigan Tech Publications

OBJECTIVE: This paper proposes a multiclass deep learning method for the classification of dementia using an informant-based questionnaire.

METHODS: A deep neural network classification model based on Keras framework is proposed in this paper. To evaluate the advantages of our proposed method, we compared the performance of our model with industry-standard machine learning approaches. We enrolled 6,701 individuals, which were randomly divided into training data sets (6030 participants) and test data sets (671 participants). We evaluated each diagnostic model in the test set using accuracy, precision, recall, and F1-Score.

RESULTS: Compared with the seven conventional machine learning algorithms, the DNN …

The Stained Glass Of Knowledge: On Understanding Novice Mental Models Of Computing, Briana Christina Bettin

Dissertations, Master's Theses and Master's Reports

Learning to program can be a novel experience. The rigidity of programming can be at odds with beginning programmer's existing perceptions, and the concepts can feel entirely unfamiliar. These observations motivated this research, which explores two major questions: What factors influence how novices learn programming? and How can analogy by more appropriately leveraged in programming education?

This dissertation investigates the factors influencing novice programming through multiple methods. The CS1 classroom is observed as a "whole system", with consideration to the factors present in it that can influence the learning process. Learning's cognitive processes are elaborated to ground exploration into specifically …

Fast Preprocessing For Optimal Orthogonal Range Reporting And Range Successor With Applications To Text Indexing, Younan Gao, Meng He, Yakov Nekrich

Michigan Tech Publications

Under the word RAM model, we design three data structures that can be constructed in O(n√lg n) time over n points in an n×n grid. The first data structure is an O(n lg n)-word structure supporting orthogonal range reporting in O(lg lg n + k) time, where k denotes output size and is an arbitrarily small constant. The second is an O(n lg lg n)-word structure supporting orthogonal range successor in O(lg lg n) time, while the third is an O(n lg n)-word structure supporting sorted range reporting in O(lg lg n + k) time. The query times of these …

Matlabta: A Style Critiquer For Novice Engineering Students, Marissa L. Walther

Dissertations, Master's Theses and Master's Reports

Novice programmers, considered to be those who have yet to understand the fundamentals of programming, exist in both engineering and computing fields. Within computing, various resources exist to help novice programmers understand fundamentals and style guidelines such as WebTA, a code critique program that gives Java students feedback about their error and style issues. There is, however, a gap in automated code critique for MATLAB, a programming language that is popular in the engineering community. When it comes to MATLAB, there are not many programs that help novices understand their errors, and even fewer that help them understand style guidelines. …

Demand-Driven Execution Using Future Gated Single Assignment Form, Omkar Javeri

Dissertations, Master's Theses and Master's Reports

This dissertation discusses a novel, previously unexplored execution model called Demand-Driven Execution (DDE), which executes programs starting from the outputs of the program, progressing towards the inputs of the program. This approach is significantly different from prior demand-driven reduction machines as it can execute a program written in an imperative language using the demand-driven paradigm while extracting both instruction and data level parallelism. The execution model relies on an executable Single Assignment Form which serves both as the internal representation of the compiler as well as the Instruction Set Architecture (ISA) of the machine. This work develops the instruction set …

Critiquing Antipatterns In Novice Code, Leo C. Ureel Ii

Dissertations, Master's Theses and Master's Reports

Students in introductory computer science courses, are learning to program. Indeed, most students perceive that learning to code is the central topic explored in the courses. Students spend an enormous amount of time struggling to learn the syntax and understand semantics of a particular language. Instructors spend a similar amount of time reading student code and explaining the meaning of the cryptic error messages displayed by compilers. Messages provided by compilers are intended to give feedback on the adherence of one’s code to the language specification and conventions. Unfortunately, these message are geared towards experts who have a clear understanding …

Distance Oracles For Interval Graphs Via Breadth-First Rank/Select In Succinct Trees, Meng He, J. Ian Munro, Yakov Nekrich, Sebastian Wild, Kaiyu Wu

Michigan Tech Publications

We present the first succinct distance oracles for (unweighted) interval graphs and related classes of graphs, using a novel succinct data structure for ordinal trees that supports the mapping between preorder (i.e., depth-first) ranks and level-order (breadth-first) ranks of nodes in constant time. Our distance oracles for interval graphs also support navigation queries – testing adjacency, computing node degrees, neighborhoods, and shortest paths – all in optimal time. Our technique also yields optimal distance oracles for proper interval graphs (unit-interval graphs) and circular-arc graphs. Our tree data structure supports all operations provided by different approaches in previous work, as well …