Indiana University-Purdue University Indianapolis (IUPUI) / The identification of the vocation of an unknown heavy-duty vehicle is valuable to parts manufacturers who may not have otherwise access to this information on a consistent basis. This study proposes a methodology for vocation identification that is based on clustering techniques. Two clustering algorithms are considered: K-Means and Expectation Maximization. These algorithms are used to first construct the operating profile of each vocation from a set of vehicles with known vocations. The vocation of an unknown vehicle is then determined using different assignment methods. These methods fall under two main categories: one-versus-all and one-versus-one. The one-versus-all approach compares an unknown vehicle to all potential vocations. The one-versus-one approach compares the unknown vehicle to two vocations at a time in a tournament fashion. Two types of tournaments are investigated: round-robin and bracket. The accuracy and efficiency of each of the methods is evaluated using the NREL FleetDNA dataset. The study revealed that some of the vocations may have unique operating profiles and are therefore easily distinguishable from others. Other vocations, however, can have confounding profiles. This indicates that different vocations may benefit from profiles with varying number of clusters. Determining the optimal number of clusters for each vocation can not only improve the assignment accuracy, but also enhance the computational efficiency of the application. The optimal number of clusters for each vocation is determined using both static and dynamic techniques. Static approaches refer to methods that are completed prior to training and may require multiple iterations. Dynamic techniques involve clusters being split or removed during training. The results show that the accuracy of dynamic techniques is comparable to that of static approaches while benefiting from a reduced computational time.

京都大学 / 0048 / 新制・課程博士 / 博士(医学) / 甲第18874号 / 医博第3985号 / 新制||医||1008(附属図書館) / 31825 / 京都大学大学院医学研究科医学専攻 / (主査)教授 渡邉 大, 教授 山田 亮, 教授 福山 秀直 / 学位規則第4条第1項該当 / Doctor of Medical Science / Kyoto University / DFAM

No description available.

Perception of depth, ego-motion and robust keypoints is critical for SLAM andstructure from motion applications. Neural networks have achieved great perfor-mance in perception tasks in recent years. But collecting labeled data for super-vised training is labor intensive and costly. This thesis explores recent methodsin unsupervised training of neural networks that can predict depth, ego-motion,keypoints and do geometric consensus maximization. The benefit of unsuper-vised training is that the networks can learn from raw data collected from thecamera sensor, instead of labeled data. The thesis focuses on training on imagesfrom a monocular camera, where no stereo or LIDAR data is available. The exper-iments compare different techniques for depth and ego-motion prediction fromprevious research, and shows how the techniques can be combined successfully.A keypoint prediction network is evaluated and its performance is comparedwith the ORB detector provided by OpenCV. A geometric consensus network isalso implemented and its performance is compared with the RANSAC algorithmin OpenCV. The consensus maximization network is trained on the output of thekeypoint prediction network. For future work it is suggested that all networkscould be combined and trained jointly to reach a better overall performance. Theresults show (1) which techniques in unsupervised depth prediction are most ef-fective, (2) that the keypoint predicting network outperformed the ORB detector,and (3) that the consensus maximization network was able to classify outlierswith comparable performance to the RANSAC algorithm of OpenCV.

Mass spectrometry is an analytical technique commonly used for determining elemental composition in a substance sample. For this purpose, the sample is placed into some liquid solution called liquid matrix. Unfortunately, the spectrum of the sample is not observable separate from that of the solution. Thus, it is desired to distinguish the sample spectrum. The analysis is usually based on the comparison of the mixed spectrum with the one of the sole solution. Introducing the missing information about the origin of observed spectrum peaks, the author obtains a classic set up for the Expectation-Maximization (EM) algorithm. The author proposed a mixture modeling the spectrum of the liquid solution as well as that of the sample. A bell-shaped probability mass function obtained by discretization of the univariate Gaussian probability density function was proposed or serving as a mixture component. The E- and M- steps were derived under the proposed model. The corresponding R program is written and tested on a small but challenging simulation example. Varying the number of mixture components for the liquid matrix and sample, the author found the correct model according to Bayesian Information Criterion. The initialization of the EM algorithm is a difficult standalone problem that was successfully resolved for this case. The author presents the findings and provides results from the simulation example as well as corresponding illustrations supporting the conclusions.

William Clarke (1976) and Nathan Greenberg (1980) offer an objective framework for the study of alliteration in Latin poetry. However, their definition of alliteration as word initial sound repetition in a verse is inconsistent with the syllabic nature both of the device itself and also of the metrical structure. The present study reconciles this disparity in the first half of the Aeneid by applying a similar method to syllable initial sound repetition. A chi-square test for goodness-of-fit reveals that the distributions of the voiceless obstruents [p], [t], [k], [k^w], [f], and [s] and the sonorants [m], [n], [l], and [r] differ significantly from a Poisson model. These sounds generally occur twice per verse more often than expected, and three or more times per verse less often than expected. This finding is largely consistent with existing observations about Vergil's style (e.g. Clarke, 1976; Greenberg, 1980; Wilkinson, 1963). The regular association of phonetic features with differences in distribution suggests phonetic motivation for the practice.

During this "white collar recession,'' there is a flooded labor market of workers. For employers seeking to hire, there is a need to identify potential qualified candidates for each job. The current state of the art is LinkedIn Recruiting or elastic search on Resumes. The current state of the art lacks efficiency and scalability along with an intuitive ranking of candidates. We believe this can be fixed with multi-layer categorical clustering via modularity maximization. To test this, we gathered a dataset that is extensive and representative of the job market. Our data comes from PeopleDataLabs and LinkedIn and is sampled from 153 million individuals. As such, this data represents one of the most informative datasets for the task of ranking and clustering job titles and skills. Properly grouping individuals will help identify more candidates to fulfill the multitude of vacant positions. We implement a novel framework for categorical clustering, involving these attributes to deliver a reliable pool of candidates. We develop a metric for clustering based on commonality to rank clustering algorithms. The metric prefers modularity-based clustering algorithms like the Louvain algorithm. This allows us to use such algorithms to outperform other unsupervised methods for categorical clustering. Our implementation accurately clusters emergency services, health-care and other fields while managerial positions are interestingly swamped by soft or uninformative features thereby resulting in dominant ambiguous clusters.

The success of Online Social Networks (OSN) is influenced by having the ability to understand who is important. An OSN can be viewed as a graph where users are vertices and their interactions are edges. Graph-based methods can enable identification of people in these networks who for example exhibit the characteristics of leaders, influencers, or information brokers. A Massively Multiplayer Online game (MMO) is a type of OSN. It is a video game where a large number of players interact with each other in a virtual world. Using behavioral data of players' interactions within the space-based MMO EVE Online, the aim of this thesis is to conduct an experimental study to evaluate the effectiveness of a number graph-based methods at finding important players within different behavioral contexts. For that purpose we extract behavioral data to construct four distinct graphs: Fleet, Aggression, Mail, and Market. We also create a ground truth data set of important players based on heuristics from key gameplay categories. We experiment on these graphs with a selection of graph centrality, Influence Maximization, and heuristic methods. We explore how they perform in terms of ground truth players found per graph and execution time, and when combining results from all graphs. Our results indicate that there is no optimal method across graphs but rather the method and graph should be chosen according to the business intention at each time. To that end we provide recommendations as well as potential business case usages. We believe that this study serves as a starting point towards more graph based analysis within the EVE Online virtual universe where there are many unexplored research opportunities. / Framgången hos Online Sociala Nätverk (OSN) påverkas av förmågan att förstå vem som är viktig. Ett OSN kan ses som en graf där användarna är noder och deras interaktioner ärbågar. Grafbaserade metoder kan möjliggöra identifiering av personer i dessa nätverk somtill exempel uppvisar egenskaper hos ledare, påverkare eller informationsförmedlare. Ett Massively Multiplayer Online game (MMO) representerar en typ av OSN. Det är ett datorrollspel där ett stort antal spelare interagerar med varandra i en virtuell värld. Genomatt använda beteendedata om spelarnas interaktioner i den rymdbaserade MMO:n EVE Online är målet med denna avhandling att genomföra en experimentell studie för att utvärdera effektiviteten hos ett antal grafbaserade metoder för att hitta viktiga spelare inom olika beteendemässiga sammanhang. För det ändamålet extraherar vi beteendedata för att konstruera fyra distinkta grafer: Fleet, Aggression, Mail och Market. Vi skapar också ett ground truth" dataset av viktiga spelare baserat på heuristik från viktiga spelkategorier. Vi utför experiment på dessa grafer med ett urval av grafcentralitet, Influence Maximization och heuristiska metoder. Vi undersöker hur metoderna presterar i termer av antal ground truth spelare som finns per graf och över grafer, och i termer av exekveringstid. Våra resultat tyder på att det inte finns någon optimal metod för alla grafer. Metoden och grafen bör väljas beroende på intentionen vid varje tillfälle. För detta ändamål tillhandahåller vi rekommendationer samt potentiella affärsmässiga användningsområden. Vi tror att denna studie tjänar som utgångspunkt för mer grafbaserad analys inom EVEOnlines virtuella universum där det finns många outforskade forskningsmöjligheter.

This dissertation addresses the problem of influence maximization in social networks. In- fluence maximization is applicable to many types of real-world problems, including modeling contagion, technology adoption, and viral marketing. Here we examine an advertisement domain in which the overarching goal is to find the influential nodes in a social network, based on the network structure and the interactions, as targets of advertisement. The assumption is that advertisement budget limits prevent us from sending the advertisement to everybody in the network. Therefore, a wise selection of the people can be beneficial in increasing the product adoption. To model these social systems, agent-based modeling, a powerful tool for the study of phenomena that are difficult to observe within the confines of the laboratory, is used. To analyze marketing scenarios, this dissertation proposes a new method for propagating information through a social system and demonstrates how it can be used to develop a product advertisement strategy in a simulated market. We consider the desire of agents toward purchasing an item as a random variable and solve the influence maximization problem in steady state using an optimization method to assign the advertisement of available products to appropriate messenger agents. Our market simulation 1) accounts for the effects of group membership on agent attitudes 2) has a network structure that is similar to realistic human systems 3) models inter-product preference correlations that can be learned from market data. The results on synthetic data show that this method is significantly better than network analysis methods based on centrality measures. The optimized influence maximization (OIM) described above, has some limitations. For instance, it relies on a global estimation of the interaction among agents in the network, rendering it incapable of handling large networks. Although OIM is capable of finding the influential nodes in the social network in an optimized way and targeting them for advertising, in large networks, performing the matrix operations required to find the optimized solution is intractable. To overcome this limitation, we then propose a hierarchical influence maximization (HIM) iii algorithm for scaling influence maximization to larger networks. In the hierarchical method the network is partitioned into multiple smaller networks that can be solved exactly with optimization techniques, assuming a generalized IC model, to identify a candidate set of seed nodes. The candidate nodes are used to create a distance-preserving abstract version of the network that maintains an aggregate influence model between partitions. The budget limitation for the advertising dictates the algorithm’s stopping point. On synthetic datasets, we show that our method comes close to the optimal node selection, at substantially lower runtime costs. We present results from applying the HIM algorithm to real-world datasets collected from social media sites with large numbers of users (Epinions, SlashDot, and WikiVote) and compare it with two benchmarks, PMIA and DegreeDiscount, to examine the scalability and performance. Our experimental results reveal that HIM scales to larger networks but is outperformed by degreebased algorithms in highly-connected networks. However, HIM performs well in modular networks where the communities are clearly separable with small number of cross-community edges. This finding suggests that for practical applications it is useful to account for network properties when selecting an influence maximization method.

Yes / In this paper, a stochastic approach for the operation of active distribution networks within a joint active and reactive distribution market environment is proposed. The method maximizes the social welfare using market based active and reactive optimal power flow (OPF) subject to network constraints with integration of demand response (DR). Scenario-Tree technique is employed to model the uncertainties associated with solar irradiance, wind speed and load demands. It further investigates the impact of solar and wind power penetration on the active and reactive distribution locational prices (D-LMPs) within the distribution market environment. A mixed-integer linear programming (MILP) is used to recast the proposed model, which is solvable using efficient off-the shelf branch-and cut solvers. The 16-bus UK generic distribution system is demonstrated in this work to evaluate the effectiveness of the proposed method. Results show that DR integration leads to increase in the social welfare and total dispatched active and reactive power and consequently decrease in active and reactive D-LMPs. / Ministry of Higher Education and Scientific Research of Iraq