Browsing by Subject "neural network"

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    A Novel Framework for Predictive Modeling and Optimization of Powder Bed Fusion Process
    (MDPI, 2021-10) Marrey, Mallikharjun; Malekipour, Ehsan; El-Mounayri, Hazim; Faierson, Eric J.; Agarwal, Mangilal; Mechanical and Energy Engineering, School of Engineering and Technology
    Powder bed fusion (PBF) process is a metal additive manufacturing process which can build parts with any complexity from a wide range of metallic materials. PBF process research has predominantly focused on the impact of only a few parameters on product properties due to the lack of a systematic approach for optimizing a large set of process parameters simultaneously. The pivotal challenges regarding this process require a quantitative approach for mapping the material properties and process parameters onto the ultimate quality; this will then enable the optimization of those parameters. In this study, we propose a two-phase framework for optimizing the process parameters and developing a predictive model for 316L stainless steel material. We also discuss the correlation between process parameters -- i.e., laser specifications -- and mechanical properties and how to achieve parts with high density (> 98%) as well as better ultimate mechanical properties. In this paper, we introduce and test an innovative approach for developing AM predictive models, with a relatively low error percentage of 10.236% that are used to optimize process parameters in accordance with user or manufacturer requirements. These models use support vector regression, random forest regression, and neural network techniques. It is shown that the intelligent selection of process parameters using these models can achieve an optimized density of up to 99.31% with uniform microstructure, which improves hardness, impact strength, and other mechanical properties.
  • Thumbnail Image
    Item
    BIoU: An Improved Bounding Box Regression for Object Detection
    (MDPI, 2022-09-28) Ravi, Niranjan; Naqvi, Sami; El-Sharkawy, Mohamed; Electrical and Computer Engineering, School of Engineering and Technology
    Object detection is a predominant challenge in computer vision and image processing to detect instances of objects of various classes within an image or video. Recently, a new domain of vehicular platforms, e-scooters, has been widely used across domestic and urban environments. The driving behavior of e-scooter users significantly differs from other vehicles on the road, and their interactions with pedestrians are also increasing. To ensure pedestrian safety and develop an efficient traffic monitoring system, a reliable object detection system for e-scooters is required. However, existing object detectors based on IoU loss functions suffer various drawbacks when dealing with densely packed objects or inaccurate predictions. To address this problem, a new loss function, balanced-IoU (BIoU), is proposed in this article. This loss function considers the parameterized distance between the centers and the minimum and maximum edges of the bounding boxes to address the localization problem. With the help of synthetic data, a simulation experiment was carried out to analyze the bounding box regression of various losses. Extensive experiments have been carried out on a two-stage object detector, MASK_RCNN, and single-stage object detectors such as YOLOv5n6, YOLOv5x on Microsoft Common Objects in Context, SKU110k, and our custom e-scooter dataset. The proposed loss function demonstrated an increment of 3.70% at 𝐴𝑃𝑆 on the COCO dataset, 6.20% at AP55 on SKU110k, and 9.03% at AP80 of the custom e-scooter dataset.
  • Thumbnail Image
    Item
    Neural‑Brane: Neural Bayesian Personalized Ranking for Attributed Network Embedding
    (Springer, 2019-06) Dave, Vachik S.; Zhang, Balchuan; Chen, Pin-Yu; Al Hasan, Mohammad; Computer and Information Science, School of Science
    Network embedding methodologies, which learn a distributed vector representation for each vertex in a network, have attracted considerable interest in recent years. Existing works have demonstrated that vertex representation learned through an embedding method provides superior performance in many real-world applications, such as node classification, link prediction, and community detection. However, most of the existing methods for network embedding only utilize topological information of a vertex, ignoring a rich set of nodal attributes (such as user profiles of an online social network, or textual contents of a citation network), which is abundant in all real-life networks. A joint network embedding that takes into account both attributional and relational information entails a complete network information and could further enrich the learned vector representations. In this work, we present Neural-Brane, a novel Neural Bayesian Personalized Ranking based Attributed Network Embedding. For a given network, Neural-Brane extracts latent feature representation of its vertices using a designed neural network model that unifies network topological information and nodal attributes. Besides, it utilizes Bayesian personalized ranking objective, which exploits the proximity ordering between a similar node pair and a dissimilar node pair. We evaluate the quality of vertex embedding produced by Neural-Brane by solving the node classification and clustering tasks on four real-world datasets. Experimental results demonstrate the superiority of our proposed method over the state-of-the-art existing methods.
  • Thumbnail Image
    Item
    Solving Prediction Problems from Temporal Event Data on Networks
    (2021-08) Sha, Hao; Mohler, George; Hasan, Mohammad; Dundar, Murat; Mukhopadhyay, Snehasis
    Many complex processes can be viewed as sequential events on a network. In this thesis, we study the interplay between a network and the event sequences on it. We first focus on predicting events on a known network. Examples of such include: modeling retweet cascades, forecasting earthquakes, and tracing the source of a pandemic. In specific, given the network structure, we solve two types of problems - (1) forecasting future events based on the historical events, and (2) identifying the initial event(s) based on some later observations of the dynamics. The inverse problem of inferring the unknown network topology or links, based on the events, is also of great important. Examples along this line include: constructing influence networks among Twitter users from their tweets, soliciting new members to join an event based on their participation history, and recommending positions for job seekers according to their work experience. Following this direction, we study two types of problems - (1) recovering influence networks, and (2) predicting links between a node and a group of nodes, from event sequences.
  • Thumbnail Image
    Item
    The Discursive and Practical Influence of Spirituality on Civic Engagement
    (Wiley, 2022-06) Steensland, Brian; King, David P.; Duffy, Barbara J.; Sociology, School of Liberal Arts
    Religion has long been recognized as promoting civic engagement. Recent declines in organized religion and growing interest in spirituality raise the question of whether spirituality might also promote civic engagement. Using data from a new nationally representative survey, we assess the independent and joint influence of spirituality and religion on civic life. We find that 40% of respondents perceive spirituality as influencing their civic engagement. Spirituality's influence typically appears in tandem with religion, but when spirituality and religion are distinct, the influence of spirituality is greater and more prevalent. Using two distinct measures, we assess the influence of spirituality on civic engagementat both discursive and practical levels. We find positive associations for both. Spirituality is both a conscious influence and tacit resource in civic life. We close by briefly outlining an agenda for better understanding socially engaged spirituality.