Browsing by Author "Computer Science, Luddy School of Informatics, Computing, and Engineering"

Now showing 1 - 10 of 25
  • Thumbnail Image
    Item
    A framework for graph-base neural network using numerical simulation of metal powder bed fusion for correlating process parameters and defect generation
    (Elsevier, 2022) Akter Jahan, Suchana; Al Hasan, Mohammad; El-Mounayri, Hazim; Computer Science, Luddy School of Informatics, Computing, and Engineering
    Powder bed fusion (PBF) is the most common technique used for metal additive manufacturing. This process involves consolidation of metal powder using a heat source such as laser or electron beam. During the formation of three-dimensional(3D) objects by sintering metal powders layer by layer, many different thermal phenomena occur that can create defects or anomalies on the final printed part. Similar to other additive manufacturing techniques, PBF has been in practice for decades, yet it is still going through research and development endeavors which is required to understand the physics behind this process. Defects and deformations highly impact the product quality and reliability of the overall manufacturing process; hence, it is essential that we understand the reason and mechanism of defect generation in PBF process and take appropriate measures to rectify them. In this paper, we have attempted to study the effect of processing parameters (scanning speed, laser power) on the generation of defects in PBF process using a graph-based artificial neural network that uses numerical simulation results as input or training data. Use of graph-based machine learning is novel in the area of manufacturing let alone additive manufacturing or powder bed fusion. The outcome of this study provides an opportunity to design a feedback controlled in-situ online monitoring system in powder bed fusion to reduce printing defects and optimize the manufacturing process.
  • Thumbnail Image
    Item
    A note on the multiplicative fairness score in the NIJ recidivism forecasting challenge
    (Springer Nature, 2021) Mohler, George; Porter, Michael D.; Computer Science, Luddy School of Informatics, Computing, and Engineering
    Background: The 2021 NIJ recidivism forecasting challenge asks participants to construct predictive models of recidivism while balancing false positive rates across groups of Black and white individuals through a multiplicative fairness score. We investigate the performance of several models for forecasting 1-year recidivism and optimizing the NIJ multiplicative fairness metric. Methods: We consider standard linear and logistic regression, a penalized regression that optimizes a convex surrogate loss (that we show has an analytical solution), two post-processing techniques, linear regression with re-balanced data, a black-box general purpose optimizer applied directly to the NIJ metric and a gradient boosting machine learning approach. Results: For the set of models investigated, we find that a simple heuristic of truncating scores at the decision threshold (thus predicting no recidivism across the data) yields as good or better NIJ fairness scores on held out data compared to other, more sophisticated approaches. We also find that when the cutoff is further away from the base rate of recidivism, as is the case in the competition where the base rate is 0.29 and the cutoff is 0.5, then simply optimizing the mean square error gives nearly optimal NIJ fairness metric solutions. Conclusions: The multiplicative metric in the 2021 NIJ recidivism forecasting competition encourages solutions that simply optimize MSE and/or use truncation, therefore yielding trivial solutions that forecast no one will recidivate.
  • Thumbnail Image
    Item
    Advancing Active Authentication for User Privacy and Revocability with BioCapsules
    (ACM, 2023-10) Sanchez, Edwin; Weyer, Anthony; Palackal, Joseph; Wang, Kai; Philips, Tyler; Zou, Xukai; Computer Science, Luddy School of Informatics, Computing, and Engineering
    Biometric Facial Authentication has become a pervasive mode of authentication in recent years. With this surge in popularity, concerns over the security and privacy of biometrics-based systems have grown. Therefore, there is a need for a system that can address security and privacy issues while remaining user-friendly and practical. The BioCapsule scheme is a flexible solution that can be embedded in existing biometrics systems in order to provide robust security and privacy protections. While BioCapsules have been evaluated for their static face authentication capabilities, this paper extends the scheme to Active Authentication, where a user is continuously authenticated throughout a session. We use the MOBIO dataset, which contains video recordings of 150 individuals using mobile devices over several sessions, in order to evaluate the BioCapsule scheme within the domain of Active Authentication. We find that the BioCapsule scheme not only performs comparably to baseline, unsecured system performance, but in some cases exceeds baseline performance in terms of False Acceptance Rate, False Rejection Rate, and Equal Error Rate. Through our experiments, we demonstrate that the BioCapsule scheme is a powerful and practical addition to existing biometrics-based Active Authentication systems to provide robust security and privacy protections.
  • Thumbnail Image
    Item
    Adversarial Attacks on Deep Temporal Point Process
    (IEEE, 2022) Khorshidi, Samira; Wang, Bao; Mohler, George; Computer Science, Luddy School of Informatics, Computing, and Engineering
    Temporal point processes have many applications, from crime forecasting to modeling earthquake aftershocks sequences. Due to the flexibility and expressiveness of deep learning, neural network-based approaches have recently shown promise for modeling point process intensities. However, there is a lack of research on the robustness of such models in regards to adversarial attacks and natural shocks to systems. Precisely, while neural point processes may outperform simpler parametric models on in-sample tests, how these models perform when encountering adversarial examples or sharp non-stationary trends remains unknown. Current work proposes several white-box and blackbox adversarial attacks against temporal point processes modeled by deep neural networks. Extensive experiments confirm that predictive performance and parametric modeling of neural point processes are vulnerable to adversarial attacks. Additionally, we evaluate the vulnerability and performance of these models in the presence of non-stationary abrupt changes, using the crimes dataset, during the Covid-19 pandemic, as an example.
  • Thumbnail Image
    Item
    An adaptive hybrid approach: Combining genetic algorithm and ant colony optimization for integrated process planning and scheduling
    (Emerald Insight, 2020) Uslu, Mehmet Fatih; Uslu, Süleyman; Bulut, Faruk; Computer Science, Luddy School of Informatics, Computing, and Engineering
    Optimization algorithms can differ in performance for a specific problem. Hybrid approaches, using this difference, might give a higher performance in many cases. This paper presents a hybrid approach of Genetic Algorithm (GA) and Ant Colony Optimization (ACO) specifically for the Integrated Process Planning and Scheduling (IPPS) problems. GA and ACO have given different performances in different cases of IPPS problems. In some cases, GA has outperformed, and so do ACO in other cases. This hybrid method can be constructed as (I) GA to improve ACO results or (II) ACO to improve GA results. Based on the performances of the algorithm pairs on the given problem scale. This proposed hybrid GA-ACO approach (hAG) runs both GA and ACO simultaneously, and the better performing one is selected as the primary algorithm in the hybrid approach. hAG also avoids convergence by resetting parameters which cause algorithms to converge local optimum points. Moreover, the algorithm can obtain more accurate solutions with avoidance strategy. The new hybrid optimization technique (hAG) merges a GA with a local search strategy based on the interior point method. The efficiency of hAG is demonstrated by solving a constrained multi-objective mathematical test-case. The benchmarking results of the experimental studies with AIS (Artificial Immune System), GA, and ACO indicate that the proposed model has outperformed other non-hybrid algorithms in different scenarios.
  • Thumbnail Image
    Item
    ASPER: Attention-based approach to extract syntactic patterns denoting semantic relations in sentential context
    (Elsevier, 2023-06) Kabir, Md. Ahsanul; Phillips, Tyler; Luo, Xiao; Al Hasan, Mohammad; Computer Science, Luddy School of Informatics, Computing, and Engineering
    Semantic relationships, such as hyponym–hypernym, cause–effect, meronym–holonym etc., between a pair of entities in a sentence are usually reflected through syntactic patterns. Automatic extraction of such patterns benefits several downstream tasks, including, entity extraction, ontology building, and question answering. Unfortunately, automatic extraction of such patterns has not yet received much attention from NLP and information retrieval researchers. In this work, we propose an attention-based supervised deep learning model, ASPER, which extracts syntactic patterns between entities exhibiting a given semantic relation in the sentential context. We validate the performance of ASPER on three distinct semantic relations—hyponym–hypernym, cause–effect, and meronym–holonym on six datasets. Experimental results show that for all these semantic relations, ASPER can automatically identify a collection of syntactic patterns reflecting the existence of such a relation between a pair of entities in a sentence. In comparison to the existing methodologies of syntactic pattern extraction, ASPER’s performance is substantially superior.
  • Thumbnail Image
    Item
    Case Study: Mapping an E-Voting Based Curriculum to CSEC2017
    (ACM, 2023-03) Zheng, Muwei; Swearingen, Nathan; Mills, Steven; Gyurek, Croix; Bishop, Matt; Zou, Xukai; Computer Science, Luddy School of Informatics, Computing, and Engineering
    An electronic voting (E-voting) oriented cybersecurity curriculum, proposed by Hostler et al. [4] in 2021, leverages the rich security features of E-voting systems and E-voting process to teach essential concepts of cybersecurity. Existing curricular guidelines describe topics in computer security, but do not instantiate them with examples. This is because their goals are different. In this case study, we map the e-voting curriculum into the CSEC2017 curriculum guidelines, to demonstrate how such a mapping is done. Further, this enables teachers to select the parts of the e-voting curriculum most relevant to their classes, by basing the selection on the relevant CSEC2017 learning objectives. We conclude with a brief discussion on generalizing this mapping to other curricular guidelines.
  • Thumbnail Image
    Item
    Classification of Alzheimer’s Disease Leveraging Multi-task Machine Learning Analysis of Speech and Eye-Movement Data
    (Frontiers Media, 2021-09-20) Jang, Hyeju; Soroski, Thomas; Rizzo, Matteo; Barral, Oswald; Harisinghani, Anuj; Newton-Mason, Sally; Granby, Saffrin; da Cunha Vasco, Thiago Monnerat Stutz; Lewis, Caitlin; Tutt, Pavan; Carenini, Giuseppe; Conati, Cristina; Field, Thalia S.; Computer Science, Luddy School of Informatics, Computing, and Engineering
    Alzheimer’s disease (AD) is a progressive neurodegenerative condition that results in impaired performance in multiple cognitive domains. Preclinical changes in eye movements and language can occur with the disease, and progress alongside worsening cognition. In this article, we present the results from a machine learning analysis of a novel multimodal dataset for AD classification. The cohort includes data from two novel tasks not previously assessed in classification models for AD (pupil fixation and description of a pleasant past experience), as well as two established tasks (picture description and paragraph reading). Our dataset includes language and eye movement data from 79 memory clinic patients with diagnoses of mild-moderate AD, mild cognitive impairment (MCI), or subjective memory complaints (SMC), and 83 older adult controls. The analysis of the individual novel tasks showed similar classification accuracy when compared to established tasks, demonstrating their discriminative ability for memory clinic patients. Fusing the multimodal data across tasks yielded the highest overall AUC of 0.83 ± 0.01, indicating that the data from novel tasks are complementary to established tasks.
  • Thumbnail Image
    Item
    Energy-Efficient and Robust QoS Control for Wireless Sensor Networks Using the Extended Gur Game
    (MDPI, 2025-01-25) Zhong, Xiaoyang; Liang, Yao; Li, Yimei; Computer Science, Luddy School of Informatics, Computing, and Engineering
    Outdoor wireless sensor networks (WSNs) operate autonomously in dynamic and unattended real-world environments, where sensor nodes are typically powered by their batteries. In hash outdoor settings, such as mountainous regions or underwater locations, recharging or replacing sensor node batteries is particularly challenging. For these WSN deployments, ensuring quality of service (QoS) control while conserving energy is crucial. This paper presents a novel QoS control algorithm for WSNs, built on extensions to the Gur game framework. The proposed approach not only enhances QoS performance compared to existing Gur game-based WSN control algorithms but also addresses their fundamental energy consumption challenges, enabling sustainable communication and extended network lifetimes. We evaluate the approach through comprehensive TinyOS-based WSN simulations and comparisons with existing algorithms. The results demonstrate that our approach, referred to as the robust Gur game, significantly enhances QoS control and achieves a 27.33% improvement in energy efficiency over the original Gur game and shuffle algorithms, showcasing the significant benefits of the proposed method.
  • Thumbnail Image
    Item
    Evaluating Web-Based Automatic Transcription for Alzheimer Speech Data: Transcript Comparison and Machine Learning Analysis
    (JMIR, 2022) Soroski, Thomas; Vasco, Thiago da Cunha; Newton-Mason, Sally; Granby, Saffrin; Lewis, Caitlin; Harisinghani, Anuj; Rizzo, Matteo; Conati, Cristina; Murray, Gabriel; Carenini, Giuseppe; Field, Thalia S.; Jang, Hyeju; Computer Science, Luddy School of Informatics, Computing, and Engineering
    Background: Speech data for medical research can be collected noninvasively and in large volumes. Speech analysis has shown promise in diagnosing neurodegenerative disease. To effectively leverage speech data, transcription is important, as there is valuable information contained in lexical content. Manual transcription, while highly accurate, limits the potential scalability and cost savings associated with language-based screening. Objective: To better understand the use of automatic transcription for classification of neurodegenerative disease, namely, Alzheimer disease (AD), mild cognitive impairment (MCI), or subjective memory complaints (SMC) versus healthy controls, we compared automatically generated transcripts against transcripts that went through manual correction. Methods: We recruited individuals from a memory clinic (“patients”) with a diagnosis of mild-to-moderate AD, (n=44, 30%), MCI (n=20, 13%), SMC (n=8, 5%), as well as healthy controls (n=77, 52%) living in the community. Participants were asked to describe a standardized picture, read a paragraph, and recall a pleasant life experience. We compared transcripts generated using Google speech-to-text software to manually verified transcripts by examining transcription confidence scores, transcription error rates, and machine learning classification accuracy. For the classification tasks, logistic regression, Gaussian naive Bayes, and random forests were used. Results: The transcription software showed higher confidence scores (P<.001) and lower error rates (P>.05) for speech from healthy controls compared with patients. Classification models using human-verified transcripts significantly (P<.001) outperformed automatically generated transcript models for both spontaneous speech tasks. This comparison showed no difference in the reading task. Manually adding pauses to transcripts had no impact on classification performance. However, manually correcting both spontaneous speech tasks led to significantly higher performances in the machine learning models. Conclusions: We found that automatically transcribed speech data could be used to distinguish patients with a diagnosis of AD, MCI, or SMC from controls. We recommend a human verification step to improve the performance of automatic transcripts, especially for spontaneous tasks. Moreover, human verification can focus on correcting errors and adding punctuation to transcripts. However, manual addition of pauses is not needed, which can simplify the human verification step to more efficiently process large volumes of speech data.