UMBC College of Engineering and Information Technology Dean's Office

Permanent URI for this collectionhttp://hdl.handle.net/11603/7919

Browse

Now showing 1 - 20 of 42

Creating Geospatial Trajectories from Human Trafficking Text Corpora
(2024-05-09) Karabatis, Saydeh N.; Janeja, Vandana
Human trafficking is a crime that affects the lives of millions of people across the globe. Traffickers exploit the victims through forced labor, involuntary sex, or organ harvesting. Migrant smuggling could also be seen as a form of human trafficking when the migrant fails to pay the smuggler and is forced into coerced activities. Several news agencies and anti-trafficking organizations have reported trafficking survivor stories that include the names of locations visited along the trafficking route. Identifying such routes can provide knowledge that is essential to preventing such heinous crimes. In this paper we propose a Narrative to Trajectory (N2T) information extraction system that analyzes reported narratives, extracts relevant information through the use of Natural Language Processing (NLP) techniques, and applies geospatial augmentation in order to automatically plot trajectories of human trafficking routes. We evaluate N2T on human trafficking text corpora and demonstrate that our approach of utilizing data preprocessing and augmenting database techniques with NLP libraries outperforms existing geolocation detection methods.
ALDAS: Audio-Linguistic Data Augmentation for Spoofed Audio Detection
(2024-10-21) Khanjani, Zahra; Mallinson, Christine; Foulds, James; Janeja, Vandana
Spoofed audio, i.e. audio that is manipulated or AI-generated deepfake audio, is difficult to detect when only using acoustic features. Some recent innovative work involving AI-spoofed audio detection models augmented with phonetic and phonological features of spoken English, manually annotated by experts, led to improved model performance. While this augmented model produced substantial improvements over traditional acoustic features based models, a scalability challenge motivates inquiry into auto labeling of features. In this paper we propose an AI framework, Audio-Linguistic Data Augmentation for Spoofed audio detection (ALDAS), for auto labeling linguistic features. ALDAS is trained on linguistic features selected and extracted by sociolinguistics experts; these auto labeled features are used to evaluate the quality of ALDAS predictions. Findings indicate that while the detection enhancement is not as substantial as when involving the pure ground truth linguistic features, there is improvement in performance while achieving auto labeling. Labels generated by ALDAS are also validated by the sociolinguistics experts.
Striving For More Efficient And Equitable Healthcare: Ian Stockwell Wins Major NIH Grant
(UMBC News, 2024-11-12) Meyers, Catherine
Let Students Take the Wheel: Introducing Post-Quantum Cryptography with Active Learning
(2024-10-17) Jamshidi, Ainaz; Kaur, Khushdeep; Gangopadhyay, Aryya; Zhang, Lei
Quantum computing presents a double-edged sword: while it has the potential to revolutionize fields such as artificial intelligence, optimization, healthcare, and so on, it simultaneously poses a threat to current cryptographic systems, such as public-key encryption. To address this threat, post-quantum cryptography (PQC) has been identified as the solution to secure existing software systems, promoting a national initiative to prepare the next generation with the necessary knowledge and skills. However, PQC is an emerging interdisciplinary topic, presenting significant challenges for educators and learners. This research proposes a novel active learning approach and assesses the best practices for teaching PQC to undergraduate and graduate students in the discipline of information systems. Our contributions are two-fold. First, we compare two instructional methods: 1) traditional faculty-led lectures and 2) student-led seminars, both integrated with active learning techniques such as hands-on coding exercises and Kahoot games. The effectiveness of these methods is evaluated through student assessments and surveys. Second, we have published our lecture video, slides, and findings so that other researchers and educators can reuse the courseware and materials to develop their own PQC learning modules. We employ statistical analysis (e.g., t-test and chi-square test) to compare the learning outcomes and students' feedback between the two learning methods in each course. Our findings suggest that student-led seminars significantly enhance learning outcomes, particularly for graduate students, where a notable improvement in comprehension and engagement is observed. Moving forward, we aim to scale these modules to diverse educational contexts and explore additional active learning and experiential learning strategies for teaching complex concepts of quantum information science.
Hearing the Voice of Software Practitioners on Technical Debt Monitoring: Understanding Monitoring Practices and the Practices' Avoidance Reasons
(Brazilian Computing Society, 2024-08-30) Freire, Sávio; Rios, Nicolli; Pérez, Boris; Castellanos, Camilo; Correal, Darío; Ramač, Robert; Mandić, Vladimir; Taušan, Nebojša; López, Gustavo; Pacheco, Alexia; Mendonça, Manoel; Falessi, Davide; Izurieta, Clemente; Seaman, Carolyn; Spínola, Rodrigo
Context. Technical debt (TD) monitoring allows software professionals to track the evolution of debt incurred in their projects. The technical literature has listed several practices used in the software industry to monitor indebtedness. However, there is limited evidence on the use and on the reasons to avoid using these practices. Aims. This work aims to investigate, from the point of view of software practitioners, the practices used for monitoring TD items, and the practice avoidance reasons (PARs) curbing the monitoring of TD items. Method. We analyze quantitatively and qualitatively a set of 653 answers collected with a family of industrial surveys distributed in six countries. Results. Practitioners are prone to monitor TD items, revealing 46 practices for monitoring the debt and 35 PARs for explaining TD non-monitoring. Both practices and PARs are strongly associated with planning and management issues. The study also shows the relationship found among practices, PARs and types of debt and presents a conceptual map that relates practices and PARs with their categories. Conclusion. The results of this study add to a practitioners’ capability to monitor TD items by revealing the monitoring practices, PARs and their relationship with different TD types.
Flood-ResNet50: Optimized Deep Learning Model for Efficient Flood Detection on Edge Device
(IEEE, 2024-03-19) Khan, Md Azim; Ahmed, Nadeem; Padela, Joyce; Raza, Muhammad Shehrose; Gangopadhyay, Aryya; Wang, Jianwu; Foulds, James; Busart, Carl; Erbacher, Robert F.
Floods are highly destructive natural disasters that result in significant economic losses and endanger human and wildlife lives. Efficiently monitoring Flooded areas through the utilization of deep learning models can contribute to mitigating these risks. This study focuses on the deployment of deep learning models specifically designed for classifying flooded and non-flooded in UAV images. In consideration of computational costs, we propose modified version of ResNet50 called Flood-ResNet50. By incorporating additional layers and leveraging transfer learning techniques, Flood-ResNet50 achieves comparable performance to larger models like VGG16/19, AlexNet, DenseNet161, EfficientNetB7, Swin(small), and vision transformer. Experimental results demonstrate that the proposed modification of ResNet50, incorporating additional layers, achieves a classification accuracy of 96.43%, F1 score of 86.36%, Recall of 81.11%, Precision of 92.41 %, model size 98MB and FLOPs 4.3 billions for the FloodNet dataset. When deployed on edge devices such as the Jetson Nano, our model demonstrates faster inference speed (820 ms), higher throughput (39.02 fps), and lower average power consumption (6.9 W) compared to larger ResNet101 and ResNet152 models.
TSSA: Two-Step Semi-Supervised Annotation for Radargrams on the Greenland Ice Sheet
(IEEE, 2023-10-20) Jebeli, Atefeh; Tama, Bayu Adhi; Janeja, Vandana; Holschuh, Nicholas; Jensen, Claire; Morlighem, Mathieu; MacGregor, Joseph A.; Fahnestock, Mark A.
Ice-penetrating radar surveys have been conducted across the Greenland Ice Sheet since the 1960s, producing radargrams that measure ice thickness and detect the ice sheet’s radiostratigraphy. However, these radargrams are relatively under-explored and not yet fully annotated, mapped, or interpreted glaciologically. We aim to move towards automatic radargram annotation using deep learning-based methods. To provide a training set for these methods, we develop a two-step semi-supervised annotation (TSSA) approach that uses an existing unsupervised layer annotation (ARESELP) method and a deep learning-based segmentation approach (U-Net) to detect surface, and bottom reflectors (representing the bedrock) layers in radargrams. Here we focus on two evaluations of our approach: 1. Surface and bottom annotations; and 2. Data augmentation and transfer learning techniques for improving the performance of deep learning methods. Our study is a foundation for improving the efficacy of AI-based methods for auto-annotation of radargrams, where the training set is generated seamlessly through unsupervised learning.
A Comprehensive View on TD Prevention Practices and Reasons for not Preventing It
(ACM, 2024-06-28) Freire, Sávio; Pacheco, Alexia; Rios, Nicolli; Pérez, Boris; Castellanos, Camilo; Correal, Darío; Rama?, Robert; Mandi?, Vladimir; Taušan, Nebojša; López, Gustavo; Mendonça, Manoel; Falessi, Davide; Izurieta, Clemente; Seaman, Carolyn; Spínola, Rodrigo
Context. Technical debt (TD) prevention allows software practitioners to apply practices to avoid potential TD items in their projects. Aims. To uncover and prioritize, from the point of view of software practitioners, the practices that could be used to avoid TD items, the relations between these practices and the causes of TD, and the practice avoidance reasons (PARs) that could explain the failure to prevent TD. Method. We analyze data collected from six replications of a global industrial family of surveys on TD, totaling 653 answers. We also conducted a follow up survey to understand the importance level of analyzed data. Results. Most practitioners indicated that TD could be prevented, revealing 89 prevention practices and 23 PARs for explaining the failure to prevent TD. The paper identifies statistically significant relationships between preventive practices and certain causes of TD. Further, it prioritizes the list of practices, PARs, and relationships regarding their level of importance for TD prevention based on the opinion of software practitioners. Conclusion. This work organizes TD prevention practices and PARs in a conceptual map and the relationships between practices and causes of TD in a Sankey diagram to help the visualization of the body of knowledge reported in this study.
Development of chemically crosslinked PEG-PAA hydrogels suitable for engineering of the vascularized outer retina
(ARVO, 2022-06-01) Pandala, Narendra; LaScola, Michael; Mulfaul, Kelly; Stone, Edwin M.; Mullins, Robert F.; Tucker, Budd A.; Lavik, Erin
To engineer a micorphysiologic system that more accurately recapitulates the vascularized outer retina suitable for evaluating AMD pathology and development of novel therapeutics. A hydrogel library based on poly (ethylene glycol) (PEG), poly-L-lysine (PLL) and poly(allylamine) (PAA) was generated using succinimide and free amine reaction chemistry. Cellular compatibility was evaluated using a rat endothelial cell line and human iPSC-derived choroidal endothelial cells generated via directed differentiation and CD31 magnetic bead immunopanning. Cell health and identity was evaluated using a series of live dead assays and immunofluorescence staining. A library of 12 synthetic, chemically crosslinked, hydrogels with tunable mechanical and degradation properties were developed. Hydrogels with a lower amine content were found to have superior endothelial cell compatibility. We hypothesize that this is due to the cell surface disrobing characteristics of the polycations presents in the gels. Hydrogels with a higher polycation concentration showed relatively poor endothelial cell compatibility. Gels with optimal compatibility were found to promote endothelial cell spreading, migration, and capillary network-like formation. In this study novel hydrogels with unique mechanical and degradation properties were generated via chemical crosslinking of PEG, PLL and PAA. Low amine hydrogels were found to be superior for promoting endothelial cell spreading, migration and vascular tube formation. To create in vitro models that more accurately recapitulate the choriocapillaris, optimized hydrogels will be used as a bioink for screen-based printing of rat and human vascular endothelial cells. This abstract was presented at the 2022 ARVO Annual Meeting, held in Denver, CO, May 1-4, 2022, and virtually.
Adopting Foundational Data Science Curriculum with Diverse Institutional Contexts
(ACM, 2024-03-07) Janeja, Vandana; Sanchez, Maria; Khoo, Yi Xuan; Von Vacano, Claudia; Chen, Lujie Karen
The prevalence of data across all disciplines and the large workforce demand from industry has led to the rise in interest of data science courses. Educators are increasingly recognizing the value of building communities of practice and adapting and translating courses and programs that have been shown to be successful and sharing lessons learned in increasing diversity in data science education. We describe and analyze our experiences translating a lower-division data science curriculum from one university, University of California, Berkeley, to another setting with very different student populations and institutional context, University of Maryland, Baltimore County (UMBC). We present our findings from student interviews across two semesters of the course offering at UMBC specifically focusing on the challenges and positive experiences that the students had in the UMBC course. We highlight lessons learned to reflect on the existing large scale program at UC Berkeley, its adaptation and opportunities for increasing diversity in new settings. Our findings emphasize the importance of adapting courses and programs to existing curricula, student populations, cyberinfrastructure, and faculty and staff resources. Smaller class sizes open up the possibility of more individualized assignments, tailored to the majors, career interests, and social change motivations of diverse students. While students across institutional contexts may need varying degrees of support, we found that often students from diverse backgrounds, if engaged deeply, show significant enthusiasm for data science and its applications.
Wearable sensors and infrared cameras: Introducing UMBC’s User Studies Lab
(UMBC News, 2020-02-05) Mastrola, Megan Hanks
Narrative to Trajectory (N2T+): Extracting Routes of Life or Death from Human Tra!icking Text Corpora
(2023-08-06) Karabatis, Saydeh N.; Janeja, Vandana
Climate change and political unrest in certain regions of the world are imposing extreme hardship on many communities and are forcing millions of vulnerable populations to abandon their homelands and seek refuge in safer lands. As international laws are not fully set to deal with the migration crisis, people are relying on networks of exploiting smugglers to escape the devastation in order to live in stability. During the smuggling journey, migrants can become victims of human trafficking if they fail to pay the smuggler and may be forced into coerced labor. Government agencies and anti- trafficking organizations try to identify the trafficking routes based on stories of survivors in order to gain knowledge and help prevent such crimes. In this paper, we propose a system called Narrative to Trajectory (N2T⁺), which extracts trajectories of trafficking routes. N2T⁺ uses Data Science and Natural Language Processing techniques to analyze trafficking narratives, automatically extract relevant location names, disambiguate possible name ambiguities, and plot the trafficking route on a map. In a comparative evaluation we show that the proposed multi-dimensional approach offers significantly higher geolocation detection than other state of the art techniques.
Audio deepfakes: A survey
(Frontiers, 2023-01-09) Khanjani, Zahra; Watson, Gabrielle; Janeja, Vandana
A deepfake is content or material that is synthetically generated or manipulated using artificial intelligence (AI) methods, to be passed off as real and can include audio, video, image, and text synthesis. The key difference between manual editing and deepfakes is that deepfakes are AI generated or AI manipulated and closely resemble authentic artifacts. In some cases, deepfakes can be fabricated using AI-generated content in its entirety. Deepfakes have started to have a major impact on society with more generation mechanisms emerging everyday. This article makes a contribution in understanding the landscape of deepfakes, and their detection and generation methods. We evaluate various categories of deepfakes especially in audio. The purpose of this survey is to provide readers with a deeper understanding of (1) different deepfake categories; (2) how they could be created and detected; (3) more specifically, how audio deepfakes are created and detected in more detail, which is the main focus of this paper. We found that generative adversarial networks (GANs), convolutional neural networks (CNNs), and deep neural networks (DNNs) are common ways of creating and detecting deepfakes. In our evaluation of over 150 methods, we found that the majority of the focus is on video deepfakes, and, in particular, the generation of video deepfakes. We found that for text deepfakes, there are more generation methods but very few robust methods for detection, including fake news detection, which has become a controversial area of research because of the potential heavy overlaps with human generation of fake content. Our study reveals a clear need to research audio deepfakes and particularly detection of audio deepfakes. This survey has been conducted with a different perspective, compared to existing survey papers that mostly focus on just video and image deepfakes. This survey mainly focuses on audio deepfakes that are overlooked in most of the existing surveys. This article's most important contribution is to critically analyze and provide a unique source of audio deepfake research, mostly ranging from 2016 to 2021. To the best of our knowledge, this is the first survey focusing on audio deepfakes generation and detection in English.
Multi-domain Anomalous Relationships in Heterogeneous Temporal Data
(2023-12-06) Ale, Tolulope; Janeja, Vandana
The Arctic region is crucial to global climate stability. However, recent years have witnessed periods of extreme snow and ice melt, with rising temperatures that double the global average. These are not isolated events. They are the result of intricate interconnections across distinct domains. The challenge, therefore, lies not in understanding these individual domains, such as temperature, and radiation, but in decoding the inter-domain relationships inducing these polar anomalies. To address this, our study presents a novel framework aimed at mining these inter-domain relationships to explain such anomalies and the relationship across time series features comprehensively. These features may be selected from the same or different domains. Such anomalous relationships across features could help detect interesting phenomena such as extreme snow melt, and cloud cover and help identify time periods of interest when such relationships are more prevalent. We extracted the anomalous intervals in each domain using the Poisson Distribution model of rSatScan, then leveraged the concept of Direct Overlap and Proximity of anomalies to identify the direct and time-delayed temporal association (delayed correlation) between anomalies across features. The concept helps us understand how events in one domain may be associated with events in another domain during specific time periods using association rule mining. We evaluated our approach using ERA5 reanalysis data, and validated the identified anomalies against ground truth and evaluated the strength of the generated association rules using metrics like confidence and lift. Notably, several of our identified rules were consistent with findings confirmed by domain experts.
UMBC’s Vandana Janeja aims to boost high-performance computing know-how to tackle environmental science challenges with a $1 million NSF grant
(UMBC News, 2023-10-30) Meyers, Catherine
Discovering Portable Options through Automated Mapping
Topin, Nicholay; Haltmeyer, Nicholas; Squire, Shawn; Winder, John; MacGlashan, James; desJardins, Marie
Goal for artificial agents: Learn the most efficient process for completing a task in a given domain o Corollary: Reuse and transfer learned knowledge o Previous work assumed that a mapping was provided or that all domains were identical o Our contributions:  Automatically map across domains with different objects and attributes  Leverage prior knowledge by identifying commonalities between source and target domains  Provide novel techniques for scoring mappings and abstracting domains o Our method outperforms Pickett and Barto's PolicyBlocks (2002) and MacGlashan's Transfer Options (2013)
Game Changers
(UMBC Magazine, 2021-12-08) Lamb, Kennedy
Nanocapsules with HIF-1-alpha Inhibitor for Treatment of Choroidal Neovascularization in a Rat Model
(ARVO, 2023-06) Han, Ian; Pandala, Narendra; Maisha, Nuzhat; Ale, Tolulope; Mullins, Robert; Lavik, Erin; Tucker, Budd A.
Purpose : Choroidal neovascularization (CNV) is a vision-threatening complication of many retinal diseases, including age-related macular degeneration. Currently, the mainstay of CNV treatment is intravitreal delivery of antibodies that bind VEGF. However, there remains a great need for alternative therapies with longer duration and better treatment effect. This study describes the development of nanocapsule-based formulations toward sustained drug delivery of acriflavine (anti-angiogenic agent that inhibits hypoxia inducible factor [HIF]-1-alpha) and assesses its impact on CNV formation in a rat model. Methods : Polyurethane nanocapsules were synthesized by an interfacial condensation polymerization reaction in a nanoemulsion. Acriflavine was mixed with isophorone diisocyanate in water and then applied in drop-wise fashion to the solution before lyophilization to form drug capsules. Wild type Brown Norway rats were treated with laser photocoagulation to induce CNV. Eyes were injected intravitreally on the same day with 10 ul of either acriflavine nanocapsules (5 ug total dose of acriflavine) or blank nanocapsules as controls. Animals were assessed at 14-days post-injection with fundus photography, fluorescein angiography, and OCT (Figure). Eyes were enucleated for immunohistochemical analysis. CNV formation was compared between eyes treated with acriflavine versus blank nanocapsules. Results : Synthesis of acriflavine nanocapsules was reliable (Z-average diameter 197+/-39 nm) with a drug loading efficiency of 41 ug acriflavine/mg of nanocapsules. Following intravitreal injection, both nanocapsule formulations were well-tolerated, without signs of clinical inflammation or retinal toxicity. Visible intravitreal aggregates of nanocapsules were seen at 14-days post-injection. Preliminary qualitative analysis demonstrated markedly decreased sizes of CNV in acriflavine nanocapsules relative to fellow eye controls treated with blank nanocapsules (Figure). Conclusions : Nanocapsule formulations with acriflavine can be reliably manufactured with consistent drug dosing. Acriflavine nanocapsules are well-tolerated after intravitreal injection in an in vivo rat model and shows promise for inhibiting CNV formation. Studies are ongoing to quantify the effect of CNV inhibition at different dosages as well as various time points to evaluate drug duration.
Unaffected ex vivo clotting cascade by experimental hemostatic nanoparticles when introduced in the presence of recombinant tissue plasminogen activator
(Wolters Kluwer Health, 2022-12-06) Beyer, Margaret; France, John; Nagaraja, Tavarekere N; Lavik, Erin; Knight, Robert A; Lewandowski, Christopher A; Miller, Joseph B
CONTEXT: Hemostatic nanoparticles (hNPs) have shown efficacy in decreasing intracerebral hemorrhage (ICH) in animal models and are suggested to be of use to counter tissue plasminogen activator (tPA)-induced acute ICH. AIMS: The objective of this study was to test the ability of an hNP preparation to alter the clotting properties of blood exposed to tPA ex vivo. MATERIALS AND METHODS: Fresh blood samples were obtained from normal male Sprague-Dawley rats (~300 g; n = 6) and prepared for coagulation assays by thromboelastography (TEG) methods. Samples were untreated, exposed to tPA, or exposed to tPA and then to hNP. TEG parameters included reaction time (R, time in minutes elapsed from test initiation to initial fibrin formation), coagulation time (K, time in minutes from R until initial clot formation), angle (α, a measure in degrees of the rate of clot formation), maximum amplitude (MA, the point when the clot reaches its MA in mm), lysis at 30 min after MA (LY30, %), and clot strength (G, dynes/cm²), an index of clot strength. STATISTICAL ANALYSIS USED: Kruskal–Wallis test was employed to compare TEG parameters measured for untreated control samples versus those exposed to tPA and to compare tPA-exposed samples to samples treated with tPA + hNPs. Significances were inferred at P ≤ 0.05. RESULTS: Compared to untreated samples, tPA-treated samples showed a trend toward decreased angle and G suggesting potentially clot formation rate and clot strength. The addition of hNP did not affect any of these or other measured indices. CONCLUSIONS: The data demonstrated no hemostatic effects when the hNP was used in the presence of tPA. The lack of change in any of the TEG parameters measured in the present study may indicate limitations of the hNPs to reverse the thrombolytic cascade initiated by tPA.
Biocompatible Nanocapsules for Self-Healing Dental Resins and Bone Cements
(ACS, 2022-08-31) Menikheim, Sydney; Leckron, Joshua; Duffy, Michael; Zupan, Marc; Mallory, Amber; Lien, Wen; Lavik, Erin
Bone cements and dental resins are methacrylatebased materials that have been in use for many years, but their failure rates are quite high with essentially all dental resins failing within 10 years and 25% of all prosthetic implants will undergo aseptic loosening. There are significant healthcare costs and impacts on quality of life of patients. Self-healing bone cements and resins could improve the lifespan of these systems, reduce costs, and improve patient outcomes, but they have been limited by efficacy and toxicity of the components. To address these issues, we developed a self-healing system based on a dual nanocapsule system. Two nanocapsules were synthesized, one containing an initiator and one encapsulating a monomer, both in polyurethane shells. The monomer used was triethylene glycol dimethacrylate. The initiator capsules synthesized contained benzoyl peroxide and butylated hydroxytoluene. Resins containing the nanocapsules were tested in tension until failure, and the fractured surfaces were placed together. 33% of the samples showed self-healing behaviors to the point where they could be reloaded and tested in tension. Furthermore, the capsules and their components showed good biocompatibility with Caco-2 cells, a human epithelial cell line suggesting that they would be well tolerated in vivo.

Browse

Recent Submissions