Engineering Commons^™

Towards Interpretable Propaganda Detection In News Text Through The Use Of Rhetorical Devices As Features, Kyle Hamilton

Doctoral

This doctoral thesis presents research undertaken towards interpretable propaganda detection in news text. Propaganda and mis/disinformation in the media have been identified in the social sciences literature as a major threat to the functioning of democratic society. While mis/disinformation is false by definition, propaganda is intended to modify the beliefs and behaviors of the information consumer but does not have to be false. Propagandistic text is often characterized by the use of rhetorical devices and linguistic style designed to exploit the reader’s cognitive and emotional biases. One way of counteracting this effect is by shifting the focus from “what” is …

V2i-Based Adaptive Collision Avoidance For Safety And Traffic Efficiency, Vaishnavi Balambeed

Dissertations, Master's Theses and Master's Reports

To leverage the growing communication and connectivity among modern vehicles, Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) systems are increasingly being used to implement active safety applications. However, current research often overlooks the impact of algorithms such as collision avoidance on traffic flow efficiency. This work investigates the adaptation of a collision avoidance algorithm implemented in V2I to incorporate a variable time headway and spacing control strategy. The proposed approach aims to maintain higher average speeds among vehicles, lower individual vehicle’s waiting, and travel times in the vicinity of the infrastructural unit while simultaneously avoiding collisions; thereby enhancing both safety and traffic …

Statically Controlled Synchronized Lane Architectures, Scott K. Pomerville

Dissertations, Master's Theses and Master's Reports

Modern superscalar processors dominate the field of computing. While dynamic execution allows for versatility in code, these processors are complex. Statically scheduled code has historically enabled simpler processor designs, but static scheduling cannot account for variables that are unknown at compile time. Furthermore, static scheduling has many inefficiencies, such as the need to insert a large number of nops for code in traditional Very Long Instruction Word (VLIW) processors. In this dissertation, we explore a novel architectural approach for statically scheduled code by breaking the code into several synchronous instruction streams. By representing code in a fundamentally new way, we …

Enhancing Privacy While Revealing Vulnerabilities: Strategies For Adaptation, Optimization, And Model Extraction, Madhureeta Das

Dissertations, Master's Theses and Master's Reports

In the evolving landscape of machine learning and artificial intelligence, this dissertation presents a series of innovative contributions spanning several critical areas: embracing semi-supervised domain adaptation for secure knowledge transfer, enhancing the model performance of tiny models, and executing model stealing attacks via diversified prompts. The overarching goal is to enhance the performance, scalability, and security of AI models across various applications.

The first research focus is on semi-supervised domain adaptation within federated learning frameworks. By leveraging semi-supervised learning techniques, this work addresses the challenge of adapting models trained on a source domain to perform effectively on a target domain …

Implementing Associative Learning Using Neuromorphic Robot, Vinay Kumar Pillalamarri

Dissertations, Master's Theses and Master's Reports

Associative learning, a key cognitive process seen across the animal kingdom, enables organisms to form connections between stimuli and adapt their behaviors based on past experiences. A particularly powerful example is fear conditioning, where animals learn to associate a neutral stimulus with an aversive one, allowing them to predict and avoid potential threats. Inspired by this mechanism, this project implements associative learning on an unmanned ground vehicle (UGV) to develop adaptive behavior through neuromorphic principles. Utilizing Nengo for neural modeling, the UGV learns to associate visual (red color) and tactile (vibration) stimuli through Hebbian learning, a biologically inspired synaptic adaptation …

An Fpga-Based Eit System For Deep Space Medical Imaging, Kendall R. Farnham

Dartmouth College Ph.D Dissertations

Dangers associated with high radiation and microgravity exposure in space are critical challenges inhibiting us from exploring deep space and pursuing long-duration missions, as current medical systems are unable to monitor, diagnose, or treat tissue injury within physical spacecraft constraints and communication limits. Ultrasound (US) is the current imaging system used on the International Space Station, but this technology relies on telemedical support (or onboard artificial intelligence/autonomous capabilities) for both operation and diagnosis, posing challenges for crews isolated in deep space. Electrical impedance tomography (EIT) is a non-invasive, non-ionizing technology that produces images of the electrical properties of tissues and …

Data Quality Based Intelligent Instrument Selection With Security Integration, Sergei Chuprov, Raman Zatsarenko, Leon Reznik, Igor Khokhlov

School of Computer Science & Engineering Faculty Publications

We propose a novel Data Quality with Security (DQS) integrated instrumentation selection approach that facilitates aggregation of multi-modal data from heterogeneous sources. As our major contribution, we develop a framework that incorporates multiple levels of integration in finding the best DQS-based instrument selection: data fusion from multi-modal sensors embedded into heterogeneous platforms, using multiple quality and security metrics and knowledge integration. Our design addresses the security aspect in the instrumentation design, which is commonly overlooked in real applications, by aggregating it with other metrics into an integral DQS calculus. We develop DQS calculus that formalizes the problem of finding the …

Mobile Robot Adhesion Methodology And Development Of An Automatous Robot Module, Lauren Baird, Zachariah Stone, Madison Lemons, Jonathon Moody

Williams Honors College, Honors Research Projects

Due to the increasing availability of space travel as not only a scientific exploration but a commercial exploration, there is a need for an onsite repair station that can be deployed in the event of aircraft maintenance, damage, or failure. We have been tasked with researching and creating a prototype of an automatous robot that can be attached to a spacecraft body, move along the surface while avoiding obstacles, scan for damage, 3D print a repair piece, and then make the repair, all without the need of direct human input. Our team, as will be discussed throughout, was tasked with …

College Of Computing And Engineering Graduate Catalog 2024-2025, Nova Southeastern University

College of Psychological Services / College of Psychology Postgraduate Student and Course Catalogs

No abstract provided.

How Can A Cloud Computing It Framework Be Created And Applied Effectively In The Online Printing Industry?, Stefan Meissner

Dissertations

This research aims to design a cloud computing IT framework for the online printing industry based on a detailed literature review, the development of proof of concepts (PoC), and the conduction of a focus group. The framework can be adopted by the online printing industry or by vendors of print-specific applications to optimize their products for the online printing industry. The author has been working in the online printing process optimization and automation since 2007. During this time, he got deep insight into many industry-specific applications, their architectural design, and their challenges being used in the context of online printing. …

On The Performance Of A Photonic Reconfigurable Electromagnetic Band Gap Antenna Array For 5g Applications, Taha A. Elwi, Fatma Taher, Bal S. Virdee, Mohammad Alibakhshikenari, Ignacio J.Garcia Zuazola, Astrit Krasniqi, Amna Shibib Kamel, Nurhan Turker Tokan, Salahuddin Khan, Naser Ojaroudi Parchin, Patrizia Livreri, Iyad Dayoub, Giovanni Pau, Sonia Aissa, Ernesto Limiti, Mohamed Fathy Abo Sree

All Works

In this paper, a reconfigurable Multiple-Input Multiple-Output (MIMO) antenna array is presented for 5G portable devices. The proposed array consists of four radiating elements and an Electromagnetic Band Gap (EBG) structure. Planar monopole radiating elements are employed in the array with Coplanar Waveguide Ports (CWPs). Each CWP is grounded on one side to a reflecting L-shaped structure that has an effect of improving the antenna's directivity. It is shown that by inductively connecting Minkowski fractal structure of 1^{st} order to the radiating element, the impedance matching is improved that results in enhancement in the array's bandwidth performance. The EBG structure …

Investigation And Implementation Of Miniaturized Microwave System For Linear Array Antenna Loaded With Omega Structures Planar Array, Ahmed F. Miligy, Fatma Taher, Mohamed Fathy Abo Sree, Sara Yehia Abdel Fatah, Thamer Alghamdi, Moath Alathbah

All Works

This paper investigates and implements a miniaturized microwave system for microstrip linear array antenna that operates in X-band (10.1 GHz), S-band (3.4 GHz) and C-band (5.6 GHz). The microwave system consists of three parts: a power divider, a directional coupler, and a matching network stub. These systems feed a linear array (16 elements) of patch antennas loaded with resonance planar omega structures array (160 elements) distributed in both patch (64 elements) and ground (96 elements) as the metamaterial structures for miniaturization purpose. The 1-to-2 divider feeds two directional couplers that act as phase shifters. The couplers fed a set of …

เทคนิคการจัดกลุ่ม K-Means แบบการคำนวณควอนตัม, ภานุวัฒน์ ธนาภรณ์ชินพงษ์

Chulalongkorn University Theses and Dissertations (Chula ETD)

วิทยานิพนธ์ฉบับนี้ศึกษาอัลกอริธึม K-Means แบบผสมระหว่างควอนตัมและคลาสสิก สำหรับการจัดกลุ่มข้อมูลผู้ป่วยโรคหัวใจ โดยใช้วงจร swap-test ของควอนตัมในการคำนวณระยะทาง และได้ทำการทดสอบบนควอนตัมคอมพิวเตอร์จำลองใน 2 แนวทาง คือแบบที่มีสัญญาณรบกวน และแบบอุดมคติ ด้วยชุดข้อมูลจริงที่มีมากกว่า 1,000 รายการ ผลการทดลองแสดงให้เห็นว่า วิธีควอนตัมทั้งสองสามารถทำความแม่นยำได้สูงถึง 0.83 และให้ค่า F1-score ใกล้เคียงกับ K-Means แบบคลาสสิก (0.82–0.83) แม้ในกรณีค่าจากควอนตัมคอมพิวเตอร์ที่มีสัญญาณรบกวน ผลการศึกษานี้ชี้ให้เห็นถึงศักยภาพในการใช้งานจริงของวิธีจัดกลุ่มที่ได้รับการเสริมด้วยควอนตัม

Dynamic Modeling And Control Of A Solid State Semiconductor-Based Transformer, Microgrid And Storage Systems, Rubén Darío Viñán-Velasco

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

Smart Grids are power grid models designed with the idea of including the growing new technologies, from generation to storage devices, and are a response to the growing demands from consumers and the presence of electronic components being commonplace in the modern devices. The design requires a dynamic alternative in order to build an independent grid that can also work in cooperation with other micro-grids and the power grid in an integrated way. Smart-grids present several advantages over the traditional power grid scheme, but the economic costs of the components required to implement smart-grids is currently a great limitation. This …

การพยากรณ์จำนวนสายโทรศัพท์เข้าของศูนย์บริการข้อมูลทางโทรศัพท์แบบรายครึ่งชั่วโมง, กฤตชญา ประภารัตน์

Chulalongkorn University Theses and Dissertations (Chula ETD)

การวิจัยนี้มีวัตถุประสงค์เพื่อศึกษาโมเดลที่เหมาะสมสำหรับการพยากรณ์จำนวนสายโทรศัพท์เข้าของศูนย์บริการข้อมูลทางโทรศัพท์แบบรายครึ่งชั่วโมง โดยศูนย์บริการข้อมูลทางโทรศัพท์ หรือ Call Center มีบทบาทเป็นศูนย์รวมสายโทรเข้าและโทรออกของธุรกิจ ซึ่งเป็นช่องทางสำคัญในการตอบสนองความต้องการของลูกค้า ไม่ว่าจะเป็นการสอบถามข้อมูล การขอคำแนะนำ หรือแก้ปัญหาต่าง ๆ ศูนย์บริการข้อมูลทางโทรศัพท์จึงมีการจัดวางแผนกำลังคนรับสาย เพื่อให้สอดคล้องกับปริมาณสายโทรศัพท์ที่คาดว่าจะเข้ามา แต่ในบางครั้งการวางแผนจัดกำลังคนรับสายอาจต้องมีการปรับระหว่างวัน เนื่องจากจำนวนสายโทรเข้าอาจมีจำนวนมากกว่าหรือน้อยกว่าที่คาดการณ์ไว้ ซึ่งวิธีการเดิมที่บริษัทใช้ในการคำนวน อาจมีความคลาดเคลื่อน และไม่สามารถปรับตัวเลขได้ภายในระยะเวลาอันสั้น งานวิจัยนี้จึงนำเสนอการพยากรณ์จำนวนสายโทรศัพท์เข้าของศูนย์บริการข้อมูลทางโทรศัพท์แบบรายครึ่งชั่วโมง มีวัตถุประสงค์เพื่อพยากรณ์ปริมาณสายการโทรเข้าช่วงหลัง 10 น. เพื่อช่วยให้ฝ่ายวางแผนกำลังคนเห็นแนวโน้มปริมาณสายที่คาดว่าจะเข้ามา และตัดสินใจปรับแผนการจัดกำลังคนได้อย่างทันท่วงที โดยโมเดลจะจัดกลุ่มและพยากรณ์รูปแบบการกระจายตัวของปริมาณสายโทรเข้า และพยากรณ์จำนวนสายที่คาดว่าจะเข้ามา ผลการทดลองพบว่า โมเดลที่พัฒนาขึ้นมี MAPE อยู่ที่ 20.8% ซึ่งมีประสิทธิภาพดีกว่าวิธีการคำนวนเดิมของบริษัทที่มี MAPE อยู่ที่ 52.7%

การแบ่งส่วนเนื้องอกตับโดยใช้โมเดลการเรียนรู้เชิงลึกด้วยโครงข่ายความสนใจจากรูปภาพสเปคซีที, วันรัฐ ลิ้มประไพพงษ์

Chulalongkorn University Theses and Dissertations (Chula ETD)

การแบ่งส่วนเนื้องอกในตับโดยอัตโนมัติจากภาพถ่ายทางการแพทย์มีบทบาทสำคัญในการช่วยลดภาระงานของรังสีแพทย์ในขั้นตอนการวางแผนรักษามะเร็งตับด้วยวิธีรังสีบำบัด โดยรูปสเปคซีทีมักถูกนำมาใช้เพื่อช่วยระบุส่วนเนื้องอกให้แม่นยำเพื่อให้การวางแผนการรักษามีประสิทธิภาพ อย่างไรก็ตาม การแบ่งส่วนเนื้องอกจากภาพเหล่านี้เป็นเรื่องท้าทายเนื่องจากปัญหาต่างๆ เช่น การกระจายแสงที่ผิดปกติ ทำให้ขนาดเนื้องอกดูใหญ่กว่าความเป็นจริงและลดความแม่นยำในการแบ่งส่วน งานวิจัยฉบับนี้ได้นำเสนอโครงข่ายคัดกรองหลายระดับแบบคู่ (Paired Multiscale Attention Network) ซึ่งเป็นสถาปัตยกรรมที่แบ่งออกเป็นสองทาง เส้นทางแรกฝึกฝนชุดข้อมูลสเปคซีทีโดยใช้โครงข่าย Multiscale Attention Network (MA-Net) เส้นทางที่สองมีการใช้การแปลงแบบไวซ์ท็อปแฮท (White Top-Hat) แล้วนำลักษณะเด่นที่ได้มาควบรวมกับเส้นทางแรก ช่วยลดความบกพร่องของการแบ่งส่วนที่มักเกิดจากความแปรปรวนของแสง ในงานวิจัยนี้จะแบ่งการทดสอบเป็นสองส่วน ส่วนแรกคือการทดสอบโมเดลแบ่งส่วนเนื้อตับ โดยใช้ MA-Net โดยมีโมเดลย่อยคือ ResNet50 ฝึกกับชุดข้อมูลซีทีโดยรวมระหว่างชุดข้อมูลสาธารณะ 3DIRCADb-01 และชุดข้อมูลจากโรงพยาบาลจุฬาลงกรณ์ สภากาชาดไทย โดยมีค่า Dice similarity coefficient (DSC) อยู่ที่ 89.67% ในส่วนการทดสอบโมเดลแบ่งส่วนเนื้องอกตับ จะใช้โครงข่ายคัดกรองหลายระดับแบบคู่ ฝึกด้วยชุดข้อมูล เทคนีเซียม-99 เอ็มเอเอ สเปคซีทีจากโรงพยาบาลจุฬาลงกรณ์ สภากาชาดไทยโดยมีค่า DSC ที่ 67.00% ซึ่งให้ประสิทธิภาพการแบ่งส่วนที่ดีที่สุดเมื่อเทียบกับสถาปัตยกรรมอื่นๆ รวมถึงผลจากงานวิจัยก่อนหน้านี้ที่ทดสอบด้วยชุดข้อมูลเดียวกัน

Ensemble Learning With Sleep Mode Management To Enhance Anomaly Detection In Iot Environment, Khawlah Harahsheh, Rami Al-Naimat, Malek Alzaqebah, Salam Shreem, Esraa Aldreabi, Chung-Hao Chen

Electrical & Computer Engineering Faculty Publications

The rapid proliferation of Internet of Things (IoT) devices has underscored the critical need for energy-efficient cybersecurity measures. This presents the dual challenge of maintaining robust security while minimizing power consumption. Thus, this paper proposes enhancing the machine learning performance through Ensemble Techniques with Sleep Mode Management (ELSM) approach for IoT Intrusion Detection Systems (IDS). The main challenge lies in the high-power consumption attributed to continuous monitoring in traditional IDS setups. ELSM addresses this challenge by introducing a sophisticated sleep-awake mechanism, activating the IDS system only during anomaly detection events, effectively minimizing energy expenditure during periods of normal network operation. …

A New Cache Replacement Policy In Named Data Network Based On Fib Table Information, Mehran Hosseinzadeh, Neda Moghim, Samira Taheri, Nasrin Gholami

VMASC Publications

Named Data Network (NDN) is proposed for the Internet as an information-centric architecture. Content storing in the router’s cache plays a significant role in NDN. When a router’s cache becomes full, a cache replacement policy determines which content should be discarded for the new content storage. This paper proposes a new cache replacement policy called Discard of Fast Retrievable Content (DFRC). In DFRC, the retrieval time of the content is evaluated using the FIB table information, and the content with less retrieval time receives more discard priority. An impact weight is also used to involve both the grade of retrieval …

Resilience In The Wake Of Storms: Unveiling Spatiotemporal Mobility Dynamics Of Gulf Coast Communities Through Crowd-Sourced Data, Joswin Valerian Concessao

Computer Science and Engineering Theses - Archive

Flood events present substantial challenges for coastal communities, severely impacting public safety, transportation infrastructure, and overall livability. Tropical storms, hurricanes, and sea level rise can cause extensive damage to homes and critical systems, requiring costly and prolonged recovery efforts. Coastal transportation networks are particularly vulnerable to flooding, leading to road closures, increased congestion, restricted access to essential services, and long-term economic disruptions. Understanding the effects of flood events on mobility patterns is crucial for urban planning and effective disaster management.

This thesis utilizes motif analysis to examine transportation network disruptions and access patterns in Harrison County, Mississippi, during Hurricane Ida …

Securing Internet Of Things (Iot) Data Storage, Savannah Malo

Honors Theses and Capstones

Internet of Things (IoT) devices are commonly known to be susceptible to security attacks, which can lead to the leakage, theft, or erasure of data. Despite similar attack methods used on conventional technologies, IoT devices differ in how they consist of a small amount of hardware, limited networking capability, and utilize NoSQL databases. IoT solutions prefer NoSQL databases since they are compatible for larger datasets, unstructured and time-series data. However, these implementations are less likely to employ critical security features, like authentication, authorization, and encryption. The purpose of this project is to understand why those security measures are not strictly …

Neurosymbolic Value-Inspired Ai (Why, What, And How), Amit Sheth, Kaushik Roy

Publications

The rapid progression of Artificial Intelligence (AI) systems, facilitated by the advent of Large Language Models (LLMs), has resulted in their widespread application to provide human assistance across diverse industries. This trend has sparked significant discourse centered around the ever-increasing need for LLM-based AI systems to function among humans as part of human society, sharing human values, especially as these systems are deployed in high-stakes settings (e.g., healthcare, autonomous driving, etc.). Towards this end, neurosymbolic AI systems are attractive due to their potential to enable easy-tounderstand and interpretable interfaces for facilitating valuebased decision-making, by leveraging explicit representations of shared values. …

K-Perm: Personalized Response Generation Using Dynamic Knowledge Retrieval And Persona-Adaptive Queries, Kanak Raj, Kaushik Roy, Vamshi Bonagiri, Priyanshul Govil, Krishnaprasad Thirunarayan, Raxit Goswami, Manas Gaur

Publications

Personalizing conversational agents can enhance the quality of conversations and increase user engagement. However, they often lack external knowledge to tend to a user’s persona appropriately. This is particularly crucial for practical applications like mental health support, nutrition planning, culturally sensitive conversations, or reducing toxic behavior in conversational agents. To enhance the relevance and comprehensiveness of personalized responses, we propose using a two-step approach that involves (1) selectively integrating user personas and (2) contextualizing the response with supplementing information from a background knowledge source. We develop K-PERM (Knowledge-guided PErsonalization with Reward Modulation), a dynamic conversational agent that combines these elements. …

Causal Event Graph-Guided Language-Based Spatiotemporal Question Answering, Kaushik Roy, Alessandro Oltramari, Yuxin Zi, Chathurangi Shyalika, Vignesh Narayanan, Amit Sheth

Publications

Large Language Models have excelled at encoding and leveraging language patterns in large text-based corpora for various tasks, including spatiotemporal event-based question answering (QA). However, due to encoding a text-based projection of the world, they have also been shown to lack a fullbodied understanding of such events, e.g., a sense of intuitive physics, and cause-and-effect relationships among events. In this work, we propose using causal event graphs (CEGs) to enhance language understanding of spatiotemporal events in language models, using a novel approach that also provides proofs for the model’s capture of the CEGs. A CEG consists of events denoted by …

Tutorial: Knowledge-Infused Artificial Intelligence For Mental Healthcare, Kaushik Roy

Publications

Artificial Intelligence (AI) systems for mental healthcare (MHCare) have been ever-growing after realizing the importance of early interventions for patients with chronic mental health (MH) conditions. Social media (SocMedia) emerged as the go-to platform for supporting patients seeking MHCare. The creation of peer-support groups without social stigma has resulted in patients transitioning from clinical settings to SocMedia supported interactions for quick help. Researchers started exploring SocMedia content in search of cues that showcase correlation or causation between different MH conditions to design better interventional strategies. User-level Classification-based AI systems were designed to leverage diverse SocMedia data from various MH conditions, …

Exploring Alternative Approaches To Language Modeling For Learning From Data And Knowledge, Yuxin Zi, Kaushik Roy, Vignesh Narayanan, Amit Sheth

Publications

Despite their wide applications to language understanding tasks, large language models (LLMs) still face challenges such as hallucinations - the occasional fabrication of information, and alignment issues - the lack of associations with human-curated world models (e.g., intuitive physics or common-sense knowledge). Additionally, the black-box nature of LLMs makes it highly challenging to train them meaningfully in order to achieve a desired behavior. Specifically, the attempt to adjust LLMs’ concept embedding spaces can be highly intractable, which involves analyzing the implicit impact on LLMs’ numerous parameters and the resulting inductive biases. This paper proposes a novel architecture that wraps powerful …

Personalized Bayesian Inference For Explainable Healthcare Management And Intervention, Utkarshani Jaimini, Krishnaprasad Thirunaravan, Maninder Kalra, Robin Dawson, Amit Sheth

Publications

Chronic healthcare conditions such as Asthma re- quires constant monitoring and managing of symptoms and their triggers for better quality of life. Each asthma patient reacts very differently to potential triggers. Hence, there is a need to develop a explainable personalized framework for each patient to capture susceptibility to asthma triggers. We developed a personalized knowledge-based probabilistic model to predict asthma exacerbation for different environmental factors utilizing patient generated health data from pediatric asthma patients. Further, the personalized model provides a metric, called Health Coefficient, to quantify the health of a patient for varying environmental factors. We demonstrate the predictive …

Causal Neuro-Symbolic Ai: A Synergy Between Causality And Neuro-Symbolic Methods, Utkarshani Jaimini, Cory Henson, Amit Sheth

Publications

Causal Neuro-Symbolic AI combines the benefits of causality with Neuro-Symbolic Artificial Intelligence (NeSyAI). More specifically, it (1) enriches NeSyAI systems with explicit representations of causality, (2) integrates causal knowledge with domain knowledge, and (3) enables the use of NeSyAI techniques for causal AI tasks. The explicit causal representation yields insights that predictive models may fail to analyze from observational data. It can also assist people in decision-making scenarios where discerning the cause of an outcome is necessary to choose among various interventions.

Ontolog Summit 2024 Talk Report: Healthcare Assistance Challenges-Driven Neurosymbolic Ai, Kaushik Roy

Publications

Although Artificial Intelligence technology has proven effective in providing healthcare assistance by analyzing health data, it still falls short in supporting decision-making. This deficiency largely stems from the predominance of opaque neural networks, particularly in mental health care AI applications, which raise concerns about their unpredictable and unverifiable nature. This skepticism hinders the transition from information support to decision support. This presentation will explore neurosymbolic approaches that combine neural networks with symbolic control and verification mechanisms. These approaches aim to unlock AI’s full potential by enhancing information analysis and decision-making support for healthcare assistance1.

Neurosymbolic Customized And Compact Copilots, Kaushik Roy, Megha Chakraborty, Yuxin Zi, Manas Gaur, Amit Sheth

Publications

Large Language Models (LLMs) are credible with open-domain interactions such as question answering, summarization, and explanation generation [1]. LLM reasoning is based on parametrized knowledge, and as a consequence, the models often produce absurdities and inconsistencies in outputs (e.g., hallucinations and confirmation biases) [2]. In essence, they are fundamentally hard to control to prevent off-the-rails behaviors, are hard to fine-tune, customize for tailored needs, prompt effectively (due to the “tug-of-war” between external and parametric memory), and extremely resource-hungry due to the enormous size of their extensive parametric configurations [3,4]. Thus, significant challenges arise when these models are required to perform …

A Comprehensive Survey On Rare Event Prediction, Chathurangi Shyalika Jayakody Kankanamalage, Ruwan Wickramarachchi, Amit Sheth

Publications

Rare event prediction involves identifying and forecasting events with a low probability using machine learning (ML) and data analysis. Due to the imbalanced data distributions, where the frequency of common events vastly outweighs that of rare events, it requires using specialized methods within each step of the ML pipeline, i.e., from data processing to algorithms to evaluation protocols. Predicting the occurrences of rare events is important for real-world applications, such as Industry 4.0, and is an active research area in statistics and ML. This paper comprehensively reviews the current approaches for rare event prediction along four dimensions: rare event data, …