Digital Commons Network^™

Neurosymbolic Ai Approach To Attribution In Large Language Models, Deepa Tilwani, Revathy Venkataramanan, Amit P. Sheth

Faculty Publications

Attribution in large language models (LLMs) remains a significant challenge, particularly in ensuring the factual accuracy and reliability of the generated outputs. Current methods for citation or attribution, such as those employed by tools like Perplexity.ai and Bing Search-integrated LLMs, attempt to ground responses by providing real-time search results and citations. However, so far, these approaches suffer from issues such as hallucinations, biases, surface-level relevance matching, and the complexity of managing vast, unfiltered knowledge sources. While tools like Perplexity.ai dynamically integrate web-based information and citations, they often rely on inconsistent sources such as blog posts or unreliable sources, which limits …

Mobility Management In Tsch-Based Industrial Wireless Networks, Marco Pettorali, Francesca Righetti, Carlo Vallati, Sajal K. Das, Giuseppe Anastasi

Computer Science Faculty Research & Creative Works

Wireless Sensor and Actuator Networks (WSANs) are an effective technology for improving the efficiency and productivity in many industrial domains and are also the building blocks for the Industrial Internet of Things (IIoT). To support this trend, the IEEE has defined the 802.5.4 Time-Slotted Channel Hopping (TSCH) protocol. Unfortunately, TSCH does not provide any mechanism to manage node mobility, while many current industrial applications involve Mobile Nodes (MNs), e.g., mobile robots or wearable devices carried by workers. In this article, we present a framework to efficiently manage mobility in TSCH networks, by proposing an enhanced version of the Synchronized Single-hop …

Energy Consumption Optimization Of Uav-Assisted Traffic Monitoring Scheme With Tiny Reinforcement Learning, Xiangjie Kong, Chenhao Ni, Gaohui Duan, Guojiang Shen, Yao Yang, Sajal K. Das

Computer Science Faculty Research & Creative Works

Unmanned Aerial Vehicles (UAVs) can capture pictures of road conditions in all directions and from different angles by carrying high-definition cameras, which helps gather relevant road data more effectively. However, due to their limited energy capacity, drones face challenges in performing related tasks for an extended period. Therefore, a crucial concern is how to plan the path of UAVs and minimize energy consumption. To address this problem, we propose a multi-agent deep deterministic policy gradient based (MADDPG) algorithm for UAV path planning (MAUP). Considering the energy consumption and memory usage of MAUP, we have conducted optimizations to reduce consumption on …

Stitching Satellites To The Edge: Pervasive And Efficient Federated Leo Satellite Learning, Mohamed Elmahallawy, Tony Tie Luo

Computer Science Faculty Research & Creative Works

In the Ambitious Realm of Space AI, the Integration of Federated Learning (FL) with Low Earth Orbit (LEO) Satellite Constellations Holds Immense Promise. However, Many Challenges Persist in Terms of Feasibility, Learning Efficiency, and Convergence. These Hurdles Stem from the Bottleneck in Communication, Characterized by Sporadic and Irregular Connectivity between LEO Satellites and Ground Stations, Coupled with the Limited Computation Capability of Satellite Edge Computing (SEC). This Paper Proposes a Novel FL-SEC Framework that Empowers LEO Satellites to Execute Large-Scale Machine Learning (ML) Tasks Onboard Efficiently. its Key Components Include I) Personalized Learning Via Divide-And-Conquer, Which Identifies and Eliminates Redundant …

Trusted Digital Twin Network For Intelligent Vehicles, Asad Malik, Ayan Roy, Sanjay Madria

Computer Science Faculty Research & Creative Works

Vehicle-to-vehicle (V2V) infrastructure facilitates wireless communication among vehicles within close proximity. This allows sharing of contextual information such as speed, location, direction, traffic, route closures, human behavior mental conditions to improve traffic flow, reduce collisions, and enhance safety on the road. However, the assumption of honest peers along with the over-reliability on the information shared in the network can pose a serious threat to human safety. A digital twin is a concept that enables a system to develop a virtual environment that mimics the real-life scenario for any situation. The availability of powerful computing equipment inside vehicles can be leveraged …

Mobilytics: Mobility Analytics Framework For Transferring Semantic Knowledge, Shreya Ghosh, Soumya K. Ghosh, Sajal K. Das, Prasenjit Mitra

Computer Science Faculty Research & Creative Works

The proliferation of sensor-equipped smartphones has led to the generation of vast amounts of GPS data, such as timestamped location points, enabling a range of location-based services. However, deciphering the spatio-temporal dynamics of mobility to understand the underlying motivations behind travel patterns presents a significant challenge. his paper focuses on how individuals' GPS traces (latitude, longitude, timestamp) interpret the connection and correlations among different entities such as people, locations or point-of-interests (POIs), and semantic contexts (trip-purpose). We introduce a mobility analytics framework, named Mobilytics designed to identify trip purposes from individual GPS traces by leveraging a “mobility knowledge graph” (MKG) …

Real-Time Analysis Of Encrypted Dns Traffic For Threat Detection, Marta Moure-Garrido, Sajal K. Das, Celeste Campo, Carlos Garcia-Rubio

Computer Science Faculty Research & Creative Works

Domain Name System (DNS) tunneling is a well-known cyber-attack that allows data exfiltration - the attackers exploit this tunnel to extract sensitive information from the system. Advanced Persistent Threat (APT) attackers encapsulate malicious traffic in a DNS connection to elude security mechanisms such as Intrusion Detection System (IDS). Although different techniques have been implemented to detect these targeted attacks, their rise induces a threat to Cyber-Physical Systems (CPS). The DNS over HTTPS (DoH) tunnel detection is a challenge because the encrypted data prevents an analysis of DNS traffic content. In this paper, we present a novel detection system that identifies …

Approximation Algorithm For Connected Submodular Function Maximization Problems, Wenzheng Xu, He Xue, Jing Li, Weifa Liang, Zichuan Xu, Pan Zhou, Xiaohua Jia, Sajal K. Das

Computer Science Faculty Research & Creative Works

In this paper, we study a connected submodular function maximization problem, which arises from many applications including deploying UAV networks to serve users and placing sensors to cover Points of Interest (PoIs). Specifically, given a budget K, the problem is to find a subset S with K nodes from a graph G so that a given submodular function f (S) on S is maximized while the induced subgraph G[S] by the nodes in S is connected, where the submodular function f can be used to model many practical application problems, such as the number of users within different service areas …

Analyzing Real-Time Insect Detection In Smart Connected Farms, Ashish Gupta, Vishesh Kumar Tanwar, Amit Nath Jha, Sajal K. Das

Computer Science Faculty Research & Creative Works

With a vision of smart connected farms, this research proposes an insect detection framework (InsDet) to identify the most harmful corn crop insect, known as corn rootworm beetle. InsDet employs an object detection model with varying sizes to localize the insects in sticky-trap images.

Cav-Ad: A Robust Framework For Detection Of Anomalous Data And Malicious Sensors In Cav Networks, Md Sazedur Rahman, Mohamed Elmahallawy, Sanjay Madria, Samuel Frimpong

Computer Science Faculty Research & Creative Works

The adoption of connected and automated vehicles (CAVs) has sparked considerable interest across diverse industries, including public transportation, underground mining, and agriculture sectors. However, CAVs' reliance on sensor readings makes them vulnerable to significant threats. Manipulating these readings can compromise CAV network security, posing serious risks for malicious activities. Although several anomaly detection (AD) approaches for CAV networks are proposed, they often fail to: i) detect multiple anomalies in specific sensor(s) with high accuracy or F1 score, and ii) identify the specific sensor being attacked. In response, this paper proposes a novel framework tailored to CAV networks, called CAV-AD, for …

Freyr⁺: Harvesting Idle Resources In Serverless Computing Via Deep Reinforcement Learning, Hanfei Yu, Hao Wang, Jian Li, Xu Yuan, Seung Jong Park

Computer Science Faculty Research & Creative Works

Serverless computing has revolutionized online service development and deployment with ease-to-use operations, auto-scaling, fine-grained resource allocation, and pay-as-you-go pricing. However, a gap remains in configuring serverless functions - the actual resource consumption may vary due to function types, dependencies, and input data sizes, thus mismatching the static resource configuration by users. Dynamic resource consumption against static configuration may lead to either poor function execution performance or low utilization. This paper proposes Freyr+, a novel resource manager (RM) that dynamically harvests idle resources from over-provisioned functions to accelerate under-provisioned functions for serverless platforms. Freyr+ monitors each function's resource utilization in real-time …

Mild Cognitive Impairment Classification Using A Novel Finer-Scale Brain Connectome, Yanjun Lyu, Lu Zhang, Xiaowei Yu, Chao Cao, Tianming Liu, Dajiang Zhu

Computer Science Faculty Research & Creative Works

Mild cognitive impairment (MCI) is recognized as a precursor to Alzheimer's disease (AD), a progressive and irreversible neurodegenerative disorder of the brain. The neurodegeneration of brain connectivity networks plays a pivotal role in the development and progression of MCI. Traditionally, brain networks are generated using coarse-grained brain regions, where the regions serve as nodes and their functional or structural connections are used as edges. Recently, a novel finer scale brain folding patterns named 3hinge gyrus (3HG) was identified, which is defined as the conjunctions coming from three directions on gyral crests. 3HGs have been shown playing an important role in …

Eye-Gaze Guided Multi-Modal Alignment For Medical Representation Learning, Chong Ma, Hanqi Jiang, Wenting Chen, Yiwei Li, Zihao Wu, Xiaowei Yu, Zhengliang Liu, Lei Guo, Dajiang Zhu, Tuo Zhang, Dinggang Shen, Tianming Liu, Xiang Li

Computer Science Faculty Research & Creative Works

In the medical multi-modal frameworks, the alignment of cross-modality features presents a significant challenge. However, existing works have learned features that are implicitly aligned from the data, without considering the explicit relationships in the medical context. This data-reliance may lead to low generalization of the learned alignment relationships. In this work, we propose the Eye-gaze Guided Multi-modal Alignment (EGMA) framework to harness eye-gaze data for better alignment of medical visual and textual features. We explore the natural auxiliary role of radiologists' eye-gaze data in aligning medical images and text and introduce a novel approach by using eye-gaze data, collected synchronously …

Communication-Efficient Federated Learning For Leo Constellations Integrated With Haps Using Hybrid Noma-Ofdm, Mohamed Elmahallawy, Tony T. Luo, Khaled Ramadan

Computer Science Faculty Research & Creative Works

Space AI has become increasingly important and sometimes even necessary for government, businesses, and society. An active research topic under this mission is integrating federated learning (FL) with satellite communications (SatCom) so that numerous low Earth orbit (LEO) satellites can collaboratively train a machine learning model. However, the special communication environment of SatCom leads to a very slow FL training process up to days and weeks. This paper proposes NomaFedHAP, a novel FL-SatCom approach tailored to LEO satellites, that (1) utilizes high-altitude platforms (HAPs) as distributed parameter servers (PSs) to enhance satellite visibility, and (2) introduces non-orthogonal multiple access (NOMA) …

Towards Fine-Gained Services: Nfv-Assisted Tracking And Positioning Using Micro-Services For Multi-Robot Cooperation, Bo Yi, Lin Qiu, Jianhui Lv, Yingpu Nian, Xingwei Wang, Sajal K. Das

Computer Science Faculty Research & Creative Works

Robotics as a Service (RaaS) emerges as a new paradigm to motivate diversified potential of the "remote-controlled economy" for flexible and efficient service provision with the help of cloud computing. The multi-robot cooperation (MRC) technology has been widely used in various intelligent logistics scenarios, such as warehouses, factories, airports and subway stations, benefiting from the advantages of high operational efficiency and low labor cost. While promising, the corresponding challenge is that the service functions deployed on logistics robots (LRs) are more prone to failures such as resource exhaustion and error configuration in the multi-robot system (MRS). In this way, it …

Uncovering The Causes Of Emotions In Software Developer Communication Using Zero-Shot Llms, Mia Mohammad Imran, Preetha Chatterjee, Kostadin Damevski

Computer Science Faculty Research & Creative Works

Understanding and identifying the causes behind developers' emotions (e.g., Frustration caused by 'delays in merging pull requests') can be crucial towards finding solutions to problems and fostering collaboration in open-source communities. Effectively identifying such information in the high volume of communications across the different project channels, such as chats, emails, and issue comments, requires automated recognition of emotions and their causes. To enable this automation, large-scale software engineering-specific datasets that can be used to train accurate machine learning models are required. However, such datasets are expensive to create with the variety and informal nature of software projects' communication channels. In …

Message From Bits 2024 Co-Chairs And Technical Program Co-Chairs; Smartcomp 2024, Sajal K. Das, Hayato Yamana, Keiichi Yasumoto, Shameek Bhattacharjee

Computer Science Faculty Research & Creative Works

No abstract provided.

Unsafe Events Detection In Smart Water Meter Infrastructure Via Noise-Resilient Learning, Ayanfeoluwa Oluyomi, Sahar Abedzadeh, Shameek Bhattacharjee, Sajal K. Das

Computer Science Faculty Research & Creative Works

Residential smart water meters (SWMs) collect real-time water consumption data, enabling automated billing and peak period forecasting. The presence of unsafe events is typically detected via deviations from the benign profile of water usage. However, profiling the benign behavior is non-trivial for large-scale SWM networks because once deployed, the collected data already contain those events, biasing the benign profile. To address this challenge, we propose a real-time data-driven unsafe event detection framework for city-scale SWM networks that automatically learns the profile of benign behavior of water usage. Specifically, we first propose an optimal clustering of SWMs based on the recognition …

Log Sequence Anomaly Detection Based On Template And Parameter Parsing Via Bert, Xiaolin Chai, Hang Zhang, Jue Zhang, Yan Sun, Sajal K. Das

Computer Science Faculty Research & Creative Works

Logs record various operations and events during system running in text format, which is an essential basis for detecting and identifying potential security threats or system failures and is widely used in system management to ensure security and reliability. Existing log sequence anomaly detection is limited by log parsing and does not consider all key features of logs, which may cause false or missed detection. In this paper, we propose a fast and accurate log parsing method and feed the entire log content into the deep learning network for analysis. To avoid semantic loss during parsing, we replace some variables …

Federated Graph Anomaly Detection Via Contrastive Self-Supervised Learning, Xiangjie Kong, Wenyi Zhang, Hui Wang, Mingliang Hou, Xin Chen, Xiaoran Yan, Sajal K. Das

Computer Science Faculty Research & Creative Works

Attribute graph anomaly detection aims to identify nodes that significantly deviate from the majority of normal nodes and has received increasing attention due to the ubiquity and complexity of graph-structured data in various real-world scenarios. However, current mainstream anomaly detection methods are primarily designed for centralized settings, which may pose privacy leakage risks in certain sensitive situations. Although federated graph learning offers a promising solution by enabling collaborative model training in distributed systems while preserving data privacy, a practical challenge arises as each client typically possesses a limited amount of graph data. Consequently, naively applying federated graph learning directly to …

Move: Matching Game For Partial Offloading In Vehicular Edge Computing, Mahmuda Akter, Debjyoti Sengupta, Anurag Satpathy, Sajal Das

Computer Science Faculty Research & Creative Works

Autonomous Vehicles (AV s) require substantial computational resources to perform operations that safely navigate vehicles in urban road networks. Resource-intensive operations are offloaded to roadside units (RSUs), acting as edge servers, to improve the responsiveness and reduce the energy consumed in execution. In this context, a cooperative execution involving the vehicular on-board units (OBUs) and the RSUs can act as a game changer. However, partial offloading is non-trivial and demands addressing the following research challenges. Firstly, the RSU's resources are limited, necessitating regulated resource assignments. Secondly, capturing distinctive vehicle parameters using a unified ranking scheme is imperative. Thirdly, an efficient …

Approximation Algorithm And Applications For Connected Submodular Function Maximization Problems, Ziming Wang, Jing Li, He Xue, Wenzheng Xu, Weifa Liang, Zichuan Xu, Jian Peng, Pan Zhou, Xiaohua Jia, Sajal K. Das

Computer Science Faculty Research & Creative Works

In this paper, we study a connected submodular function maximization problem, which arises from many applications including deploying UAV networks to serve users and placing sensors to cover Points of Interest (PoIs). Specifically, given a budget $K$ , the problem is to find a subset $S$ with $K$ nodes from a graph $G$ , so that a given submodular function $f(S)$ on $S$ is maximized and the induced subgraph $G[S]$ by the nodes in $S$ is connected, where the submodular function $f$ can be used to model many practical application problems, such as the number of users within different service …

Mime: Mobility-Induced Dynamic Matching For Partial Offloading In Vehicular Edge Computing, Mahmuda Akter, Debjyoti Sengupta, Anurag Satpathy, Sajal K. Das

Computer Science Faculty Research & Creative Works

Autonomous vehicles (AVs) execute compute intensive control operations like adjusting speed and steering, causing significant energy dissipation and latency due to resource limited onboard units (OBUs). Offloading these tasks to Roadside Units (RSUs) is a solution, but it faces challenges. First, the stringent latency requirements are impacted by the vehicle's stochastic velocity. Second, allocating limited RSU resources to numerous vehicles within its coverage area is difficult. This paper proposes the MIME framework to address these issues. We use Discrete Fourier transform (DFT) that computes the average velocity over an aperiodic velocity signal extracted from a real-world dataset. for resource allocation, …

Persistent Monitoring Of Insect-Pests On Sticky Traps Through Hierarchical Transfer Learning And Slicing-Aided Hyper Inference, Fateme Fotouhi, Kevin Menke, Aaron Prestholt, Ashish Gupta, Matthew E. Carroll, Hsin Jung Yang, Edwin J. Skidmore, Matthew O'Neal, Nirav Merchant, Sajal K. Das, Peter Kyveryga, Baskar Ganapathysubramanian, Asheesh K. Singh, Arti Singh, Soumik Sarkar

Computer Science Faculty Research & Creative Works

Introduction: Effective monitoring of insect-pests is vital for safeguarding agricultural yields and ensuring food security. Recent advances in computer vision and machine learning have opened up significant possibilities of automated persistent monitoring of insect-pests through reliable detection and counting of insects in setups such as yellow sticky traps. However, this task is fraught with complexities, encompassing challenges such as, laborious dataset annotation, recognizing small insect-pests in low-resolution or distant images, and the intricate variations across insect-pests life stages and species classes. Methods: to tackle these obstacles, this work investigates combining two solutions, Hierarchical Transfer Learning (HTL) and Slicing-Aided Hyper Inference …

A Comprehensive Survey On Pretrained Foundation Models: A History From Bert To Chatgpt, Ce Zhou, Qian Li, Chen Li, Jun Yu, Yixin Liu, Guangjing Wang, Kai Zhang, Cheng Ji, Qiben Yan, Lifang He, Hao Peng, Jianxin Li, Jia Wu, Ziwei Liu, Pengtao Xie, Caiming Xiong, Jian Pei, Philip S. Yu, Lichao Sun

Computer Science Faculty Research & Creative Works

Pretrained Foundation Models (PFMs) are regarded as the foundation for various downstream tasks across different data modalities. A PFM (e.g., BERT, ChatGPT, GPT-4) is trained on large-scale data, providing a solid parameter initialization for a wide range of downstream applications. In contrast to earlier methods that use convolution and recurrent modules for feature extraction, BERT learns bidirectional encoder representations from Transformers, trained on large datasets as contextual language models. Similarly, the Generative Pretrained Transformer (GPT) method employs Transformers as feature extractors and is trained on large datasets using an autoregressive paradigm. Recently, ChatGPT has demonstrated significant success in large language …

Adversarial Hidden Link Threats In Meta Computing, Junjie Xiong, Mingkui Wei, Zhuo Lu, Yao Liu

Computer Science Faculty Research & Creative Works

In the emerging field of Meta Computing, where data collection and integration are essential components, the threat of adversary hidden link attacks poses a significant challenge to web crawlers. In this paper, we investigate the impact of these attacks on data collection by web crawlers, emphasizing their evasion of traditional detection methods. Through empirical evaluation, we uncover vulnerabilities in existing crawler mechanisms, particularly in code inspection, and propose enhancements to mitigate these weaknesses. Our assessment of real-world web pages reveals the prevalence and impact of adversary hidden link attacks, emphasizing the necessity for robust countermeasures. Furthermore, we introduce a mitigation …

Should The Future Of Ais Conferences Be Hybrid?, Traci Carte, Matthew Nelson, Monica J. Garfield, Athanasia Pouloudi, Mani R. Subramani, Guillermo Rodríguez-Abitia, Souren Paul

Faculty Publications - Information Technology

Academic conferences provide a needed opportunity for academic community members to come together and share ideas. COVID-19 forced AIS to host conferences remotely for two years. From that experience, we learned a few things about virtualizing our conference activities including the potential for virtual conferences to widen participation and membership. In this paper, we reflect on that learning through a lens informed by reviewing published work on conference hybridization. We also make recommendations for how future conference chairs can think about AIS conferences. Changing how our conferences are delivered is risky, but simply returning to the old normal is also …

On Generative Models And Joint Architectures For Document-Level Relation Extraction, Aviv Brokman

Theses and Dissertations--Statistics

Biomedical text is being generated at a high rate in scientific literature publications and electronic health records. Within these documents lies a wealth of potentially useful information in biomedicine. Relation extraction (RE), the process of automating the identification of structured relationships between entities within text, represents a highly sought-after goal in biomedical informatics, offering the potential to unlock deeper insights and connections from this vast corpus of data. In this dissertation, we tackle this problem with a variety of approaches.

We review the recent history of the field of document-level RE. Several themes emerge. First, graph neural networks dominate the …

Effective Data Augmentation Techniques For Time Series Classification: An Empirical Evaluation, Pongpanod Sankosik

Chulalongkorn University Theses and Dissertations (Chula ETD)

Time series classification is crucial in fields such as healthcare, finance, and industrial processes, but it faces challenges like temporal data ordering, class im-balance, noise, and limited data. This research explores data augmentation techniques to improve classification performance, focusing on the MiniRocket classifier across 85 UCR datasets. The study identifies conditions under which augmentation techniques, like wDBA, enhance accuracy, though overall performance may vary. A dataset-specific approach is essential for effective augmentation. The research also examines the impact of augmentation on datasets with different characteristics, providing insights into when specific strategies are most benefi-cial. Future work includes optimizing augmentation methods …

Building A Human Digital Twin (Hdtwin) Using Large Language Models For Cognitive Diagnosis: Algorithm Development And Validation, Gina Sprint, Maureen Schmitter-Edgecombe, Diane Cook

Computer Science Faculty Scholarship

Background: Human digital twins have the potential to change the practice of personalizing cognitive health diagnosis because these systems can integrate multiple sources of health information and influence into a unified model. Cognitive health is multifaceted, yet researchers and clinical professionals struggle to align diverse sources of information into a single model. Objective: This study aims to introduce a method called HDTwin, for unifying heterogeneous data using large language models. HDTwin is designed to predict cognitive diagnoses and offer explanations for its inferences. Methods: HDTwin integrates cognitive health data from multiple sources, including demographic, behavioral, ecological momentary assessment, n-back test, …