Digital Commons Network^™

Achieving Efficient And Privacy-Preserving Reverse Skyline Query Over Single Cloud, Yubo Peng, Xiong Li, Ke Gu, Jinjun Chen, Sajal K. Das, Xiaosong Zhang

Computer Science Faculty Research & Creative Works

Reverse skyline query (RSQ) has been widely used in practice since it can pick out the data of interest to the query vector. To save storage resources and facilitate service provision, data owners usually outsource data to the cloud for RSQ services, which poses huge challenges to data security and privacy protection. Existing privacy-preserving RSQ schemes are either based on a two-cloud model or cannot fully protect privacy. To this end, we propose an efficient privacy-preserving reverse skyline query scheme over a single cloud (ePRSQ). Specifically, we first design a privacy-preserving inner product's sign determination scheme (PIPSD), which can determine …

Adaptive Critic Optimal Control Of An Uncertain Robot Manipulator With Applications, Ravi Prakash, Laxmidhar Behera, Sarangapani Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

Realistic manipulation tasks involve a prolonged sequence of motor skills in varying control environments consisting of uncertain robot dynamic models and end-effector payloads. To address these challenges, this article proposes an adaptive critic (AC)-based basis function neural network (BFNN) optimal controller. Using a single neural network (NN) with a basis function, the proposed optimal controller simultaneously learns task-related optimal cost function, robot internal dynamics, and optimal control law. This is achieved through the development of a novel BFNN tuning law using closed-loop system stability. Therefore, the proposed optimal controller provides real-time, implementable, cost-effective control solutions for practical robotic tasks. The …

Lifelong Safe Optimal Adaptive Tracking Control Of Nonlinear Strict-Feedback Discrete-Time Systems, Behzad Farzanegan, S. Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

This paper presents a comprehensive approach for achieving multi-task safe optimal adaptive tracking (MSOAT) for a class of nonlinear discrete-time systems, particularly those in strict-feedback form, utilizing a multi-layer neural network (MNN)-based framework. To begin, a cost function with a novel Barrier function (BF) term is introduced for each subsystem to address the weak safely reachable problem, serving as a crucial tool for guiding the system's trajectory toward the safe set while avoiding unwanted sets. To deal with the tracking problem, the Hamilton-Jacobi-Bellman (HJB) framework is used through the actor-critic MNN-based backstepping technique to estimate the solution of the value …

Ai Trustworthy: Ethical Challenges And Strategies, Jian Liu, Iwan Sandjaja, Donald C. Wunsch

Electrical and Computer Engineering Faculty Research & Creative Works

This paper explores the pivotal role of trust in the widespread application of Artificial Intelligence (AI) across various domains. We review AI applications in sectors like energy, healthcare, and autonomous vehicles and discuss the crisis of human trust they face. This paper introduces a novel framework that delineates the relationship between AI transparency and user trust, highlighting specific industry applications. Through a systematic review of recent literature, we first delve into factors such as emotional response, acceptance, transparency, accuracy, and interpretability that shape human trust in AI. We then underscore the necessity of ethical AI practices and highlight the importance …

Automatic Classification Of Activities In Classroom Videos, Jonathan K. Foster, Matthew Korban, Peter Youngs, Ginger S. Watson, Scott T. Acton

VMASC Publications

Classroom videos are a common source of data for educational researchers studying classroom interactions as well as a resource for teacher education and professional development. Over the last several decades emerging technologies have been applied to classroom videos to record, transcribe, and analyze classroom interactions. With the rise of machine learning, we report on the development and validation of neural networks to classify instructional activities using video signals, without analyzing speech or audio features, from a large corpus of nearly 250 h of classroom videos from elementary mathematics and English language arts instruction. Results indicated that the neural networks performed …

Bias-Aware Gaze Uniformity Assessment In Group Images, Omkar Kulkarni

Electronic Theses & Dissertations (2024 - present)

Today, more than 5 billion photos are captured every day, with smartphones generating over 94\% of these images. However, despite advancements in technology, achieving aesthetically pleasing group photos remains challenging, especially when it comes to aligning the direction of everyone’s gaze. While current methods focus on facial features, they often fail to ensure consistent gaze direction. The introduction of the iPhone's Live mode, which captures a 1.5-second video snippet along with still images, complicates the selection of the best key photo due to its subjective nature and a lack of publicly available data, especially during the pandemic.

To address these …

Trust: The Feature That Vending Machines And Atms Share, But Simplygo Lacks, Sun Sun Lim

Research Collection College of Integrative Studies

The article discussed the intricacies of trust in the SimplyGo debacle and highlighted how the design of physical interfaces like vending machines and ATMs and digital interfaces from apps like Grab, Parking.sg and ShopBack have critical features to instil trust. People need to be reassured that their transactions have proceeded as they should, and thay have not been short-changed.

Collect Spatiotemporally Correlated Data In Iot Networks With An Energy-Constrained Uav, Wenzheng Xu, Heng Shao, Qunli Shen, Jian Peng, Wen Huang, Weifa Liang, Tang Liu, Xin Wei Yao, Tao Lin, Sajal K. Das

Computer Science Faculty Research & Creative Works

UAVs (Unmanned Aerial Vehicles) Are Promising Tools For Efficient Data Collections Of Sensors In IoT Networks. Existing Studies Exploited Both Spatial And Temporal Data Correlations To Reduce The Amount Of Collected Redundant Data, In Which Sensors Are First Partitioned Into Different Clusters, A Master Sensor In Each Cluster Then Collects Raw Data From Other Sensors And Compresses The Received Data. An Energy-Constrained UAV Finally Collects The Maximum Amount Of Compressed Data From Different Master Sensors. We However Notice That The Compressed Data From Only A Portion Of Clusters Are Collected By The UAV In The Existing Studies, While The Data …

Resource Aware Clustering For Tackling The Heterogeneity Of Participants In Federated Learning, Rahul Mishra, Hari Prabhat Gupta, Garvit Banga, Sajal K. Das

Computer Science Faculty Research & Creative Works

Federated Learning Is A Training Framework That Enables Multiple Participants To Collaboratively Train A Shared Model While Preserving Data Privacy. The Heterogeneity Of Devices And Networking Resources Of The Participants Delay The Training And Aggregation. The Paper Introduces A Novel Approach To Federated Learning By Incorporating Resource-Aware Clustering. This Method Addresses The Challenges Posed By The Diverse Devices And Networking Resources Among Participants. Unlike Static Clustering Approaches, This Paper Proposes A Dynamic Method To Determine The Optimal Number Of Clusters Using Dunn Indices. It Enables Adaptability To The Varying Heterogeneity Levels Among Participants, Ensuring A Responsive And Customized Approach To …

Personalized Federated Graph Learning On Non-Iid Electronic Health Records, Tao Tang, Zhuoyang Han, Zhen Cai, Shuo Yu, Xiaokang Zhou, Taiwo Oseni, Sajal K. Das

Computer Science Faculty Research & Creative Works

Understanding The Latent Disease Patterns Embedded In Electronic Health Records (EHRs) Is Crucial For Making Precise And Proactive Healthcare Decisions. Federated Graph Learning-Based Methods Are Commonly Employed To Extract Complex Disease Patterns From The Distributed EHRs Without Sharing The Client-Side Raw Data. However, The Intrinsic Characteristics Of The Distributed EHRs Are Typically Non-Independent And Identically Distributed (Non-IID), Significantly Bringing Challenges Related To Data Imbalance And Leading To A Notable Decrease In The Effectiveness Of Making Healthcare Decisions Derived From The Global Model. To Address These Challenges, We Introduce A Novel Personalized Federated Learning Framework Named PEARL, Which Is Designed For …

Undeniable Authentication Of Digital Twin-Managed Smart Microfactory, Anusha Vangala, Ashok Kumar Das, Sajal K. Das

Computer Science Faculty Research & Creative Works

Smart Microfactories Use Additive Manufacturing to Create Products with Mixed Materials and Variable Sizes. Digital Twin Technology Enhances Control of the Additive Manufacturing Equipment in These Factories, Increasing Productivity and Minimizing Errors. the Digital Twins Communicate with the Machines to Furnish Sensitive Data and Instructions, Which Must Be Protected from Tampering. Authentication Rescues the Digital and Physical Twins from Menacing Attacks Such as Privileged Insider, Impersonation, Ephemeral Secret Leakage (ESL) and Man-In-The-Middle (MiTM) Attacks. to This End, We Propose Lightweight Authentication among the Digital and Physical Twins with the Undeniability of Issued Commands and Deniable Key Agreement. It Achieves Perfect …

Lease: Leveraging Energy-Awareness In Serverless Edge For Latency-Sensitive Iot Services, Aastik Verma, Anurag Satpathy, Sajal K. Das, Sourav Kanti Addya

Computer Science Faculty Research & Creative Works

Resource Scheduling Catering to Real-Time IoT Services in a Serverless-Enabled Edge Network is Particularly Challenging Owing to the Workload Variability, Strict Constraints on Tolerable Latency, and Unpredictability in the Energy Sources Powering the Edge Devices. This Paper Proposes a Framework LEASE that Dynamically Schedules Resources in Serverless Functions Catering to Different Microservices and Adhering to their Deadline Constraint. to Assist the Scheduler in Making Effective Scheduling Decisions, We Introduce a Priority-Based Approach that Offloads Functions from over-Provisioned Edge Nodes to Under-Provisioned Peer Nodes, Considering the Expended Energy in the Process Without Compromising the Completion Time of Microservices. for Real-World Implementations, …

Early Detection Of Driving Maneuvers For Proactive Congestion Prevention, Debasree Das, Shameek Bhattacharjee, Sandip Chakraborty, Bivas Mitra, Sajal K. Das

Computer Science Faculty Research & Creative Works

Road Traffic Congestion Affects Not Only the Commute Delay but Also a city's overall Social, Economic, and Environmental Growth. Existing Approaches for Road Congestion Mitigation Primarily Adopt a Reactive Approach by Detecting Congestion after It Occurs and Recommending Alternate Routes to the Vehicles, Which Fails to Prevent Congestion Cascading. in Contrast, We Propose a Pervasive Platform Called ProCon that Proactively Infers the Driving Micro-Behaviors that Can Contribute to Congestion Formation and Assist the Drivers in Avoiding Such Maneuvers in Real-Time during the Navigation. Thorough Evaluations over Multiple Real-Life and Simulated Datasets Indicate that ProCon Can Reduce Congestion for More Than …

Incivility In Open Source Projects: A Comprehensive Annotated Dataset Of Locked Github Issue Threads, Ramtin Ehsani, Mia Mohammad Imran, Robert Zita, Kostadin Damevski, Preetha Chatterjee

Computer Science Faculty Research & Creative Works

In the dynamic landscape of open-source software (OSS) development, understanding and addressing incivility within issue discussions is crucial for fostering healthy and productive collaborations. This paper presents a curated dataset of 404 locked GitHub issue discussion threads and 5961 individual comments, collected from 213 OSS projects. We annotated the comments with various categories of incivility using Tone Bearing Discussion Features (TBDFs), and, for each issue thread, we annotated the triggers, targets, and consequences of incivility. We observed that Bitter frustration, Impatience, and Mocking are the most prevalent TBDFs exhibited in our dataset. The most common triggers, targets, and consequences of …

On The K-Weak Coverage Of Random Mobile Sensors, Sajal K. Das, Rafal Kapelko

Computer Science Faculty Research & Creative Works

This paper studies the fundamental problem of energy consumption in the movement of mobile random sensors ensuring k-weak coverage on the domain. In particular, we analyze two notions of k-weak coverage on the unit square, namely (1) (k, x)-weak coverage in which every straight-line path across the width of the unit square passes through the sensing range of at least k sensors; and (2) (k, x, y)-weak coverage in which every straight-line path across the width and the length of the unit square passes through the sensing range of at least k sensors. The number of reliable and p-reliable sensors …

Posca: Path Optimization For Solar Cover Amelioration In Urban Air Mobility, Debjyoti Sengupta, Anurag Satpathy, Sajal K. Das

Computer Science Faculty Research & Creative Works

Urban Air Mobility (UAM) encompasses both piloted and autonomous aerial vehicles, spanning from small unmanned aerial vehicles (UAVs) like drones to passenger-carrying personal air vehicles (PAVs), to revolutionize smart transportation in congested urban areas. This emerging paradigm is anticipated to offer disruptive solutions to the mobility challenges in congested cities. In this context, a pivotal concern centers on the sustainability of transitioning to this mode of transportation, especially with the focus on incorporating clean technology into developing innovative solutions from the ground up. Recent studies highlight that a significant portion of the total energy consumption in UAM can be attributed …

Tasr: A Novel Trust-Aware Stackelberg Routing Algorithm To Mitigate Traffic Congestion, Doris E.M. Brown, Venkata Sriram Siddhardh Nadendla, Sajal K. Das

Computer Science Faculty Research & Creative Works

A Stackelberg routing platform (SRP) reduces congestion in one-shot traffic networks by proposing optimal route recommendations to the selfish travelers. Traditionally, Stackel-berg routing is cast as a partial control problem where a fraction of the traveler flow complies with route recommendations, while the remaining responds as selfish travelers. In this paper, we formulate a novel Stackelberg routing framework where the agents exhibit probabilistic compliance by accepting SRP's route recommendations with a trust probability. Specifically, we propose a greedy Trust-Aware Stackelberg Routing algorithm (in short, TASR) for SRP to compute unique path recommendations to each traveler flow with a unique demand. …

Traffic Prediction-Based Vnf Auto-Scaling And Deployment Mechanism For Flexible And Elastic Service Provision, Bo Yi, Jiacheng Wang, Qiang He, Xingwei Wang, Min Huang, Sajal K. Das, Keqin Li

Computer Science Faculty Research & Creative Works

Network Function Virtualization (NFV) provides a flexible way to provision new services by decoupling network functions from hardware and implementing them as Virtual Network Functions (VNFs). However, the rapid development of technologies greatly promotes the explosion of diverse services, which directly results in the exponential increase of heterogeneous traffic. In addition, such a tremendous amount of heterogeneous traffic will generate bursts in a more dynamic and unexpected manner, so it becomes extremely hard to satisfy the customer demands. Aiming at addressing these challenges, this work proposes a positive and elastic VNF deployment mechanism for service provisioning, which introduces three novelties: …

L3geocast: Enabling P4-Based Customizable Network-Layer Geocast At The Network Edge, Xindi Hou, Shuai Gao, Ningchun Liu, Fangtao Yao, Hongke Zhang, Sajal K. Das

Computer Science Faculty Research & Creative Works

Geocast is a one-to-many communication paradigm that enables the transmission of data packets to a designated area rather than an IP address. The most common geocast solutions rely on the application-layer Geolocation-to-IP database. But these IP-based approaches cannot cope with the challenges of flexibility and mobility in a granularity-customizable geocast scenario. While some non-IP network-layer (L3) attempts have resulted in low addressing accuracy and poor routing scalability. Besides, the clean-slate design is incompatible with the existing network. To address these issues, this article proposes an innovative network-layer geographic addressing scheme that leverages P4-based Software Defined Networks (SDN) to enable flexible …

Learning Social Fairness Preferences From Non-Expert Stakeholder Opinions In Kidney Placement, Mukund Telukunta, Sukruth Rao, Gabriella Stickney, Venkata Sriram Siddardh Nadendla, Casey I. Canfield

Computer Science Faculty Research & Creative Works

Modern kidney placement incorporates several intelligent recommendation systems which exhibit social discrimination due to biases inherited from training data. Although initial attempts were made in the literature to study algorithmic fairness in kidney placement, these methods replace true outcomes with surgeons' decisions due to the long delays involved in recording such outcomes reliably. However, the replacement of true outcomes with surgeons' decisions disregards expert stakeholders' biases as well as social opinions of other stakeholders who do not possess medical expertise. This paper alleviates the latter concern and designs a novel fairness feedback survey to evaluate an acceptance rate predictor (ARP) …

Disseminating Over-The-Air Updates Via Intelligent Labeling In Multi-Tier Networks, Atefeh Asayesh, Asad Waqar Malik, Sajal K. Das

Computer Science Faculty Research & Creative Works

Connected Vehicles Rely on Sophisticated Software Systems for Diverse Features, Including Navigation, Entertainment, Communication, and Safety Functions. as Technology Continues to Advance, the Reliance on Software in Connected Vehicles Becomes Increasingly Integral to their overall Performance and the Delivery of Innovative Features. Therefore, in the Domain of Software-Enabled Automobiles, the Implementation of over-The-Air (OTA) Software Updates is Deemed Essential for the Dissemination of Software and Fixes in Connected Vehicles. the Conventional Method of Addressing This Matter Entailed Manufacturers Undertaking the Task of Recalling Outdated Vehicles; However, the Central Issue Lies in the Considerable Challenge of Effectively Notifying Owners through Recall …

Deep Learning For Uav Detection And Classification Via Radio Frequency Signal Analysis, Prajoy Podder, Maciej Zawodniok, Sanjay Madria

Electrical and Computer Engineering Faculty Research & Creative Works

Unmanned Aerial Vehicles (UAVs) are advertised as great tool that benefits society and humanity. However, UAVs also pose significant security threats ranging from privacy invasions, to interfering with commercial aircraft landing and takeoff, to accidently crashing into vehicles or people, to military or terrorist attacks. Consequently, there is a pressing need to detect and identify UAVs to mitigate such potential risks. While image-based methods are crucial for UAV detection, radio frequency (RF) emissions offer additional valuable insights. Analyzing RF signals, such as those used in UAV-ground station communications, can provide information about UAV types based on distinct frequency usage or …

Programming By Voice, Sadia Nowrin

Dissertations, Master's Theses and Master's Reports

Programmers typically rely on a keyboard and mouse for input, which poses significant challenges for individuals with motor impairments, limiting their ability
to effectively input programs. Voice-based programming offers a promising alternative,
enabling a more inclusive and accessible programming environment. Insights from interviews with motor-impaired programmers revealed that memorizing unnatural commands in existing voice-based programming systems led to frustration. In this work, we explore how programmers naturally speak a single line of code and present a comprehensive methodology for a voice programming system aimed at making programming more accessible for diverse users. To achieve this, we adopted a two-step pipeline. …

The Impact Of Eye-Tracking On Mixed Reality Typing, Cecilia Schmitz

Dissertations, Master's Theses and Master's Reports

Accuracy and speed are pivotal when typing. We hypothesized that the lack of tactile feedback on midair mixed reality keyboards may adversely impact typing performance, especially when ten fingers are used to type. We examined the differences in performance when participants typed on a virtual keyboard using just their index fingers versus all ten fingers. The keyboard was deterministic (without auto-correct), relied only on the headset's egocentric cameras for sensing, and included symbol keys. We used a novel eye-tracking technique to mitigate accidental key presses. The technique was successful at reducing error rates, though participants still typed faster using their …

การใช้เหมืองกระบวนการข้อมูลแบบหลายชั้นสำหรับเพื่อวิเคราะห์วิถีการรักษาพยาบาลของผู้ป่วยโรคเบาหวาน, Kantapat Chaichareenon

Chulalongkorn University Theses and Dissertations (Chula ETD)

This study addresses the challenge of chronic diseases like diabetes, requiring ongoing care. It aims to visualize revisit intervals affecting patient treatment using multi-level process mining and machine learning to identify factors causing missed appointments. Our research shows that patients with improvements have shorter revisit intervals than those deteriorating, with a P-value of 3.83x10%. A significant challenge is the high number of no-shows. Using PyCaret to compare 14 models, we found that the historical attendance of individual patients is a crucial factor in predicting no-shows, with an AUC score of 0.80 using the Gradient Boosting Clas-sifier. Our analysis suggests that …

Deep Learning-Based For Epileptogenic Zone Detection In 18f-Fdg Pet Imaging For Drug-Resistant Epilepsy, Peerawat Wattanachareekul

Chulalongkorn University Theses and Dissertations (Chula ETD)

-

Neural Additive Models For Predicting Her2 Status In Breast Cancer From Immunohistochemical Images, Surayuth Pintawong

Chulalongkorn University Theses and Dissertations (Chula ETD)

This study investigated the application of Conformal Prediction (CP) for uncertainty quantifica- tion in Human Epidermal growth factor receptor 2 (HER2) status classification from immunohistochemistry (IHC) images of breast cancer. Although existing machine learning approaches demonstrate high accuracy in predicting HER2 status, they often struggle with borderline cases that require additional testing. We addressed this challenge by implementing a CP framework that generates prediction sets with controlled error rates. Unlike traditional classifiers that provide single predictions, our CP framework can output either singleton predictions for confident cases or multiple labels for uncertain cases, thereby naturally identifying samples that require additional …

Improved Sequence Embeddings For Peptide-Class I Mhc Binding Prediction, Patiphan Wongklaew

Chulalongkorn University Theses and Dissertations (Chula ETD)

The binding of a peptide antigen to a class I major histocompatibility complex (MHC) protein is considered an essential process by which the immune system monitors infected cells. This mechanism has facilitated the development of peptide-based vaccines aimed at stimulating the patient's immune response for cancer treat-ment. Accurate prediction of peptide-MHC binding is therefore crucial for prioritizing optimal peptides tailored to individual patients. Nevertheless, many MHC alleles lack sufficient experimental data on peptide-MHC binding, which potentially constrains the accuracy of existing prediction models. This study introduces an enhanced iteration of MHCSeqNet, an open-source deep learning model which utilizes sequence data …

Improving Thai-Dialect Automatic Speech Recognition With Curriculum Learning, Artit Suwanbandit

Chulalongkorn University Theses and Dissertations (Chula ETD)

Automatic Speech Recognition (ASR) has been the foremost feature and integrated in many real-world usages for decades. The novel deep learning approaches prevail in the ASR field as a model architecture. However, ASR still struggles with low-resource data, especially in the Thai dialectal language. Transfer learning is the conventional approach in the machine learning field for escalating the performance of low-resource settings. In the scenario that additional fine-tuning tasks are not achievable, exerting all efficiency of target data is an accountability. To overcome stagnation, we proposed transfer-based curriculum learning for low-resource dialectal ASR, Phonemetically-induced subword Out-of-vocabulary rate (PhIS-OOV), and Model …

Grammatical Error Correction In Thai Sentences For Deaf Students, Supachan Traitruengsakul

Chulalongkorn University Theses and Dissertations (Chula ETD)

Deaf students encounter challenges in written communication due to errors such as insertion, deletion, disorder, misusage, and misspellings. Grammatical error correction (GEC) technology can help mitigate these issues. However, existing GEC models are primarily trained on online resources from second-language hearing learners. In contrast, sentences written by deaf students suffer from a variety of errors not typically found elsewhere. To address this issue, we create the Thai Deaf Corpus (TDC), focusing on identifying and analyzing errors among deaf students in grades 7-12 across four deaf schools. Additionally, we introduce a two-stage system for the Thai-GEC model, automatically detecting and correcting …