Artificial Intelligence and Robotics Commons^™

Charting A Path To The Quintuple Aim: Harnessing Ai To Address Social Determinants Of Health, Yash Shah, Zachary Goldberg, Erika Harness, David Nash

College of Population Health Faculty Papers

The Quintuple Aim seeks to improve healthcare by addressing social determinants of health (SDOHs), which are responsible for 70-80% of medical outcomes. SDOH-related concerns have traditionally been addressed through referrals to social workers and community-based organizations (CBOs), but these pathways have had limited success in connecting patients with resources. Given that health inequity is expected to cost the United States nearly USD 300 billion by 2050, new artificial intelligence (AI) technology may aid providers in addressing SDOH. In this commentary, we present our experience with using ChatGPT to obtain SDOH management recommendations for archetypal patients in Philadelphia, PA. ChatGPT identified …

Try It Together - Qualitative Coding With Atlas.Ti, Danping Dong, Bryan Leow

2024 AI for Research Week

This hands-on session introduces Atlas.ti, a well-established qualitative data analysis tool for analyzing your transcripts and textual data. The session will cover coding data, extracting insights, creating visualizations, and exploring the tool's latest AI features.

Try It Together: Transcribing Your Audio With Whisper Api, Bella Ratmelia

2024 AI for Research Week

In this hands-on session, we will explore using the Whisper API to transcribe audio recordings from interviews, focus groups, and speeches. The session will delve into best practices and address common issues that may arise during the transcription process.

Customization Of Large Language Models For Causal Inference And Data Quality, Xingqiao Wang

Theses and Dissertations

In the burgeoning fields of artificial intelligence (AI) and natural language processing (NLP), Large Language Models (LLMs) have emerged as powerful tools for understanding complex textual data. This dissertation focuses on the novel customization of LLMs for enhancing causal inference in pharmacovigilance and improving entity matching for data quality—two critical challenges in healthcare analytics and data management. Through an in-depth exploration of encoder and decoder LLMs, this study illustrates how domain-specific customization can significantly advance the processing and interpretation of textual information. For pharmacovigilance, it demonstrates how tailored LLMs can extract causal relationships from adverse event reports, offering a new …

Singleadv: Single-Class Target-Specific Attack Against Interpretable Deep Learning Systems, Eldor Abdukhamidov, Mohammed Abuhamad, George K. Thiruvathukal, Hyoungshick Kim, Tamer Abuhmed

Computer Science: Faculty Publications and Other Works

In this paper, we present a novel Single-class target-specific Adversarial attack called SingleADV. The goal of SingleADV is to generate a universal perturbation that deceives the target model into confusing a specific category of objects with a target category while ensuring highly relevant and accurate interpretations. The universal perturbation is stochastically and iteratively optimized by minimizing the adversarial loss that is designed to consider both the classifier and interpreter costs in targeted and non-targeted categories. In this optimization framework, ruled by the first- and second-moment estimations, the desired loss surface promotes high confidence and interpretation score of adversarial samples. By …

Detecting Drifts In Data Streams Using Kullback-Leibler (Kl) Divergence Measure For Data Engineering Applications, Jeomoan Francis Kurian, Mohamed Allali

Engineering Faculty Articles and Research

The exponential growth of data coupled with the widespread application of artificial intelligence(AI) presents organizations with challenges in upholding data accuracy, especially within data engineering functions. While the Extraction, Transformation, and Loading process addresses error-free data ingestion, validating the content within data streams remains a challenge. Prompt detection and remediation of data issues are crucial, especially in automated analytical environments driven by AI. To address these issues, this study focuses on detecting drifts in data distributions and divergence within data fields processed from different sample populations. Using a hypothetical banking scenario, we illustrate the impact of data drift on automated …

Automatic Measurement Of Dialogue Engagingness In Multilingual Settings, Amila Ferron

Dissertations and Theses

Expansive use of large language models (LLMs) as dialogue systems brings increased importance to the evaluation of the responses they generate. Although evaluation of qualities such as coherence and fluency are readily possible with well-established automatic metrics, engagingness is often measured with human evaluation -- a process that can be costly and slows the pace of development. Existing automatic metrics for engagingness have low to moderate correlation with human annotations, evaluate the response without the conversation history, are complicated to implement, or are designed for a specific dataset. Moreover, they have been tested exclusively on English conversations. Given that dialogue …

Academic Search And Discovery Tools In The Age Of Ai And Large Language Models: An Overview Of The Space, Aaron Tay

2024 AI for Research Week

In the ever-evolving landscape of academic research, “AI tools” for literature search and synthesis are currently getting a lot of attention. These tools promise to ramp up productivity, enabling us to accomplish more in less time or absorb more knowledge without drowning in endless reading. With the sheer number of these systems increasing daily, it's natural to wonder: are they really worth our time and money? And if they are, how should we go about picking the right one from the multitude of options?

In this talk, I will share my views on how the space has developed over two …

Queering Futures With Data-Driven Speculation: The Design Of An Expanded Mixed Methods Research Framework Integrating Quantitative, Qualitative, And Practice-Based Modes, Jess Parris Westbrook

College of Education Theses and Dissertations

Queering’ questions, unlearns, disrupts, and transforms approaches, expectations, and realities. Futures are time and change. The approach I have designed to operationalize Queering and futures, or Queering futures, is the Queering Futures Framework (QFF). The Queering Futures Framework (QFF) is a brand-new transdisciplinary research framework intersecting values, positionality, complexity, Queerness themes, and futures praxis. This framework expands traditional mixed methods research conventions by integrating quantitative, qualitative, and practice-based research modes and mindsets. The Queering Futures Framework (QFF) prototype presented in this dissertation functions as a test case and proof of concept. The prototype quantitative mode measures attitudes towards AI, and …

Context Aware Music Recommendation And Playlist Generation, Elias Mann

SMU Journal of Undergraduate Research

There are many reasons people listen to music, and the type of music is largely determined by what the listener may be doing while they listen. For example, one may listen to one type of music while commuting, another while exercising, and yet another while relaxing. Without access to the physiological state of the user, current music recommendation methods rely on collaborative filtering - recommending music based on what other similar users listen to - and content based filtering - recommending songs based on their similarities to songs the user already prefers. With the rise in popularity of smart devices …

Helping The Home Cook: How Unsupervised Machine Learning Can Prevent Food Waste, Ryan B. Watson

Honors Projects

A common problem for the home cook is having too much of one food ingredient leftover, then not knowing what to do with it. To alleviate this problem, I propose using an unsupervised machine learning model to recommend recipes based on what ingredients the home cook wants to use. This model is built with FastText and trained on the recipe ingredients in the RecipeNLG dataset. Recipes are recommended based on which recipe ingredient set is most similar to the recipe ingredients provided in the user input. This solution will reduce consumer food waste by giving the home cook the information …

Making The Most Of Artificial Intelligence And Large Language Models: A Novel Approach For Book Recommendation And Discovery In Medical Libraries, Ivan Portillo, David Carson

Library Presentations, Posters, and Audiovisual Materials

This poster presentation evaluates the use of Artificial Intelligence and large language models (LLMs) to assist health science libraries in recommending and discovering book titles as part of their collection development. Using pre-determined prompts, the researchers evaluated ChatGPT 4.0, Bing Chat, and Google Bard as recommender systems for book discovery and ranking existing titles.

Supporting South Korea’S Aging Population: How Ai And Iot Acceptance Connects The Young And Old, Bobby Im

Master's Projects and Capstones

In 2024, South Korea surpassed every other nation by becoming the country with the lowest fertility rate (below 0.7%). Population decline will hinder future ability to care for their aging population and although the government and private corporations are investing millions of dollars on developing Artificial Intelligence-Internet of Things (AI-IoT) devices to support the aging, the acceptance levels and the amount of family support required is undervalued. By examining AI-IoT’s current use and role in South Korea’s public health system this paper shows how intergenerational support helps optimize existing procedures and equipment, increases the level of acceptance and use, and …

Fusing Classic Motion Energy Models And Deep Learning For Coarse-To-Fine Moving Object Segmentation, Matthias Tangemann, Matthias Kümmerer, Matthias Bethge

MODVIS Workshop

Classic motion energy models are able to predict a wide range of physiological and behavioral aspects of motion perception in humans. Whether these models can be used as a basis for higher-level tasks, such as moving object segmentation, has however hardly been explored yet. Here, we present a model that combines a motion energy representation with recent computer vision approaches for figure-ground segmentation of naturalistic stimuli. We find that unlike established motion segmentation models but similar to humans, our model generalizes to random-dot stimuli when only trained on RGB videos.

Missing Wedge Completion Via Unsupervised Learning With Coordinate Networks, Dave Van Veen, Jesús G Galaz-Montoya, Liyue Shen, Philip Baldwin, Akshay S Chaudhari, Dmitry Lyumkis, Michael F Schmid, Wah Chiu, John Pauly

Faculty, Staff and Students Publications

Cryogenic electron tomography (cryoET) is a powerful tool in structural biology, enabling detailed 3D imaging of biological specimens at a resolution of nanometers. Despite its potential, cryoET faces challenges such as the missing wedge problem, which limits reconstruction quality due to incomplete data collection angles. Recently, supervised deep learning methods leveraging convolutional neural networks (CNNs) have considerably addressed this issue; however, their pretraining requirements render them susceptible to inaccuracies and artifacts, particularly when representative training data is scarce. To overcome these limitations, we introduce a proof-of-concept unsupervised learning approach using coordinate networks (CNs) that optimizes network weights directly against input …

Dense Video Description Method Based On Multi-Modal Fusion In Transformer Network, Xiang Li, Haifeng Sang

Journal of System Simulation

Abstract: In order to solve the problems that most of the current dense video description models use twostage methods, which have low efficiency, ignore audio and semantic information, and have incomplete description results, a multi-modal and semantic information fusion dense video description method was proposed. An adaptive R(2+1)D network was proposed to extract visual features, a semantic detector was designed to generate semantic information, audio features were added to supplement it, a multi-scale deformable attention module was established, and a parallel prediction head was applied to accelerate the convergence rate and improve the accuracy of the model. The experimental results …

Research On Simulation Model Of Double-Layer Expansion Design Of Expressway, Jiandong Qiu, Yi Tang, Yuxiong Ji, Heng Liu, Junsha Luo

Journal of System Simulation

Abstract: Aiming at the problems that the traditional traffic simulation technology has insufficient evaluation accuracy and little application effect in the three-dimensional composite expansion scenario of expressway, a simulation model construction method for double-layer expansion design of expressway was proposed. The reconstruction and expansion project of Shenzhen Jihe Expressway is selected as the research object, the three simulation model modeling elements, including road network facilities, traffic demand data, and driving behavior model parameters, are sorted out, and the technical process of simulation modeling is proposed. The whole road network including key infrastructure such as interchange, toll station, ramp up and …

A Graph Neural Network Visual Slam Algorithm For Large-Angle View Motion, Jinhui Liu, Mengyuan Chen, Pengpeng Han, Hebao Chen, Yukun Zhang

Journal of System Simulation

Abstract: Aimed at the difficulty of feature point extraction in mobile robots with drastic changes in illumination or sparse texture scenes under large-angle view motion, difficulty in matching features at extreme angles leads to large errors in Epipolar Geometry calculations, a fusion of an improved graph neural network based visual SLAM algorithm (GNN-SLAM) is proposed. The priori location estimation feature extraction network is proposed to achieve fast and uniform detection and description of image feature points by a priori location estimation and to construct real and accurate feature point information. The graph attention mechanism feature matching network is proposed to …

Implementation And Numerical Simulation On Object-Oriented Elastic-Plastic Finite Element Method Based On Python, Henghui Li, Yingxiong Xiao

Journal of System Simulation

Abstract: With the continuous expansion of the application fields of finite element methods, higher requirements are put forward for the scalability of finite element methods. In order to overcome the defects of the traditional finite element methods, a simple and easily extensible object-oriented elasticplastic finite element program framework is proposed based on Python. Combined with the characteristics of Python, we design some finite element classes such as the pre-processing class, the post-processing class, the linear solution class, the stress integration class and the analysis class. By applying the resulting framework to several typical elastic-plastic mechanical problems and comparing the results …

Optimization Of Highway Emergency Lane Control Based On Kriging Genetic Algorithm, Jinjun Tang, Lipeng Hu, Mingyang Li, Xuan Zhang

Journal of System Simulation

Abstract: To address the issue of how to effectively improve the highway operational efficiency and reduce the safety risks under different traffic flow conditions, this study proposed a genetic algorithm based on Kriging agent model is proposed to optimize the emergency lane control strategy. A mathematical optimization model is designed by combining the spatial and temporal characteristics of the emergency lane opening strategy. By introducing Kriging agent model, combining the genetic algorithm to build the optimization framework, and using simulation software to obtain data to train the agent model, the problem of minimizing the total travel time and the total …

Research On Forest Fire Spread Simulation System Based On Osg, Lei Shao, Xiaotian Yan, Jian Liu, Yuming Liu

Journal of System Simulation

Abstract: A novel expended lattice structure of DEM-Cell model incorporating DEM elevation information is proposed, in response to the requirements of extrapolation of trends and hazards of forest fire spread, as well as the need of route selection and real-time path optimization for rescuers. Combining vegetation attributes of meta cells with geographic elevation information, we develop a simulation and fire fighting exercise system that computing the resultant data in real time and converting it into renderable resource, which is directly used by the OSG engines. With the help of the same data structure and the corresponding key algorithms and technologies, …

Hierarchical Guided Enhanced Multi-Objective Firefly Algorithm, Jia Zhao, Zhizhen Lai, Runxiu Wu, Zhihua Cui, Hui Wang

Journal of System Simulation

Abstract: The multi-objective firefly algorithm is easy to produce oscillation and aggregation phenomenon in the solution process, which leads to weak development ability and poor solution accuracy. This paper proposes a hierarchical guided enhanced multi-objective firefly algorithm (HGEMOFA). HGEMOFA builds a hierarchical guidance model, uses non-dominated sorting to obtain different levels of individuals. The individuals in the dominant layer are used to guide the evolution of the individuals in the inferior layer, the guidance direction is clear, the oscillation in the evolution process is solved, the aggregation phenomenon is reduced, and the convergence of the algorithm is enhanced. The Lévy …

Research On Path Planning Of Warehouse Robot With Improved Harris Hawks Algorithm, Xu Lei, Jingyi Chen, Xiaoyang Chen

Journal of System Simulation

Abstract: To improve the path planning efficiency of warehouse mobile robots in static environments, and to solve the problems of slow convergence and local optimum of traditional Harris Hawk (HHO) algorithm in path planning, a Harris Hawk optimization algorithm based on Tent chaotic mapping fused with Cauchy's back-learning variant (TCLHHO) is proposed. The population diversity is increased by Tent Chaotic mapping to speed up convergence. An exponential prey escape energy updating strategy is proposed to balance the global search and local exploitation capabilities of the algorithm. The optimal individual is disturbed by Cauchy mutation operator and inverse learning strategy to …

Image Self-Enhancement De-Hazing Algorithm Combined With Generative Adversarial Network, Wanjun Liu, Yuqian Cheng, Haicheng Qu

Journal of System Simulation

Abstract: To solve the problem that existing dehazing models are prone to over fitting after training with synthetic hazy image data sets, an image self-enhancement dehazing algorithm is proposed in combination with generative adversarial network. The depth information of an image is estimated while combining two Generative Adversarial Networks. The first GAN uses a clear image to learn the process of image hazing, and then adopts the hazed image generated by it as the input of the second GAN to guide the second GAN to correct dehazing. In order to reduce the difference before and after image processing, the consistency …

Cooperative And Optimal Control Of Multiple Mimo Objects Under Information Sharing, Jiong Shao, Xinchun Jie, Meng Wu

Journal of System Simulation

Abstract: Aiming at the problems of low cooperative efficiency and slow convergence of control algorithm for multiple MIMO objects in cyber-physical system (CPS), a cooperative optimization control strategy for multiple MIMO objects under the condition of information sharing is proposed. A new network control system structure with only physical layer and information layer is used to realize real-time sharing of state variables, control and detection information of multiple MIMO objects. Under the condition of information sharing, based on the performance indexes assigned by CPS and the physical constraints between each object, the cooperative controller designed by minimum principle realizes the …

Research On Collaborative Optimization Method Of Multi-Uav Task Allocation And Path Planning, Peng Xiao, Feng Xie, Haihong Ni, Min Zhang, Zhili Tang, Ni Li

Journal of System Simulation

Abstract: Aiming at the task requirements of multi-UAV to perform multi-target collaborative reconnaissance, a collaborative optimization method of multi-machine and multi-objective task allocation and path planning is proposed. Based on the partheno genetic algorithms (PGA), a cost function combined with the actual path cost is constructed through the Dubins curve. To further reduce the calculation cost, a clustering algorithm based on UAV detection distance is proposed, and the generated clustering point is used as a new waypoint of UAV. The simulation results show that considering the dangerous area and the large number of reconnaissance points, the algorithm can effectively complete …

Tri-Training Algorithm Based On Density Peaks Clustering, Yuhang Luo, Runxiu Wu, Zhihua Cui, Yiying Zhang, Yeshen He, Jia Zhao

Journal of System Simulation

Abstract: Tri-training can effectively improve the generalization ability of classifiers by using unlabeled data for classification, but it is prone to mislabeling unlabeled data, thus forming training noise. Tritraining (Tri-training with density peaks clustering, DPC-TT) algorithm based on density peaks clustering is proposed. The DPC-TT algorithm uses the density peaks clustering algorithm to obtain the class cluster centers and local densities of the training data, and the samples within the truncation distance of the class cluster centers are identified as the samples with better spatial structure, and these samples are labeled as the core data, and the classifier is updated …

Deep Learning Based Local Path Planning Method For Moving Robots, Zesen Liu, Sheng Bi, Chuanhong Guo, Yankui Wang, Min Dong

Journal of System Simulation

Abstract: In order to integrate visual information into the robot navigation process, improve the robot's recognition rate of various types of obstacles, and reduce the occurrence of dangerous events, a local path planning network based on two-dimensional CNN and LSTM is designed, and a local path planning approach based on deep learning is proposed. The network uses the image from camera and the global path to generate the current steering angle required for obstacle avoidance and navigation. A simulated indoor scene is built for training and validating the network. A path evaluation method that uses the total length and the …

Path Planning Of Unmanned Delivery Vehicle Based On Improved Q-Learning Algorithm, Xiaokang Wang, Jie Ji, Yang Liu, Qing He

Journal of System Simulation

Abstract: To solve the traditional Q-learning algorithm for unmanned vehicle path planning suffers from the problems of low planning efficiency and slow convergence speed, for this reason, a path planning algorithm for unmanned delivery vehicles based on the improved Q-learning algorithm is proposed. Learning from the energy iteration principle of the simulated annealing algorithm, adjusts the greedy factor ε to make it change dynamically during the training process, so as to balance the relationship between exploration and utilization, and thus improve the planning efficiency. The reward value in the reward mechanism is changed from a discrete value to a continuous …

Research On Simulation Methods For Forest Fire Extinguishing Using Water Mist, Bing Xiang, Xiaohong Dong, Yang Li

Journal of System Simulation

Abstract: As a highly hazardous natural disaster, the occurrence and spread of forest fires are usually affected by a variety of complex factors such as climate, terrain, vegetation, combustible materials, etc., which makes it difficult to accurately simulate the spread and extinguishing process of forest fires. The spread of forest fires and the process of water mist fire extinguishing are physically modele. The spread model adopts a tree module structure to simulate the pyrolysis reaction of tree burning, and considers the effects of temperature, wind field,mass loss rate and other factors on the spread of tree burning.In the fire extinguishing …