Artificial Intelligence and Robotics Commons^™

Diffusion Of Ai Governance, Langtao Chen, Brenda Eschenbrenner, Fiona Fui-Hoon Nah, Keng Siau, Yuzhou Qian

Research Collection School Of Computing and Information Systems

Artificial intelligence (AI) has the potential to address social, economic, and environmental challenges. However, effective use of AI in organizations relies on the establishment of an AI governance framework. Although existing studies have discussed a variety of issues raised by AI-based systems and proposed AI governance frameworks to overcome those issues, organizations face challenges in adopting AI governance. Informed by innovation diffusion theory, this research evaluates the impact of internal and external influences on AI governance adoption between highly regulated and less regulated industries. We also assess the effect of adopting AI governance on organizational performance. Findings from this study …

Feasibility Studies In Indoor Localization Through Intelligent Conversation, Sheshadri Smitha, Linus Cheng, Kotaro Hara

Research Collection School Of Computing and Information Systems

We propose a model to achieve human localization in indoor environments through intelligent conversation between users and an agent. We investigated the feasibility of conversational localization by conducting two studies. First, we conducted a Wizard-of-Oz study with N = 7 participants and studied the feasibility of localizing users through conversation. We identified challenges posed by users’ language and behavior. Second, we collected N = 800 user descriptions of virtual indoor locations from N = 80 Amazon Mechanical Turk participants to analyze user language. We explored the effects of conversational agent behavior and observed that people describe indoor locations differently based …

Hierarchical Value Decomposition For Effective On-Demand Ride Pooling, Hao Jiang, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

On-demand ride-pooling (e.g., UberPool, GrabShare) services focus on serving multiple different customer requests using each vehicle, i.e., an empty or partially filled vehicle can be assigned requests from different passengers with different origins and destinations. On the other hand, in Taxi on Demand (ToD) services (e.g., UberX), one vehicle is assigned to only one request at a time. On-demand ride pooling is not only beneficial to customers (lower cost), drivers (higher revenue per trip) and aggregation companies (higher revenue), but is also of crucial importance to the environment as it reduces the number of vehicles required on the roads. Since …

Supervised Representation Learning For Improving Prediction Performance In Medical Decision Support Applications, Phawis Thammasorn

Graduate Theses and Dissertations

Machine learning approaches for prediction play an integral role in modern-day decision supports system. An integral part of the process is extracting interest variables or features to describe the input data. Then, the variables are utilized for training machine-learning algorithms to map from the variables to the target output. After the training, the model is validated with either validation or testing data before making predictions with a new dataset. Despite the straightforward workflow, the process relies heavily on good feature representation of data. Engineering suitable representation eases the subsequent actions and copes with many practical issues that potentially prevent the …

Radiomic Features To Predict Overall Survival Time For Patients With Glioblastoma Brain Tumors Based On Machine Learning And Deep Learning Methods, Lina Chato

UNLV Theses, Dissertations, Professional Papers, and Capstones

Machine Learning (ML) methods including Deep Learning (DL) Methods have been employed in the medical field to improve diagnosis process and patient’s prognosis outcomes. Glioblastoma multiforme is an extremely aggressive Glioma brain tumor that has a poor survival rate. Understanding the behavior of the Glioblastoma brain tumor is still uncertain and some factors are still unrecognized. In fact, the tumor behavior is important to decide a proper treatment plan and to improve a patient’s health. The aim of this dissertation is to develop a Computer-Aided-Diagnosis system (CADiag) based on ML/DL methods to automatically estimate the Overall Survival Time (OST) for …

Lexglue: A Benchmark Dataset For Legal Language Understanding In English, Ilias Chalkidis, Abhik Jana, Dirk Hartung, Michael Bommarito, Ion Androutsopoulos, Daniel Katz, Nikolaos Aletras

Research Collection Yong Pung How School Of Law

Lawsandtheirinterpretations, legal arguments and agreements are typically expressed in writing, leading to the production of vast corpora of legal text. Their analysis, which is at the center of legal practice, becomes increasingly elaborate as these collections grow in size. Natural language understanding (NLU) technologies can be a valuable tool to support legal practitioners in these endeavors. Their usefulness, however, largely depends on whether current state-of-the-art models can generalize across various tasks in the legal domain. To answer this currently open question, we introduce the Legal General Language Understanding Evaluation (LexGLUE) benchmark, a collection of datasets for evaluating model performance across …

Robust And Fair Machine Learning Under Distribution Shift, Wei Du

Graduate Theses and Dissertations

Machine learning algorithms have been widely used in real world applications. The development of these techniques has brought huge benefits for many AI-related tasks, such as natural language processing, image classification, video analysis, and so forth. In traditional machine learning algorithms, we usually assume that the training data and test data are independently and identically distributed (iid), indicating that the model learned from the training data can be well applied to the test data with good prediction performance. However, this assumption is quite restrictive because the distribution shift can exist from the training data to the test data in many …

Data-Driven Models For Remaining Useful Life Estimation Of Aircraft Engines And Hard Disk Drives, Austin Coursey

Honors College Theses

Failure of physical devices can cause inconvenience, loss of money, and sometimes even deaths. To improve the reliability of these devices, we need to know the remaining useful life (RUL) of a device at a given point in time. Data-driven approaches use data from a physical device to build a model that can estimate the RUL. They have shown great performance and are often simpler than traditional model-based approaches. Typical statistical and machine learning approaches are often not suited for sequential data prediction. Recurrent Neural Networks are designed to work with sequential data but suffer from the vanishing gradient problem …

Using Machine Learning To Recognize Chronic Rhinosinusitis, Irene Liu '23

Student Publications & Research

Chronic Rhinosinusitis (CRS) is a nasal disease characterized by the inflammation of the mucosa and paranasal sinuses with a duration of at least 12 consecutive weeks. So, to diagnose CRS, one needs to keep a record of their symptoms for ~12 weeks before they are recommended to get a tomography which will allow physicians to classify them as a patient with CRS or without. This is a timely and costly process; thus, machine learning should be used to speed the process up. Since patients with CRS have more obstructed noses, the sound produced should be different than an individual without …

Identification Of Return-Oriented Programming Attacks Using Risc-V Instruction Trace Data, Daniel F. Koranek, Scott R. Graham, Brett J. Borghetti, Wayne C. Henry

Faculty Publications

An increasing number of embedded systems include dedicated neural hardware. To benefit from this specialized hardware, deep learning techniques to discover malware on embedded systems are needed. This effort evaluated candidate machine learning detection techniques for distinguishing exploited from non-exploited RISC-V program behavior using execution traces. We first developed a dataset of execution traces containing Return Oriented Programming (ROP) exploitation on the RISC-V Instruction Set Architecture (ISA) and then developed several deep learning bidirectional Long Short-Term Memory (LSTM) models capable of distinguishing exploited traces from non-exploited traces, each using subsets of features from the execution traces. An objective of this …

Self-Supervised Video Object Segmentation Via Cutout Prediction And Tagging, Jyoti Kini, Fahad Shahbaz Khan, Salman Khan, Mubarak Shah

Computer Vision Faculty Publications

We propose a novel self-supervised Video Object Segmentation (VOS) approach that strives to achieve better object-background discriminability for accurate object segmentation. Distinct from previous self-supervised VOS methods, our approach is based on a discriminative learning loss formulation that takes into account both object and background information to ensure object-background discriminability, rather than using only object appearance. The discriminative learning loss comprises cutout-based reconstruction (cutout region represents part of a frame, whose pixels are replaced with some constant values) and tag prediction loss terms. The cutout-based reconstruction term utilizes a simple cutout scheme to learn the pixel-wise correspondence between the current …

Data-Driven Design And Analysis Of Next Generation Mobile Networks For Anomaly Detection And Signal Classification With Fast, Robust And Light Machine Learning, Muhammed Furkan Küçük

USF Tampa Graduate Theses and Dissertations

This research focuses on machine (and deep) learning applications (including clustering,anomaly detection and signal classification) for self-organizing and next generation mobile networks in wireless communications. Specifically, this dissertation document will address the three different topics.

First, in the study titled “Performance analysis of neural network topologies and hyperparameters for deep clustering”, we explore the relationship between the clustering performance and network complexity. Deep learning found its initial footing in supervised applications such as image and voice recognition successes of which were followed by deep generative models across similar domains. In recent years, researchers have proposed creative learning representations to utilize …

Study On Near-Body Pressure Characteristics Of Bionic Robotic Fish Undulating In Near Wall Region, Ou Xie, Aiguo Song, Qixin Zhu

Journal of System Simulation

Abstract: To avoid unbalanced workload assignment, we studied the vehicle routing problem with refined oil secondary distribution considering workload balance. A bi-objectivemixed integer programming model was built to minimize the total distribution cost and the maximum difference in vehicle route length. A heuristic variable neighborhood tabu search algorithm was designed. An improved Solomon_I1 insertion algorithm was developed to generate afeasible initial solution such that the total distribution cost was as small as possible. Then, the variable neighborhood tabu search algorithm was used to improve the initial solution and thereby obtain the approximate optimal solution. The simulation results show that in …

Multi-Modality Affective Computing Model Based On Personality And Memory Mechanism, Sijin Zhou, Dicheng Chen, Geng Tu, Dazhi Jiang

Journal of System Simulation

Abstract: With the development of affective computing, the correlation of memory, individuation and emotion is more and more important. Focus on the machine emotion shortcomings in the perception, understanding and expression, an emotion computing model integrating the emotion perception, understanding and expression is proposed. The model is a memory-oriented deep network perception model that accepts multiple modal inputs (visual, auditory, lexical) and applies a fuzzy emotion integration decision to realize the understanding of uncertain emotions. The simulation experiments prove that the model has a good performance in all kinds of multimodal affective computing.

Virtual Scene Stereoscopic Panorama Generation And Viewport Rendering Algorithm, Haoxiang Li, Chunyi Chen, Xiaojuan Hu, Yunbiao Liu, Qiwei Xing

Journal of System Simulation

Abstract: Aiming at the nonuniform sampling in map projection and the redundancy in aspheric projection, spherical Fibonacci lattices is used to sample the visible spherical area to generate spherical Fibonacci lattice panorama with low-redundancy and high-quality. On the basis of panoramic stereo imaging model, the binocular ray direction generation algorithm for spherical stereo panorama is proposed. With Fibonacci grid, an adaptive filtering method of light-visibility map for panorama is designed to generate spherical panorama with approximate soft shadow. The nearest neighbor interpolation is used to render the viewport of panorama. Extensive experiments show that the frame frequency of the viewport …

Simulation On Cold Chain Distribution Path Of Fresh Agricultural Products Under Low-Carbon Constraints, Tao Ning, Tao Gou, Xiangdong Liu

Journal of System Simulation

Abstract: The freshness distribution requirements of fresh agricultural products may increase the carbon emissions of the cold chain distribution process. A cold chain distribution scheduling strategy and simulation method for the fresh agricultural products under low-carbon constraints is proposed. Based on the quantitative analysis of the carbon tax mechanism, a mathematical model of minimizing the carbon emissions and minimizing the overall cost of distribution is established. Comprehensively analyzing the conventional factors such as the product delivery volume, delivery time and loading and unloading time in logistics distribution, an improved quantum ant colony algorithm based on adaptive rotation angle …

Simulation Optimization On Joint Production And Preventive Maintenance Scheduling For Distributed Job-Shop, Fei Ye, Ziqing Li, Yuanjun Laili

Journal of System Simulation

Abstract: Distributed job-shop production scheduling is the key to high efficient production. Preventive maintenance, an essential means to ensure the safety and reliability of equipment, should be the necessary content of the production decision-making. Aiming at the production delay caused by equipment maintenance, a simulation-corrected optimization method is proposed. The mathematical model and simulation model for the joint production and preventive maintenance scheduling are established. The sequence exchange-based genetic algorithm is combined with the simulation-corrected optimization method to form a fast simulation optimization scheme. Experimental results on typical cases show that the proposed simulation optimization method can improve the solution …

Research On Discrete Workshop Task Assignment Based On Improved Water Filling Algorithm, Kaituan Feng, Jie Yuan

Journal of System Simulation

Abstract: Aiming at the unsatisfactory the results of the real-time dynamic task allocation in discrete workshops are not ideal, an improved water filling algorithm is proposed. Compared with the equal cost allocation of the water injection algorithm, the processing rate and cost factors are added to the improved water injection algorithm to coordinate the processing rate, the cost and the workpieces. The allocation of the different cost workpieces is realized and the result is adjusted, which can meet the requirements of discrete distribution. The improved water injection algorithm can dynamically allocate the newly added workpieces in real time. The proposed …

Key Technology Research On Stall Spin Simulation Training System Of An Aircraft, Guangxu Xi, Yongyi Liu, Chong Wu, Junjie Zhang, Yinghao Chen

Journal of System Simulation

Abstract: In order to realize the simulation continuity of the multi-state evolution of traffic and to solve the problem that multi-state traffic can only be simulated by single state traffic through multiple times, the middleware model of continuous traffic event simulation is built by the secondary development interface of VISSIM simulation software, and the original two related traffic simulation events are jointly driven. The secondary development of VISSIM-com is carried out by C# and database. The survey data of the intersection of Ganghua Road and Baihua Road in the Yuzhong District of Chongqing is selected as the example, and the …

Simulation On Mutual Interference Of Laser Radar In Road Environments, Xuesong Mao, Runlong Lei, Shaowei Huang, Xuetao Mao

Journal of System Simulation

Abstract: Transmission line inspection is an important work to ensure the safe operation of the power grid. It involves the live-work, the power-outage-maintenance and the fault-diagnosis. Training using only 3D virtual technology cannot achieve realistic results. It is necessary to combine 3D virtual scenes with digital grids. To this end, using the collected monitoring data and multi-time-scale calculation models, a twin state digital power grid has been constructed for the live-work, a parallel state digital power grid has been constructed for the power-outage-maintenance, and corresponding analog devices have been added to the parallel digital power grid to complete the training …

Learning Enriched Features For Fast Image Restoration And Enhancement, Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, Ling Shao

Computer Vision Faculty Publications

Given a degraded input image, image restoration aims to recover the missing high-quality image content. Numerous applications demand effective image restoration, e.g., computational photography, surveillance, autonomous vehicles, and remote sensing. Significant advances in image restoration have been made in recent years, dominated by convolutional neural networks (CNNs). The widely-used CNN-based methods typically operate either on full-resolution or on progressively low-resolution representations. In the former case, spatial details are preserved but the contextual information cannot be precisely encoded. In the latter case, generated outputs are semantically reliable but spatially less accurate. This paper presents a new architecture with a holistic goal …

Cross-Temporal Snapshot Alignment For Dynamic Multi-Relational Networks, Lvjia Chen, Shangsong Liang

Machine Learning Faculty Publications

A dynamic network is often represented as a sequence of snapshots evolving over time. In certain real-world scenarios, the identities of nodes in snapshots of a dynamic network are unknown and need to be figured out. To deal with such a challenge, recently, the task of cross-temporal snapshot alignment for dynamic networks is proposed, which aims to match equivalent nodes across temporal snapshots of a dynamic network given a small set of identified nodes. However, in many dynamic multi-relational networks like temporal knowledge graphs, the relation type information of edges, which can be useful for the alignment task, is neglected …

Research On Credibility Assessment Of Cloud Simulation System, Wei Li, Huan Zhang, Ping Ma, Ming Yang

Journal of System Simulation

Abstract: The cloud simulation platform supports the "cloud simulation" mode, which can automatically find simulation resources and dynamically build the cloud simulation system. Because the cloud simulation platform has the characteristics of simulation services establishment on demand and multi-granularity resources sharing, the credibility evaluation of the cloud simulation system faces new challenges in the credibility of the simulation resources, the credibility of the simulation subsystems and the reliability of the simulation environment, etc. From the whole life cycle perspective of the cloud simulation system, the credibility evaluation process model and the credibility evaluation index system of the cloud simulation system …

Research On Physical Layer Security Of Full-Duplex Uav Relaying, Shu Ye, Xiaodong Ji, Wenhua Li

Journal of System Simulation

Abstract: Aiming at the physical layer security of a full-duplex UAV relaying system, a novel scheme based on the joint optimization of the transmit power and UAV flight trajectory is proposed. Under the condition of limited transmit power and flight trajectory, a joint optimization that maximizing the average secrecy rate of the system is constructed. The non-concave problem that cannot be solved directly is resolved into two sub-problems of transmit power and flight trajectory optimization, which can be transformed into the concave problem by the successive convex approximation method. An iterative algorithm is proposed to obtain the numerical solution of …

Optimal Operation For Park Integrated Energy System Considering Interruptible Loads, Lixin Ma, Ying Cheng

Journal of System Simulation

Abstract: The operating mode of thermal power generation units has certain limitations in peak shaving capacity. Interruptible load (IL), as a power resource to be tapped, can be applied to the park integrated energy management and microgrid systems to guide users to reduce peak electricity consumption. The IL function is introduced into the park integrated energy system with combined heat and power units to improve the system's peak shaving ability, and the corresponding model is established with the optimization goal of economy. Taking an ecological park of northern region as the example, the adaptive chaotic particle swarm algorithm is used …

Radar Remote Sensing Data Augmentation Method Based On Generative Adversarial Network, Xu Kang, Xiaofeng Zhang

Journal of System Simulation

Abstract: In the research field of radar remote sensing, both the completeness and diversity of radar data samples cannot meet the requirement of effective training of deep learning models, and the models are prone to over-fitting, which significantly limits the wide application of deep learning techniques in this field. Targeting on the needs of intelligent application in radar remote sensing, a microwave imaging radar suited data augmentation method is proposed to solve the issue of insufficient radar data samples by leveraging the general framework of generative adversarial network. Aiming at the features of radar samples being not obvious, the label …

A Devs-Based Formal Description Method For Complex Product Behavior Models, Qingquan Lin, Jiaran Yang, Heming Zhang

Journal of System Simulation

Abstract: For the online optimization of pedestrian flow control in subway station, an algorithm frame for pedestrian flow control in subway station based on machine learning is designed. The pedestrian flow control process of a subway station during morning rush hour is selected,and the agent-based model is built to simulate the control process. The training data is collected through the multiple runs of the model, which is used as the input of deep reinforcement learning network, and the mature net is obtained through adequate training to provide the optimizing scheduling policy. Linking the actual data with the mature net …

An Unmanned Swarm Search Method Based On Human-Robot Cooperation, Xin Zhou, Weiping Wang, Yifan Zhu, Tao Wang, Tian Jing

Journal of System Simulation

Abstract: Human-robot collaboration is a research hotspot and the human and unmanned swarm collaborative search is a typical scenario. It can carry out the more complex tasks by combining the human complex reasoning capabilities with repeated and precise execution capabilities of unmanned swarm. Based on the high-value target search of the uncertain scenarios, the concept definition for the collaborative search of human and unmanned swarm is given. A multi-agent dynamic programming model under uncertain with unknown prior knowledge is proposed, established to describe how the multi-agent system carries out the search under human support. A dynamic programming algorithm …

Research On Space Launch Visualization Simulation Analysis Technology And Application, Feng Wu, Xiuluo Liu, Jia Wang, Yang Liu, Sujiang Li, Yan Zhong

Journal of System Simulation

Abstract: Through the typical cases in the field of military, society, manufacturing etc., this paper introduces the concept and features of complex engineering system of systems as well as the significance of modeling and simulation for the study of complex engineering system of systems. Taking complex product manufacturing as an example, the evolution process from systems engineering to model-based systems engineering (MBSE) and then to modeling and simulation-based system of systems engineering is analyzed. The characteristics and challenges of modeling and simulation of complex engineering system of systems is discussed. Some research topics in filed of MSBS2E is introduced, which …

Hybrid Variable Neighborhood Search Algorithm For The Multi-Trip And Heterogeneous-Fleet Electric Vehicle Routing Problem, Weiquan Wang, Ding Ding, Shuyan Cao

Journal of System Simulation

Abstract: Based on the real business practice, the multi-trip and heterogeneous-fleet electric vehicle routing problem (MTHF-EVRP) with time windows in green logistics is studied. A path-based mixed-integer linear model is built for the precise solution to the small-scale instances. A hybrid variable neighborhood search algorithm (Hybrid VNS) combined the variable neighborhood search algorithm with the labeling algorithm is proposed for the large-scale instances. The algorithm generates a modified insertion heuristic with random factor to construct the initial solution, allows the time window and range violation, adopts the neighborhood operators for the local search, and applies a labeling algorithm to solve …