Computer Sciences Commons^™

Heterogeneous Graph Transformer With Poly-Tokenization, Zhiyuan Lu, Yuan Fang, Cheng Yang, Chuan Shi

Research Collection School Of Computing and Information Systems

Graph neural networks have shown widespread success for learning on graphs, but they still face fundamental drawbacks, such as limited expressive power, over-smoothing, and over-squashing. Meanwhile, the transformer architecture offers a potential solution to these issues. However, existing graph transformers primarily cater to homogeneous graphs and are unable to model the intricate semantics of heterogeneous graphs. Moreover, unlike small molecular graphs where the entire graph can be considered as the receptive field in graph transformers, real-world heterogeneous graphs comprise a significantly larger number of nodes and cannot be entirely treated as such. Consequently, existing graph transformers struggle to capture the …

Tackling Stackelberg Network Interdiction Against A Boundedly Rational Adversary, Tien Mai, Avinandan Bose, Arunesh Sinha, Thanh Nguyen, Ayushman Kumar Singh

Research Collection School Of Computing and Information Systems

This work studies Stackelberg network interdiction games --- an important class of games in which a defender first allocates (randomized) defense resources to a set of critical nodes on a graph while an adversary chooses its path to attack these nodes accordingly. We consider a boundedly rational adversary in which the adversary's response model is based on a dynamic form of classic logit-based (quantal response) discrete choice models. The resulting optimization is non-convex and additionally, involves complex terms that sum over exponentially many paths. We tackle these computational challenges by presenting new efficient algorithms with solution guarantees. First, we present …

Empathyear : An Open-Source Avatar Multimodal Empathetic Chatbot, Hao Fei, Han Zhang, Bin Wang, Lizi Liao, Qian Liu, Erik Cambria

Research Collection School Of Computing and Information Systems

This paper introduces EmpathyEar, a pioneering open-source, avatar-based multimodal empathetic chatbot, to fill the gap in traditional text-only empathetic response generation (ERG) systems. Leveraging the advancements of a large language model, combined with multimodal encoders and generators, EmpathyEar supports user inputs in any combination of text, sound, and vision, and produces multimodal empathetic responses, offering users, not just textual responses but also digital avatars with talking faces and synchronized speeches. A series of emotion-aware instruction-tuning is performed for comprehensive emotional understanding and generation capabilities. In this way, EmpathyEar provides users with responses that achieve a deeper emotional resonance, closely emulating …

Planning Like Human : A Dual-Process Framework For Dialogue Planning, Tao He, Lizi Liao, Yixin Cao, Yuanxing Liu, Ming Liu, Zerui Chen, Bing Qin

Research Collection School Of Computing and Information Systems

In proactive dialogue, the challenge lies not just in generating responses but in steering conversations toward predetermined goals, a task where Large Language Models (LLMs) typically struggle due to their reactive nature. Traditional approaches to enhance dialogue planning in LLMs, ranging from elaborate prompt engineering to the integration of policy networks, either face efficiency issues or deliver suboptimal performance. Inspired by the dual-process theory in psychology, which identifies two distinct modes of thinking—intuitive (fast) and analytical (slow), we propose the Dual-Process Dialogue Planning (DPDP) framework. DPDP embodies this theory through two complementary planning systems: an instinctive policy model for familiar …

Analyzing Temporal Complex Events With Large Language Models? A Benchmark Towards Temporal, Long Context Understanding, Zhihan Zhang, Yixin Cao, Chenchen Ye, Ma. Yunshan, Lizi Liao, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

The digital landscape is rapidly evolving with an ever-increasing volume of online news, emphasizing the need for swift and precise analysis of complex events.We refer to the complex events composed of many news articles over an extended period as Temporal Complex Event (TCE). This paper proposes a novel approach using Large Language Models (LLMs) to systematically extract and analyze the event chain within TCE, characterized by their key points and timestamps. We establish a benchmark, named TCELongBench, to evaluate the proficiency of LLMs in handling temporal dynamics and understanding extensive text. This benchmark encompasses three distinct tasks - reading comprehension, …

Synergizing Large Language Models And Pre-Trained Smaller Models For Conversational Intent Discovery, Jinggui Liang, Lizi Liao, Hao Fei, Jing Jiang

Research Collection School Of Computing and Information Systems

In Conversational Intent Discovery (CID), Small Language Models (SLMs) struggle with overfitting to familiar intents and fail to label newly discovered ones. This issue stems from their limited grasp of semantic nuances and their intrinsically discriminative framework. Therefore, we propose Synergizing Large Language Models (LLMs) with pre-trained SLMs for CID (SynCID). It harnesses the profound semantic comprehension of LLMs alongside the operational agility of SLMs. By utilizing LLMs to refine both utterances and existing intent labels, SynCID significantly enhances the semantic depth, subsequently realigning these enriched descriptors within the SLMs’ feature space to correct cluster distortion and promote robust learning …

A Survey On Neural Question Generation : Methods, Applications, And Prospects, Shasha Guo, Lizi Liao, Cuiping Li, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

In this survey, we present a detailed examination of the advancements in Neural Question Generation (NQG), a field leveraging neural network techniques to generate relevant questions from diverse inputs like knowledge bases, texts, and images. The survey begins with an overview of NQG’s background, encompassing the task’s problem formulation, prevalent benchmark datasets, established evaluation metrics, and notable applications. It then methodically classifies NQG approaches into three predominant categories: structured NQG, which utilizes organized data sources, unstructured NQG, focusing on more loosely structured inputs like texts or visual content, and hybrid NQG, drawing on diverse input modalities. This classification is followed …

Ee-Lce: An Event Extraction Framework Based On Llm-Generated Cot Explanation, Yanhua Yu, Yuanlong Wang, Yunshan Ma, Jie Li, Kangkang Lu, Zhiyong Huang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Generative models have been widely used in event extraction. However, the interpretability of event extraction has not been fully investigated. In this paper, we propose an Event Extraction framework based on LLM-generated CoT Explanation EE-LCE, which can generate chain-of-thought-style (CoT-style) explanations for events. To this end, we provide each sample of event datasets with an explanation of the reasoning process using a large language model (LLM) GPT-3.5, and fine-tune the Flan-T5 lightweight language model (LM) supervised by the augmented dataset, enhancing both interpretability and performance of the event extraction. Moreover, we use a prefix tree (trie) to normalize the decoding …

Sociomathematical Norms And Automated Proof Checking In Mathematical Education: Reflections And Experiences, Merlin Carl

Journal of Humanistic Mathematics

According to a widely held view, mathematical proofs are essentially (indications of) formal derivations, and thus in principle mechanically checkable (this view is defended, for example, by Azzouni [3]). This should in particular hold for the kind of simple proof exercises typically given to students of mathematics learning to write proofs. If that is so, then automated proof checking should be an attractive option for math education at the undergraduate level. An opposing view would be that mathematical proofs are social objects and that what constitutes a mathematical proof can thus not be separated from the social context in which …

Maximizing Generative Ai Benefits With Task Creativity And Human Validation, Charu Sinha, Veselina P. Vracheva, Cristina Nistor

Business Faculty Articles and Research

Much of the existing literature on generative AI applications is conflicting, with findings suggesting that investing in AI will lead to better organizational outcomes but also pointing out that incorporating AI may be a wasteful even counterproductive initiative. We develop a conceptual frame-work to characterize generative AI benefits based on the types of tasks that generative AI may be used for in management. Our work suggests that task creativity plays a key role in successful generative AI outcomes, but human validation - the extent to which a human engages in a supervisory role - is required to reap the benefits. …

Leveraging Generative Artificial Intelligence Models In Patient Education On Inferior Vena Cava Filters, Som Singh, Aleena Jamal, Farah Qureshi, Rohma Zaidi, Fawad Qureshi

SKMC Student Presentations and Publications

Background: Inferior Vena Cava (IVC) filters have become an advantageous treatment modality for patients with venous thromboembolism. As the use of these filters continues to grow, it is imperative for providers to appropriately educate patients in a comprehensive yet understandable manner. Likewise, generative artificial intelligence models are a growing tool in patient education, but there is little understanding of the readability of these tools on IVC filters. Methods: This study aimed to determine the Flesch Reading Ease (FRE), Flesch–Kincaid, and Gunning Fog readability of IVC Filter patient educational materials generated by these artificial intelligence models. Results: The ChatGPT cohort had …

Smart Airports: Artificial Intelligence–Enabled Internet Of Things Networks Using Blockchain Technology, Edwin Ongola

Journal of Aviation Technology and Engineering

This article provides a perspective on how an internet of heterogeneous self-service airport terminal systems can be used for data collection, which is stored on a private or consortium blockchain depending on the ownership or operations of an airport or both. Such a setup would help to increase efficiency, reduce costs, and improve traveler experience at airport terminals. Moreover, it would allow airports to gather data directly from passengers as opposed to waiting to receive the same data from airlines. Subsequently, this data, now on a blockchain system, becomes a data source for other applications such as machine learning. In …

Personalized Driving Using Inverse Reinforcement Learning, Rodrigo J. Gonzalez Salinas

Theses and Dissertations

This thesis introduces an autonomous driving controller designed to replicate individual driving behaviors based on a provided demonstration. The controller employs Inverse Reinforcement Learning (IRL) to formulate the reward function associated with the provided demonstration. IRL is implemented through a dual-feedback loop system. The inner loop utilizes Q-learning, a model-free reinforcement learning technique, to optimize the Hamilton-Jacobi-Bellman (HJB) equation and derive an appropriate control solution. The outer loop leverages this derived control solution to generate parameters for the reward function, which are subsequently integrated into the HJB equation. The ultimate control policy is deduced from the final reward function obtained …

Transforming Libraries Through Engagement: Lessons From A Library Ai Interest Group, Lily Dubach, Rachel Vacek

Faculty Scholarship and Creative Works

Learn how one academic library is engaging with its employees to explore the latest trends, tools, and topics in AI through an interest group (IG). Through stimulating discussions, webinars, guest speakers, demos, and sharing of experiences with AI, the IG empowers its library community to explore and become more comfortable with AI. This session caters to varying levels of AI expertise. Challenges, successes, and valuable insights for deeper engagement will be shared so you can learn how to establish a similar initiative in your library.

Predicting Choroidal Nevus Transformation To Melanoma Using Machine Learning, Prashant D. Tailor, Piotr K. Kopinski, Haley S. D'Souza, David A. Leske, Timothy W. Olsen, Carol L. Shields, Jerry A. Shields, Lauren A. Dalvin

Wills Eye Hospital Papers

PURPOSE: To develop and validate machine learning (ML) models to predict choroidal nevus transformation to melanoma based on multimodal imaging at initial presentation.

DESIGN: Retrospective multicenter study.

PARTICIPANTS: Patients diagnosed with choroidal nevus on the Ocular Oncology Service at Wills Eye Hospital (2007-2017) or Mayo Clinic Rochester (2015-2023).

METHODS: Multimodal imaging was obtained, including fundus photography, fundus autofluorescence, spectral domain OCT, and B-scan ultrasonography. Machine learning models were created (XGBoost, LGBM, Random Forest, Extra Tree) and optimized for area under receiver operating characteristic curve (AUROC). The Wills Eye Hospital cohort was used for training and testing (80% training-20% testing) with …

Empowering Traditional Industries With Digital Intelligence For Transformation And Upgrading, Jiyuan Zang, Huanyong Ji, Qingxue Huang

Bulletin of Chinese Academy of Sciences (Chinese Version)

Traditional industries are the basic support and driving force for the high-quality development of the economy. Digital intelligence is an important lever for traditional industries to achieve the transformation of old and new kinetic energy and the leapfrogging of the global value chain. This study firstly deconstructs the rich connotations of digital intelligence from the perspectives of digitalization, networkization, and intelligentization. Secondly, it analyzes the transformation mechanism and various pathways through which digital intelligence impacts traditional industries. Thirdly, it analyzes the barriers faced by traditional industries in the process of adopting digital intelligence technologies. Finally, this study puts forward four …

Strategic Study On Leading Construction Of Modern Agricultural System By Technology Innovation, Yan Yan, Xurong Mei, Xiudong Wang

Bulletin of Chinese Academy of Sciences (Chinese Version)

Technology innovation is the fundamental solution to build a modern agricultural system, and it is also an important support for building the large base, large enterprise, and large industry of modern agriculture and achieving the modernization of material equipment, technology, management, agricultural informatization, and sustainable resource utilization of agriculture. This paper explains the scientific concepts and logical relationships of the agricultural production system, industrial system and management system, which are the main components of a modern agricultural system. It emphasizes that ensuring food security, promoting industrial integration and upgrading, and cultivating leading enterprises are current key tasks. Nevertheless, from the …

A Qualitative Study On The Integration Of Artificial Intelligence In Cultural Heritage Conservation, Kholoud Ghaith, James Hutson

Faculty Scholarship

The widespread adoption of generative artificial intelligence (GAI) technologies heralds an era of expanding possibilities in the domain of cultural heritage conservation. This paradigm shift is marked by a confluence of innovative methodologies, including digital twin mapping, digital archiving, and enhanced preservation strategies, aimed at safeguarding the vestiges of our shared past. The application of AI within this field represents a frontier where technology and tradition intersect, offering new vistas for the preservation of historical structures and artifacts that are at risk of deterioration or oblivion. This article endeavors to elucidate the perspectives of professionals within the conservation domain on …

Riesz Particle Markov Chain Monte Carlo Methods, Xiongming Dai

LSU Doctoral Dissertations

Markov chain Monte Carlo (MCMC) methods are simulations that explore complex statistical distributions, while bypassing the cumbersome requirement of a specific analytical expression for the target. This stochastic exploration of an uncertain parameter space comes at the expense of a large number of ``burn-in'' samples, and the computational complexity leads to the curse of dimensionality. Although at the exploration level, some methods have been proposed to accelerate the convergence of the algorithm, such as tempering, Hamiltonian Monte Carlo, Rao-redwellization, and scalable methods for better performance, they cannot avoid the stochastic nature of this exploration. We develop algorithms for the energy …

Effective Position Intelligent Decision Method Based On Model Fusion And Generative Network, Liqiang Guo, Liang Ma, Hui Zhang, Jing Yang, Lianfeng Li, Yaqi Zhai

Journal of System Simulation

Abstract: Military intelligence technology is currently the most dynamic frontier and the inevitable trend for the development of unmanned equipment in the future. Aiming at the dual requirements of reliability and real-time performance of unmanned platform autonomous decision-making in complex environments and the shortcomings of existing combat simulation technology based on rule reasoning in terms of dynamics and flexibility, a research method of principle analysis and experimental verification is adopted. Based on the shooting experiment dataset of an unmanned platform, the effective position recognition link of attack decision-making is transformed into a binary classification problem with imbalanced categories in the …

Digital Twin Modeling And Control Of Robots For Intelligent Manufacturing Scenarios, Ying Li, Lan Gao, Zhisong Zhu

Journal of System Simulation

Abstract: The introduction of Industry 4.0 and the Made in China 2025 development policy has accelerated the transformation of the manufacturing industry from automation to intelligence. Industrial robots, as the representative equipment of intelligent manufacturing, will also become more intelligent. Based on digital twin technology, digital modeling, and simulation debugging are conducted for such problems as interference and collision, tedious operation, and low efficiency of industrial robot spot welding debugging in production. Process Simulate from TECNOMATIX software is utilized to digitally model the robot spot welding station and define its motion, and TIA Portal and S7-PLCSIM Advanced are applied to …

Research On Learnable Wargame Agent Driven By Battle Scheme, Yifeng Sun, Zhi Li, Jiang Wu, Yubin Wang

Journal of System Simulation

Abstract: To enable the agent to cope with complex battle scenarios and objectives in wargame, a learnable wargame agent architecture driven by a battle scheme is proposed. By analyzing the "attachment characteristics" and "loose coupling characteristics" of the agent to wargame system, the learnable requirements of the agent are obtained. In the design of the agent framework, battle schemes are used to reduce the learning range of the agent. The finite state machine corresponds to the knowledge of the operational phase in the battle scheme, and the decision-making space of the agent is determined according to the framework of the …

A Deep Fuzzy Classifier Based On Feature Transform And Reconstruction, Rui Yin, Wei Lu, Jianhua Yang

Journal of System Simulation

Abstract: To obtain a classifier with good classification accuracy and interpretability, a deep fuzzy classifier based on feature transform and reconstruction (FR-DFC) is proposed. In FR-DFC, several fuzzy systems (FT_FS) for feature transform and a multi-prototype fuzzy classification system (MPRFD_FS) are stacked together to realize the classification process of the model, based on the hierarchically stacked thought originated from deep learning. Specifically, the stacked FT_FSs explore the hidden features in the data by transferring data from the original data space to the high-level feature space. MPRFD_FS, on the other hand, implements classification based on multiple prototypes that characterize the distribution …

Adaptive Particle Swarm Optimization Algorithm Based On Trap Label And Lazy Ant, Wei Zhang, Yuefeng Jiang

Journal of System Simulation

Abstract: Many existing strategies for improving particle swarm optimization (PSO) fall short in assisting particles trapped in local optima and experiencing premature convergence to recover optimization performance. In response, an adaptive particle swarm optimization algorithm based on trap label and lazy ant (TLLA-APSO) is proposed. Firstly, the trap label strategy dynamically adjusts particle velocities, enabling the particle swarm to escape from local optima. Secondly, the lazy ant optimization strategy is employed to diversify particle velocity and enhance population diversity. Finally, the inertia cognition strategy introduces historical position into velocity updates, promoting path diversity and particle exploration while effectively mitigating the …

Simulation Optimization Of Airport Baggage Import System Based On Multi-Objective Wolf Pack Algorithm, Yifei Tao, Xiaopeng Ding, Junbin Luo, Xiao Fu, Jiaxing Wu, Yirong Li

Journal of System Simulation

Abstract: Aiming at the problems of long waiting time for passenger baggage import and high system energy consumption during the operation of the baggage import system in civil aviation airports, a simulation optimization framework for solving this problem is proposed by comprehensively considering the influence of key control parameters on the operation efficiency of the baggage import system in airports, including the virtual window control mode, the operation speed of the collection belt conveyor, the length of the virtual window and the number of check-in counters opened at the same time. By analyzing the actual operating conditions of the airport …

Task Analysis Methods Based On Deep Reinforcement Learning, Xue Gong, Pengfei Peng, Li Rong, Yalian Zheng, Jun Jiang

Journal of System Simulation

Abstract: In response to the high coupling of task interaction and many influencing factors in task analysis, a task analysis method based on sequence decoupling and deep reinforcement learning (DRL) is proposed, which can achieve task decomposition and task sequence reconstruction under complex constraints. The method designs an environment for deep reinforcement learning based on task information interaction, while improving the SumTree algorithm based on the difference between the loss functions of the target network and the evaluation network, achieving the priority evaluation among tasks. The activation function operation mechanism is introduced into the deep reinforcement learning network, followed by …

Modeling And Verification Of Cooperative Vehicle Infrastructure System At Unsignalized Intersection Based On Time Automata, Wei Liu, Qirui Xiao, Xinhai Chen, Chang Rao, Yu Zhang, Bosi Wang

Journal of System Simulation

Abstract: Cooperative vehicle infrastructure system (CVIS) is one of the advanced solutions to enhance intersection vehicle passage safety. Due to the lack of clear specifications and standards regarding the dynamic timing and transition processes of system object state interaction in existing CVIS technologies, ensuring the safety of passage control logic is challenging. This study utilizes formal language to describe the functional logic of CVIS in unsignalized intersections, verifying the safety of system object state interaction and control logic to improve vehicle passage safety at unsignalized intersections. Simulations are conducted for scenarios including single-vehicle non-conflict, dual-vehicle conflict, and multi-vehicle conflict to …

Real-Time Non-Photorealistic Rendering Method For Black And White Comic Style In Games And Animation, Yan Hu, Lizhe Chen, Hanna Xie, Yuyao Ge, Shun Zhou, Xingquan Cai

Journal of System Simulation

Abstract: To address the issues of high resource consumption and lengthy workflow in general nonphotorealistic, this paper proposes a real-time non-photorealistic rendering method for black and white comic style in games and animation. A specialized lighting model is designed to highlight the main environmental light and the grayscale grading of diffuse reflection based on the analysis of the lighting model effect. The pre-processing of the scene is achieved by merging the various components of the lighting model. A screen space three-phase edge detection method is proposed to sequentially perform depth edge detection, normal edge detection, and color edge detection on …

Simulation System For Carrier-Based Aircraft Ammunition Support Scheduling, Zhe Liu, Jiafeng Chen, Junfei Ma, Songhua Ma

Journal of System Simulation

Abstract: For inefficient scheduling of carrier-based aircraft ammunition support on the flight deck of aircraft carriers, a Unity3D-based 3D virtual demonstration method for carrier-based aircraft ammunition scheduling is proposed, and a 3D virtual simulation system for carrier-based aircraft ammunition scheduling on the flight deck of aircraft carriers is constructed. A problem model targeted at carrierbased aircraft ammunition transportation and loading scheduling process as well as processing rules for path determination, sequence constraint, and loading position compensation are established based on the defining system. An optimal solution for the scheduling process is realized by using the improved discrete grey wolf optimizer …

Uav Path Planning Based On Improved Harris Hawk Algorithm And B-Spline Curve, Zhifeng Huang, Yuanhua Liu

Journal of System Simulation

Abstract: Aiming at the global path planning problem of unmanned aerial vehicles (UAVs) in dynamic environments, this paper proposes an improved Harris Hawk optimization algorithm. To address the problem of insufficient search performance in the later stage of the algorithm, an adaptive chaos and core population dynamic partitioning strategy is proposed to improve the searchability of the algorithm in the later stage. The Harris Hawk update formula is modified, and the golden sine strategy is introduced to improve the search efficiency of the algorithm. Then, an adaptive dynamic cloud optimal solution perturbation strategy is integrated to improve the ability of …