arXiv subjects

Zhiyuan Wang

Publications and source records attributed to Zhiyuan Wang.

At least 109 records · Page 6Linked to original sources

arXiv2024

Deep Learning Aided Multi-Objective Optimization and Multi-Criteria Decision Making in Thermal Cracking Process for Olefines Production

Background: Multilayer perceptron (MLP) aided multi-objective particle swarm optimization algorithm (MOPSO) is employed in the present article to optimize the liquefied petroleum gas (LPG) thermal cracking process. This new approach significantly accelerated the multi-objective optimization (MOO), which can now be completed within one minute compared to the average of two days required by the conventional approach. Methods: MOO generates a set of equally good Pareto-optimal solutions, which are then ranked using a combination of a weighting method and five multi-criteria decision making (MCDM) methods. The final selection of a single solution for implementation is based on majority voting and the similarity of the recommended solutions from the MCDM methods. Significant Findings: The deep learning (DL) aided MOO and MCDM approach provides valuable insights into the trade-offs between conflicting objectives and a more comprehensive understanding of the relationships between them. Furthermore, this approach also allows for a deeper understanding of the impact of decision variables on the objectives, enabling practitioners to make more informed, data-driven decisions in the thermal cracking process.

physics.chem-ph↗

arXiv2024

Word-Sequence Entropy: Towards Uncertainty Estimation in Free-Form Medical Question Answering Applications and Beyond

Uncertainty estimation is crucial for the reliability of safety-critical human and artificial intelligence (AI) interaction systems, particularly in the domain of healthcare engineering. However, a robust and general uncertainty measure for free-form answers has not been well-established in open-ended medical question-answering (QA) tasks, where generative inequality introduces a large number of irrelevant words and sequences within the generated set for uncertainty quantification (UQ), which can lead to biases. This paper introduces Word-Sequence Entropy (WSE), a method that calibrates uncertainty at both the word and sequence levels, considering semantic relevance. WSE quantifies uncertainty in a way that is more closely aligned with the reliability of LLMs during uncertainty quantification (UQ). We compare WSE with six baseline methods on five free-form medical QA datasets, utilizing seven popular large language models (LLMs). Experimental results demonstrate that WSE exhibits superior performance in UQ under two standard criteria for correctness evaluation. Additionally, in terms of real-world medical QA applications, the performance of LLMs is significantly enhanced (e.g., a 6.36% improvement in model accuracy on the COVID-QA dataset) by employing responses with lower uncertainty that are identified by WSE as final answers, without any additional task-specific fine-tuning or architectural modifications.

cs.CL↗

arXiv2024

ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees

Uncertainty quantification (UQ) in natural language generation (NLG) tasks remains an open challenge, exacerbated by the closed-source nature of the latest large language models (LLMs). This study investigates applying conformal prediction (CP), which can transform any heuristic uncertainty notion into rigorous prediction sets, to black-box LLMs in open-ended NLG tasks. We introduce a novel uncertainty measure based on self-consistency theory, and then develop a conformal uncertainty criterion by integrating the uncertainty condition aligned with correctness into the CP algorithm. Empirical evaluations indicate that our uncertainty measure outperforms prior state-of-the-art methods. Furthermore, we achieve strict control over the correctness coverage rate utilizing 7 popular LLMs on 4 free-form NLG datasets, spanning general-purpose and medical scenarios. Additionally, the calibrated prediction sets with small size further highlights the efficiency of our method in providing trustworthy guarantees for practical open-ended NLG applications.

cs.CL↗

arXiv2024

Link-identified Routing Architecture in Space

Low earth orbit (LEO) satellite networks have the potential to provide low-latency communication with global coverage. To unleash this potential, it is crucial to achieve efficient packet delivery. In this paper, we propose a Link-identified Routing (LiR) architecture for LEO satellite networks. The LiR architecture leverages the deterministic neighbor relation of LEO constellations, and identifies each inter-satellite link (ISL). Moreover, LiR architecture adopts source-route-style forwarding based on in-packet bloom filter (BF). Each satellite could efficiently encode multiple ISL identifiers via an in-packet BF to specify the end-to-end path for the packets. Due to false positives caused by BF, the more ISLs are encoded at a time, the more redundant forwarding cases emerge. Based on the topology characteristics, we derive the expected forwarding overhead in a closed-form and propose the optimal encoding policy. To accommodate link-state changes in LEO satellite networks, we propose the on-demand rerouting scheme and the on-demand detouring scheme to address the intermittent ISLs. We also elaborate how to take advantage of LiR architecture to achieve seamless handover for ground-satellite links (GSLs). Finally, we conduct extensive numerical experiments and packet-level simulations to verify our analytical results and evaluate the performance of the LiR architecture.

cs.NI↗

arXiv2024

Multi-Criteria Decision Making in Chemical and Process Engineering: Methods, Progress and Potential

Multi-criteria decision making (MCDM) is necessary for choosing one from the available alternatives (or from the obtained Pareto-optimal solutions for multi-objective optimization), where the performance of each alternative is quantified against several criteria (or objectives). This paper presents a comprehensive review of the application of MCDM methods in chemical and process engineering. It systematically outlines the essential steps in MCDM, including the various normalization, weighting, and MCDM methods that are critical to the decision-making. The review draws on published papers identified through a search in the SCOPUS database, focusing on works by authors with more contributions to the field. Each selected paper is analyzed based on the MCDM, normalization and weighting methods used. Additionally, this paper introduces two readily available programs for performing MCDM calculations. In short, it provides insights into MCDM steps and methods, highlights their applications in chemical engineering, and discusses the challenges and prospects in this area.

physics.chem-ph↗

arXiv2024

Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agents

This article explores the convergence of connectionist and symbolic artificial intelligence (AI), from historical debates to contemporary advancements. Traditionally considered distinct paradigms, connectionist AI focuses on neural networks, while symbolic AI emphasizes symbolic representation and logic. Recent advancements in large language models (LLMs), exemplified by ChatGPT and GPT-4, highlight the potential of connectionist architectures in handling human language as a form of symbols. The study argues that LLM-empowered Autonomous Agents (LAAs) embody this paradigm convergence. By utilizing LLMs for text-based knowledge modeling and representation, LAAs integrate neuro-symbolic AI principles, showcasing enhanced reasoning and decision-making capabilities. Comparing LAAs with Knowledge Graphs within the neuro-symbolic AI theme highlights the unique strengths of LAAs in mimicking human-like reasoning processes, scaling effectively with large datasets, and leveraging in-context samples without explicit re-training. The research underscores promising avenues in neuro-vector-symbolic integration, instructional encoding, and implicit reasoning, aimed at further enhancing LAA capabilities. By exploring the progression of neuro-symbolic AI and proposing future research trajectories, this work advances the understanding and development of AI technologies.

cs.AI↗

arXiv2024

PALLM: Evaluating and Enhancing PALLiative Care Conversations with Large Language Models

Effective patient-provider communication is crucial in clinical care, directly impacting patient outcomes and quality of life. Traditional evaluation methods, such as human ratings, patient feedback, and provider self-assessments, are often limited by high costs and scalability issues. Although existing natural language processing (NLP) techniques show promise, they struggle with the nuances of clinical communication and require sensitive clinical data for training, reducing their effectiveness in real-world applications. Emerging large language models (LLMs) offer a new approach to assessing complex communication metrics, with the potential to advance the field through integration into passive sensing and just-in-time intervention systems. This study explores LLMs as evaluators of palliative care communication quality, leveraging their linguistic, in-context learning, and reasoning capabilities. Specifically, using simulated scripts crafted and labeled by healthcare professionals, we test proprietary models (e.g., GPT-4) and fine-tune open-source LLMs (e.g., LLaMA2) with a synthetic dataset generated by GPT-4 to evaluate clinical conversations, to identify key metrics such as `understanding' and `empathy'. Our findings demonstrated LLMs' superior performance in evaluating clinical communication, providing actionable feedback with reasoning, and demonstrating the feasibility and practical viability of developing in-house LLMs. This research highlights LLMs' potential to enhance patient-provider interactions and lays the groundwork for downstream steps in developing LLM-empowered clinical health systems.

cs.CL↗

arXiv2024

Caterpillar: A Pure-MLP Architecture with Shifted-Pillars-Concatenation

Modeling in Computer Vision has evolved to MLPs. Vision MLPs naturally lack local modeling capability, to which the simplest treatment is combined with convolutional layers. Convolution, famous for its sliding window scheme, also suffers from this scheme of redundancy and lower parallel computation. In this paper, we seek to dispense with the windowing scheme and introduce a more elaborate and parallelizable method to exploit locality. To this end, we propose a new MLP module, namely Shifted-Pillars-Concatenation (SPC), that consists of two steps of processes: (1) Pillars-Shift, which generates four neighboring maps by shifting the input image along four directions, and (2) Pillars-Concatenation, which applies linear transformations and concatenation on the maps to aggregate local features. SPC module offers superior local modeling power and performance gains, making it a promising alternative to the convolutional layer. Then, we build a pure-MLP architecture called Caterpillar by replacing the convolutional layer with the SPC module in a hybrid model of sMLPNet. Extensive experiments show Caterpillar's excellent performance on both small-scale and ImageNet-1k classification benchmarks, with remarkable scalability and transfer capability possessed as well. The code is available at https://github.com/sunjin19126/Caterpillar.

cs.CV↗

arXiv2024

Two-dimensional non-Hermitian skin effect in an ultracold Fermi gas

The concept of non-Hermiticity has expanded the understanding of band topology leading to the emergence of counter-intuitive phenomena. One example is the non-Hermitian skin effect (NHSE), which involves the concentration of eigenstates at the boundary. However, despite the potential insights that can be gained from high-dimensional non-Hermitian quantum systems in areas like curved space, high-order topological phases, and black holes, the realization of this effect in high dimensions remains unexplored. Here, we create a two-dimensional (2D) non-Hermitian topological band for ultracold fermions in spin-orbit-coupled optical lattices with tunable dissipation, which exhibits the NHSE. We first experimentally demonstrate pronounced nonzero spectral winding numbers in the complex energy plane with non-zero dissipation, which establishes the existence of 2D skin effect. Further, we observe the real-space dynamical signature of NHSE in real space by monitoring the center of mass motion of atoms. Finally, we also demonstrate that a pair of exceptional points (EPs) are created in the momentum space, connected by an open-ended bulk Fermi arc, in contrast to closed loops found in Hermitian systems. The associated EPs emerge and shift with increasing dissipation, leading to the formation of the Fermi arc. Our work sets the stage for further investigation into simulating non-Hermitian physics in high dimensions and paves the way for understanding the interplay of quantum statistics with NHSE.

cond-mat.quant-gas↗

arXiv2024

AudioInsight: Detecting Social Contexts Relevant to Social Anxiety from Speech

During social interactions, understanding the intricacies of the context can be vital, particularly for socially anxious individuals. While previous research has found that the presence of a social interaction can be detected from ambient audio, the nuances within social contexts, which influence how anxiety provoking interactions are, remain largely unexplored. As an alternative to traditional, burdensome methods like self-report, this study presents a novel approach that harnesses ambient audio segments to detect social threat contexts. We focus on two key dimensions: number of interaction partners (dyadic vs. group) and degree of evaluative threat (explicitly evaluative vs. not explicitly evaluative). Building on data from a Zoom-based social interaction study (N=52 college students, of whom the majority N=45 are socially anxious), we employ deep learning methods to achieve strong detection performance. Under sample-wide 5-fold Cross Validation (CV), our model distinguished dyadic from group interactions with 90\% accuracy and detected evaluative threat at 83\%. Using a leave-one-group-out CV, accuracies were 82\% and 77\%, respectively. While our data are based on virtual interactions due to pandemic constraints, our method has the potential to extend to diverse real-world settings. This research underscores the potential of passive sensing and AI to differentiate intricate social contexts, and may ultimately advance the ability of context-aware digital interventions to offer personalized mental health support.

cs.HC↗

arXiv2024

Multi-Objective Optimization and Multi-Criteria Decision-Making Approach to Design Multi-Tubular Packed-Bed Membrane Reactor in Oxidative Dehydrogenation of Ethane

Ethylene is a crucial chemical in manufacturing numerous consumer products. In recent years, the oxidative dehydrogenation of ethane (ODHE) technique has garnered significant interest as a means for ethylene production due to its high ethylene selectivity and energy efficiency, the availability of ethane as a feedstock, and catalysts that can improve the performance of the process. This work delves into determining the optimal operating conditions for the ODHE process within a multi-tubular packed-bed membrane reactor by formulating and resolving multi-objective optimization (MOO) problems. The elitist non-dominated sorting genetic algorithm II (NSGA-II) method is employed in conjunction with three different multi-criteria decision-making (MCDM) methods: (i) technique for order of preference by similarity to ideal solution (TOPSIS), (ii) preference ranking on the basis of ideal-average distance (PROBID), and (iii) simple additive weighting (SAW), to solve the MOO problems, obtain the optimal Pareto frontier, and recommend one solution for ultimate implementation. Through this approach, this work elucidates the trade-offs between conflicting objectives, deepens the comprehension of their interrelationships, and underscores the effects of decision variables on the optimization objectives. Consequently, this work provides practitioners with the insights needed for informed decision-making in the ODHE process operation.

physics.chem-ph↗

arXiv2024

Selected multi-criteria decision-making methods and their applications to product and system design

Optimization has found numerous applications in engineering, particularly since 1960s. Many optimization applications in engineering have more than one objective (or performance criterion). Such applications require multi-objective (or multi-criteria) optimization (MOO or MCO). Spurred by this and development of techniques for handling multiple objectives, MOO has found many applications in engineering in the last two decades. Optimization of an application for more than one objective gives a set of optimal solutions (known as non-dominated or Pareto-optimal solutions), which are equally good in the sense that no objective can be further improved without resulting in deterioration of at least one other objective. MOO in engineering has mainly focused on development of a model for the application, formulation of the MOO problem and solution of the formulated problem to find Pareto-optimal solutions. However, for completion of MOO, one more step is required to choose one of these optimal solutions for implementation.

physics.chem-ph↗

arXiv2024

CommSense: A Wearable Sensing Computational Framework for Evaluating Patient-Clinician Interactions

Quality patient-provider communication is critical to improve clinical care and patient outcomes. While progress has been made with communication skills training for clinicians, significant gaps exist in how to best monitor, measure, and evaluate the implementation of communication skills in the actual clinical setting. Advancements in ubiquitous technology and natural language processing make it possible to realize more objective, real-time assessment of clinical interactions and in turn provide more timely feedback to clinicians about their communication effectiveness. In this paper, we propose CommSense, a computational sensing framework that combines smartwatch audio and transcripts with natural language processing methods to measure selected ``best-practice'' communication metrics captured by wearable devices in the context of palliative care interactions, including understanding, empathy, presence, emotion, and clarity. We conducted a pilot study involving N=40 clinician participants, to test the technical feasibility and acceptability of CommSense in a simulated clinical setting. Our findings demonstrate that CommSense effectively captures most communication metrics and is well-received by both practicing clinicians and student trainees. Our study also highlights the potential for digital technology to enhance communication skills training for healthcare providers and students, ultimately resulting in more equitable delivery of healthcare and accessible, lower cost tools for training with the potential to improve patient outcomes.

cs.HC↗

arXiv2024

Towards Timely Video Analytics Services at the Network Edge

Real-time video analytics services aim to provide users with accurate recognition results timely. However, existing studies usually fall into the dilemma between reducing delay and improving accuracy. The edge computing scenario imposes strict transmission and computation resource constraints, making balancing these conflicting metrics under dynamic network conditions difficult. In this regard, we introduce the age of processed information (AoPI) concept, which quantifies the time elapsed since the generation of the latest accurately recognized frame. AoPI depicts the integrated impact of recognition accuracy, transmission, and computation efficiency. We derive closed-form expressions for AoPI under preemptive and non-preemptive computation scheduling policies w.r.t. the transmission/computation rate and recognition accuracy of video frames. We then investigate the joint problem of edge server selection, video configuration adaptation, and bandwidth/computation resource allocation to minimize the long-term average AoPI over all cameras. We propose an online method, i.e., Lyapunov-based block coordinate descent (LBCD), to solve the problem, which decouples the original problem into two subproblems to optimize the video configuration/resource allocation and edge server selection strategy separately. We prove that LBCD achieves asymptotically optimal performance. According to the testbed experiments and simulation results, LBCD reduces the average AoPI by up to 10.94X compared to state-of-the-art baselines.

cs.DC↗

arXiv2024

Estimating Difficulty Levels of Programming Problems with Pre-trained Model

As the demand for programming skills grows across industries and academia, students often turn to Programming Online Judge (POJ) platforms for coding practice and competition. The difficulty level of each programming problem serves as an essential reference for guiding students' adaptive learning. However, current methods of determining difficulty levels either require extensive expert annotations or take a long time to accumulate enough student solutions for each problem. To address this issue, we formulate the problem of automatic difficulty level estimation of each programming problem, given its textual description and a solution example of code. For tackling this problem, we propose to couple two pre-trained models, one for text modality and the other for code modality, into a unified model. We built two POJ datasets for the task and the results demonstrate the effectiveness of the proposed approach and the contributions of both modalities.

cs.SE↗

arXiv2024

Task-agnostic Decision Transformer for Multi-type Agent Control with Federated Split Training

With the rapid advancements in artificial intelligence, the development of knowledgeable and personalized agents has become increasingly prevalent. However, the inherent variability in state variables and action spaces among personalized agents poses significant aggregation challenges for traditional federated learning algorithms. To tackle these challenges, we introduce the Federated Split Decision Transformer (FSDT), an innovative framework designed explicitly for AI agent decision tasks. The FSDT framework excels at navigating the intricacies of personalized agents by harnessing distributed data for training while preserving data privacy. It employs a two-stage training process, with local embedding and prediction models on client agents and a global transformer decoder model on the server. Our comprehensive evaluation using the benchmark D4RL dataset highlights the superior performance of our algorithm in federated split learning for personalized agents, coupled with significant reductions in communication and computational overhead compared to traditional centralized training approaches. The FSDT framework demonstrates strong potential for enabling efficient and privacy-preserving collaborative learning in applications such as autonomous driving decision systems. Our findings underscore the efficacy of the FSDT framework in effectively leveraging distributed offline reinforcement learning data to enable powerful multi-type agent decision systems.

cs.LG↗

arXiv2024

Blood Works for Graphene Production

Blood, a ubiquitous and fundamental carbohydrate material composed of plasma, red blood cells, white blood cells, and platelets, has been playing an important role in biology, life science, history, and religious study, while graphene has garnered significant attention due to its exceptional properties and extensive range of potential applications. Achieving environmentally friendly, cost-effective growth using hybrid precursors and obtaining high-quality graphene through a straightforward CVD process has been traditionally considered mutually exclusive. This study demonstrates that we can produce high-quality graphene domains with controlled thickness through a one-step growth process at atmospheric pressure using blood as a precursor. Raman spectroscopy confirms the uniformity of the blood-grown graphene films, and observing the half-integer quantum Hall effect in the measured devices highlights its outstanding electronic properties. This unprecedented approach opens possibilities for blood application, facilitating an unconventional route in graphene growth applications.

cond-mat.mes-hall↗

arXiv2024

Ultimate charge transport regimes in doping-controlled graphene laminates: phonon-assisted processes revealed by the linear magnetoresistance

Understanding and controlling the electrical properties of solution-processed 2D materials is key to further printed electronics progress. Here we demonstrate that the thermolysis of the aromatic intercalants utilized in nanosheet exfoliation for graphene laminates opens the route to achieving high intrinsic mobility and simultaneously controlling doping type ($n$- and $p$-) and concentration over a wide range. We establish that the intra-flake mobility is high by observing a linear magnetoresistance of such solution-processed graphene laminates and using it to devolve the inter-flake tunneling and intra-layer magnetotransport. Consequently, we determine the temperature dependences of the inter- and intra-layer characteristics, which both appear to be dominated by phonon-assisted processes at temperature $T>$20 Kelvin. In particular, we identify the efficiency of phonon-assisted tunneling as the main limiting factor for electrical conductivity in graphene laminates at room temperature. We also demonstrate a thermoelectric sensitivity of around 50 $μ$V K$^{-1}$ in a solution-processed metal-free graphene-based thermocouple.

cond-mat.mes-hall↗