Physical Sciences and Mathematics Commons^™

Ur2m: Uncertainty And Resource-Aware Event Detection On Microcontrollers, Hong Jia, Young D. Kwon, Dong Ma, Nhat Pham, Lorena Qendro, Tam Vu, Cecilia Mascolo

Research Collection School Of Computing and Information Systems

Traditional machine learning techniques are prone to generating inaccurate predictions when confronted with shifts in the distribution of data between the training and testing phases. This vulnerability can lead to severe consequences, especially in applications such as mobile healthcare. Uncertainty estimation has the potential to mitigate this issue by assessing the reliability of a model's output. However, existing uncertainty estimation techniques often require substantial computational resources and memory, making them impractical for implementation on microcontrollers (MCUs). This limitation hinders the feasibility of many important on-device wearable event detection (WED) applications, such as heart attack detection. In this paper, we present …

Optimal Scheduling Strategy Of Virtual Power Plant With Carbon Emission And Carbon Penalty Considering Uncertainty Of Wind Power And Photovoltaic Power, Jijun Shui, Daogang Peng, Yankan Song, Qiang Zhou

Journal of System Simulation

Abstract: To better meet the development needs of China's new power system, an optimal scheduling strategy of virtual power plant(VPP) with carbon emission and carbon penalty considering the uncertainty of wind power and photovoltaic power is proposed. The mathematical description of photovoltaic(PV), wind turbine(WT), combined heat and power(CHP) unit and energy storage system (ESS) is carried out, and a wind-solar output model considering the uncertainty is established. The scenario generation and reduction method is used to generate the typical scenario. To maximize the overall operation benefit of VPP, considering carbon emission cost and carbon penalty, an optimal scheduling model of …

Active Discovering New Slots For Task-Oriented Conversation, Yuxia Wu, Tianhao Dai, Zhedong Zheng, Lizi Liao

Research Collection School Of Computing and Information Systems

Existing task-oriented conversational systems heavily rely on domain ontologies with pre-defined slots and candidate values. In practical settings, these prerequisites are hard to meet, due to the emerging new user requirements and ever-changing scenarios. To mitigate these issues for better interaction performance, there are efforts working towards detecting out-of-vocabulary values or discovering new slots under unsupervised or semi-supervised learning paradigms. However, overemphasizing on the conversation data patterns alone induces these methods to yield noisy and arbitrary slot results. To facilitate the pragmatic utility, real-world systems tend to provide a stringent amount of human labeling quota, which offers an authoritative way …

Affinity Uncertainty-Based Hard Negative Mining In Graph Contrastive Learning, Chaoxi Niu, Guansong Pang, Ling Chen

Research Collection School Of Computing and Information Systems

Hard negative mining has shown effective in enhancing self-supervised contrastive learning (CL) on diverse data types, including graph CL (GCL). The existing hardness-aware CL methods typically treat negative instances that are most similar to the anchor instance as hard negatives, which helps improve the CL performance, especially on image data. However, this approach often fails to identify the hard negatives but leads to many false negatives on graph data. This is mainly due to that the learned graph representations are not sufficiently discriminative due to oversmooth representations and/or non-independent and identically distributed (non-i.i.d.) issues in graph data. To tackle this …

Robust Interventions In Network Epidemiology, Erik Weis

Graduate College Dissertations and Theses

Which individual should we vaccinate to minimize the spread of a disease? Designing optimal interventions of this kind can be formalized as an optimization problem on networks, in which we have to select a budgeted number of dynamically important nodes to receive treatment that optimizes a dynamical outcome. Describing this optimization problem requires specifying the network, a model of the dynamics, and an objective for the outcome of the dynamics. In real-world contexts, these inputs are vulnerable to misspecification---the network and dynamics must be inferred from data, and the decision-maker must operationalize some (potentially abstract) goal into a mathematical objective …

Designing Large-Scale Intelligent Collaborative Platform For Freight Forwarders, Pang Jin Tan, Shih-Fen Cheng, Richard Chen

Research Collection School Of Computing and Information Systems

In this paper, we propose to design a large-scale intelligent collaborative platform for freight forwarders. This platform is based on a mathematical programming formulation and an efficient solution approach. Forwarders are middlemen who procure container capacities from carriers and sell them to shippers to serve their transport requests. However, due to demand uncertainty, they often either over-procure or under-procure capacities. We address this with our proposed platform where forwarders can collaborate and share capacities, allowing one's transport requests to be potentially shipped on another forwarder's container. The result is lower total costs for all participating forwarders. The collaboration can be …

Optimized Uncertainty Estimation For Vision Transformers: Enhancing Adversarial Robustness And Performance Using Selective Classification, Erik Pautsch, John Li, Silvio Rizzi, George K. Thiruvathukal, Maria Pantoja

Computer Science: Faculty Publications and Other Works

Deep Learning models often exhibit undue confidence when encountering out-of-distribution (OOD) inputs, misclassifying with high confidence. The ideal outcome, in these cases, would be an "I do not know" verdict. We enhance the trustworthiness of our models through selective classification, allowing the model to abstain from making predictions when facing uncertainty. Rather than a singular prediction, the model offers a prediction distribution, enabling users to gauge the model’s trustworthiness and determine the need for human intervention. We assess uncertainty in two baseline models: a Convolutional Neural Network (CNN) and a Vision Transformer (ViT). By leveraging these uncertainty values, we minimize …

Optimizing Uncertainty Quantification Of Vision Transformers In Deep Learning On Novel Ai Architectures, Erik Pautsch, John Li, Silvio Rizzi, George K. Thiruvathukal, Maria Pantoja

Computer Science: Faculty Publications and Other Works

Deep Learning (DL) methods have shown substantial efficacy in computer vision (CV) and natural language processing (NLP). Despite their proficiency, the inconsistency in input data distributions can compromise prediction reliability. This study mitigates this issue by introducing uncertainty evaluations in DL models, thereby enhancing dependability through a distribution of predictions. Our focus lies on the Vision Transformer (ViT), a DL model that harmonizes both local and global behavior. We conduct extensive experiments on the ImageNet-1K dataset, a vast resource with over a million images across 1,000 categories. ViTs, while competitive, are vulnerable to adversarial attacks, making uncertainty estimation crucial for …

Uncertainty-Adjusted Inductive Matrix Completion With Graph Neural Networks, Petr Kasalicky, Antoine Ledent, Rodrigo Alves

Research Collection School Of Computing and Information Systems

We propose a robust recommender systems model which performs matrix completion and a ratings-wise uncertainty estimation jointly. Whilst the prediction module is purely based on an implicit low-rank assumption imposed via nuclear norm regularization, our loss function is augmented by an uncertainty estimation module which learns an anomaly score for each individual rating via a Graph Neural Network: data points deemed more anomalous by the GNN are downregulated in the loss function used to train the low-rank module. The whole model is trained in an end-to-end fashion, allowing the anomaly detection module to tap on the supervised information available in …

Research On Period Emergency Supply Distribution Optimization Under Uncertainty, Li Zhang, Mingling He, Qiushuang Yin, Ning Li, Le'an Yu

Journal of System Simulation

Abstract: Aiming at the uncertainty and multi-periodicity of emergency supply distribution, a novel period vehicle routing problem(PVRP) multi-objective optimization model is built and a three-step optimization method is proposed. A triangular fuzzy number is used to eliminate the uncertainty. An AHP approach is used to transform the multi-objective function into the single objective function. An improved ACO algorithm is proposed to solve the single objective optimization problem. By classical data set, the time effectiveness of proposed method on emergency supply distribution problem is verified. The computational advantage in convergence speed is proved by the comparative analysis of the proposed …

Avoiding Starvation Of Arms In Restless Multi-Armed Bandit, Dexun Li, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Restless multi-armed bandits (RMAB) is a popular framework for optimizing performance with limited resources under uncertainty. It is an extremely useful model for monitoring beneficiaries (arms) and executing timely interventions using health workers (limited resources) to ensure optimal benefit in public health settings. For instance, RMAB has been used to track patients' health and monitor their adherence in tuberculosis settings, ensure pregnant mothers listen to automated calls about good pregnancy practices, etc. Due to the limited resources, typically certain individuals, communities, or regions are starved of interventions, which can potentially have a significant negative impact on the individual/community in the …

Performance Analysis Of Empirical Open-Circuit Voltage Modeling In Lithium-Ion Batteries, Part-3: Experimental Results, Prarthana Pillai, James Nguyen, Balakumar Balasingam

Computer Science Publications

This paper is the third part of a series of papers about empirical approaches to open circuit voltage (OCV) modeling of lithium-ion batteries. The first part of the series proposed models to quantify various sources of uncertainties in the OCV models; the second part of the series presented systematic data collection approaches to compute the uncertainties in the OCV to state of charge (SOC) models. This paper uses data collected from 28 OCV characterization experiments, performed according to the data collection plan presented in the second part, to compute and analyze three OCV uncertainty metrics: cell-to-cell variations, C-Rate error, and …

A Comparative Assessment Of Human Factors In Cybersecurity: Implications For Cyber Governance, Muhammad Umair Shah, Farkhund Iqbal, Umair Rehman, Patrick C.K. Hung

All Works

This paper provides an extensive overview of cybersecurity awareness in the young, educated, and technology-savvy population of the United Arab Emirates (UAE), compared to the United States of America (USA) for advancing the scholarship and practice of global cyber governance. We conducted comparative empirical studies to identify differences in specific human factors that affect cybersecurity behaviour in the UAE and the USA. In addition, we employed several control variables to observe reliable results. We used Hofstede’s theoretical framework on culture to advance our investigation. The results show that the targeted population in the UAE exhibits contrasting interpretations of cybersecurity awareness …

Fuzzy Reasoning Procedure For Ontologies Based On Rough Membership Approximation, Armand Florentin Donfack Kana, Babatunde Opeoluwa Akinkunmi

Future Computing and Informatics Journal

One of the major challenges in modeling a real-world domain is how to effectively represent uncertain and incomplete knowledge of that domain. Several techniques for representing uncertainty in ontologies have been proposed with some of the techniques lacking provision for vague inference. The classical tableaux-based algorithm does not provide the flexibility for reasoning over such vague ontologies. However, several extensions of the tableaux-based algorithm have been proposed to cope with fuzzy reasoning. Similarly, several alternative reasoning methods for incomplete, inconsistent, and uncertain ontologies have been proposed. One of the major limitations of most of those techniques is that they require …

Learning Scenario Representation For Solving Two-Stage Stochastic Integer Programs, Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang

Research Collection School Of Computing and Information Systems

Many practical combinatorial optimization problems under uncertainty can be modeled as stochastic integer programs (SIPs), which are extremely challenging to solve due to the high complexity. To solve two-stage SIPs efficiently, we propose a conditional variational autoencoder (CVAE) based method to learn scenario representation for a class of SIP instances. Specifically, we design a graph convolutional network based encoder to embed each scenario with the deterministic part of its instance (i.e. context) into a low-dimensional latent space, from which a decoder reconstructs the scenario from its latent representation conditioned on the context. Such a design effectively captures the dependencies of …

Knowledge Graph Embedding By Normalizing Flows, Changyi Xiao, Xiangnan He, Yixin Cao

Research Collection School Of Computing and Information Systems

A key to knowledge graph embedding (KGE) is to choose a proper representation space, e.g., point-wise Euclidean space and complex vector space. In this paper, we propose a unified perspective of embedding and introduce uncertainty into KGE from the view of group theory. Our model can incorporate existing models (i.e., generality), ensure the computation is tractable (i.e., efficiency) and enjoy the expressive power of complex random variables (i.e., expressiveness). The core idea is that we embed entities/relations as elements of a symmetric group, i.e., permutations of a set. Permutations of different sets can reflect different properties of embedding. And the …

Uncertainty Simulation Method Based On Deep Bayesian Networks Learning, Nie Kai, Kejun Zeng, Qinghai Meng

Journal of System Simulation

Abstract: There are lots of uncertain elements in battlefields situation assessment and the uncertainty simulation would enhance the ability of situation assessment. A deep variational autoencoder bayesian networks (BN) model with memory module is proposed aiming at the problem of being unable to represent the uncertainties exactly caused by the various combat objects and more uncertain elements. Based on the deep BN learning, the situation assessment model is designed from the deep generative model. The principle of deep generative model mixing with the memory module is discussed and the leaning and reasoning process of the model is explained. The proposed …

Jointly-Learnt Networks For Future Action Anticipation Via Self-Knowledge Distillation And Cycle Consistency, Md Moniruzzaman, Zhaozheng Yin, Zhihai He, Ming-Chuan Leu, Ruwen Qin

Mechanical and Aerospace Engineering Faculty Research & Creative Works

Future action anticipation aims to infer future actions from the observation of a small set of past video frames. In this paper, we propose a novel Jointly learnt Action Anticipation Network (J-AAN) via Self-Knowledge Distillation (Self-KD) and cycle consistency for future action anticipation. In contrast to the current state-of-the-art methods which anticipate the future actions either directly or recursively, our proposed J-AAN anticipates the future actions jointly in both direct and recursive ways. However, when dealing with future action anticipation, one important challenge to address is the future's uncertainty since multiple action sequences may come from or be followed by …

Indigeneity And Spatial Information Science, Matt Duckham, Serene Ho

Journal of Spatial Information Science

Spatial information science has given rise to a set of concepts, tools, and techniques for understanding our geographic world. In turn, the technologies built on this body of knowledge embed certain ways of knowing." This vision paper traces the roots and impacts of those embeddings and explores how they can sometimes be inherently at odds with or completely subvert Indigenous Peoples' ways of knowing. However advancements in spatial information science offer opportunities for innovation whilst working towards reconciliation. We highlight as examples four active research topics in the field to support a call to action for greater inclusion of Indigenous …

How Well Do We Really Know The World? Uncertainty In Giscience, Michael F. Goodchild

Journal of Spatial Information Science

There are many reasons why geospatial data are not geography, but merely representations of it. Thus geospatial data will always leave their user uncertain about the true nature of the world. Over the past three decades uncertainty has become the focus of significant research in GIScience. This paper reviews the reasons for uncertainty, its various dimensions from measurement to modeling, visualization, and propagation. The later sections of the paper explore the implications of current trends, specifically data science, new data sources, and replicability, and the new questions these are posing for GIScience research in the coming years.

Exploring The Effectiveness Of Geomasking Techniques For Protecting The Geoprivacy Of Twitter Users, Song Gao, Jinmeng Rao, Xinyi Liu, Yuhao Kang, Qunying Huang, Joseph App

Journal of Spatial Information Science

With the ubiquitous use of location-based services, large-scale individual-level location data has been widely collected through location-awareness devices. Geoprivacy concerns arise on the issues of user identity de-anonymization and location exposure. In this work, we investigate the effectiveness of geomasking techniques for protecting the geoprivacy of active Twitter users who frequently share geotagged tweets in their home and work locations. By analyzing over 38,000 geotagged tweets of 93 active Twitter users in three U.S. cities, the two-dimensional Gaussian masking technique with proper standard deviation settings is found to be more effective to protect user's location privacy while sacrificing geospatial analytical …

Active Learning Intelligent Soft Sensor Based On Probability Selection, Xuezhi Dai, Weili Xiong

Journal of System Simulation

Abstract: Aiming at lack of tag samples and high cost of sampling tags in complex industrial processes, an active learning algorithm based on probability selection is proposed. Firstly, unlabeled samples are performed subspace integration by using the principal component analysis. Then, the information of unlabeled samples is evaluated by the uncertainty, which is calculated based on the out put of all sub learners. And the most valuable samples are selected to mark manually. Finally, the function of unlabeled samples and labeled samples are analyzed, and the termination conditions are designed by introducing the performance index of training set. Through simulations …

Compact Representations Of Uncertainty In Clustering, Craig Stuart Greenberg

Doctoral Dissertations

Flat clustering and hierarchical clustering are two fundamental tasks, often used to discover meaningful structures in data, such as subtypes of cancer, phylogenetic relationships, taxonomies of concepts, and cascades of particle decays in particle physics. When multiple clusterings of the data are possible, it is useful to represent uncertainty in clustering through various probabilistic quantities, such as the distribution over partitions or tree structures, and the marginal probabilities of subpartitions or subtrees. Many compact representations exist for structured prediction problems, enabling the efficient computation of probability distributions, e.g., a trellis structure and corresponding Forward-Backward algorithm for Markov models that model …

Increasing The Value Of Information During Planning In Uncertain Environments, Gaurab Pokharel

Honors Papers

Prior studies have demonstrated that for many real-world problems, POMDPs can be solved through online algorithms both quickly and with near optimality [10, 8, 6]. However, on an important set of problems where there is a large time delay between when the agent can gather information and when it needs to use that information, these solutions fail to adequately consider the value of information. As a result, information gathering actions, even when they are critical in the optimal policy, will be ignored by existing solutions, leading to sub-optimal decisions by the agent. In this research, we develop a novel solution …

Reliable And Interpretable Machine Learning For Modeling Physical And Cyber Systems, Daniel L. Marino Lizarazo

Theses and Dissertations

Over the past decade, Machine Learning (ML) research has predominantly focused on building extremely complex models in order to improve predictive performance. The idea was that performance can be improved by adding complexity to the models. This approach proved to be successful in creating models that can approximate highly complex relationships while taking advantage of large datasets. However, this approach led to extremely complex black-box models that lack reliability and are difficult to interpret. By lack of reliability, we specifically refer to the lack of consistent (unpredictable) behavior in situations outside the training data. Lack of interpretability refers to the …

A New Method For Optimal Expansion Planning In Electrical Energy Distributionnetworks With Distributed Generation Resources Considering Uncertainties, Amir Masoud Mohaghegh, S Yaser Derakhshandeh, Abbas Kargar

Turkish Journal of Electrical Engineering and Computer Sciences

The present study aims to introduce a robust model for distribution network expansion planning considering system uncertainties. The proposed method determines optimal size and placement of distributed generation resources, as well as installation and reinforcement of feeders and substations. This model is designed to minimize cost and to determine the best time for the installation of equipment in the expansion planning. In the proposed expansion planning, the fuzzy logic theory is employed to model uncertainties of loads and energy price. Also, since the proposed model is a nonlinear and nonconvex optimization problem, a tri-stage algorithm is developed to solve it. …

Optimal Planning Dg And Bes Units In Distribution System Consideringuncertainty Of Power Generation And Time-Varying Load, Mansur Khasanov, Salah Kamel, Ayman Awad, Francisco Jurado

Turkish Journal of Electrical Engineering and Computer Sciences

Global environmental problems associated with traditional energy generation have led to a rapid increasein the use of renewable energy sources (RES) in power systems. The integration of renewable energy technologiesis commercially available nowadays, and the most common of such RES technology is photovoltaic (PV). This paperproposes an application of hybrid teaching-learning and artificial bee colony (TLABC) technique for determining theoptimal allocation of PV based distributed generation (DG) and battery energy storage (BES) units in the distributionsystem (DS) with the aim of minimizing the total power losses. Besides, some potential nodes identified by the powerloss sensitivity factor (PLSF). Thereupon TLABC is …

Communicating Uncertain Information From Deep Learning Models In Human Machine Teams, Harishankar V. Subramanian, Casey I. Canfield, Daniel Burton Shank, Luke Andrews, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

The role of human-machine teams in society is increasing, as big data and computing power explode. One popular approach to AI is deep learning, which is useful for classification, feature identification, and predictive modeling. However, deep learning models often suffer from inadequate transparency and poor explainability. One aspect of human systems integration is the design of interfaces that support human decision-making. AI models have multiple types of uncertainty embedded, which may be difficult for users to understand. Humans that use these tools need to understand how much they should trust the AI. This study evaluates one simple approach for communicating …

Co2vec: Embeddings Of Co-Ordered Networks Based On Mutual Reinforcement, Meng-Fen Chiang, Ee-Peng Lim, Wang-Chien Lee, Philips Kokoh Prasetyo

Research Collection School Of Computing and Information Systems

We study the problem of representation learning for multiple types of entities in a co-ordered network where order relations exist among entities of the same type, and association relations exist across entities of different types. The key challenge in learning co-ordered network embedding is to preserve order relations among entities of the same type while leveraging on the general consistency in order relations between different entity types. In this paper, we propose an embedding model, CO2Vec, that addresses this challenge using mutually reinforced order dependencies. Specifically, CO2Vec explores in-direct order dependencies as supplementary evidence to enhance order representation learning across …

Establishing Topological Data Analysis: A Comparison Of Visualization Techniques, Tanmay J. Kotha

USF Tampa Graduate Theses and Dissertations

When visualizing data, we would like to convey both the data and the uncertainty associated with it. There are many incentives to do this, ranging from hurricane path projection to geographical surveys. Important decision making tasks rely upon humans perceiving a clear picture of the data and having confidence in their decisions. Topological Data Analysis has the potential to visualize the data as features or hierarchies in ways that are familiar to human intuition, and thus could help us convey the variation associated with uncertainty.

In this thesis, we evaluate four visualization techniques: color maps, isocontours, Reeb graphs, and persistence …