Open Access. Powered by Scholars. Published by Universities.®

Physical Sciences and Mathematics Commons™

Open Access. Powered by Scholars. Published by Universities.®

Discipline
Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 25591 - 25620 of 302624

Full-Text Articles in Physical Sciences and Mathematics

Graph Neural Networks For Inverse Problems With Flexible Meshes, William Herzberg Oct 2022

Graph Neural Networks For Inverse Problems With Flexible Meshes, William Herzberg

Dissertations (1934 -)

This thesis addresses the electrical impedance tomography (EIT) image reconstruction problem where samples may have irregular discretizations and presents two, new, learned reconstruction algorithms which leverage a graph framework. These new frameworks consider the irregular, non-uniform data as a graph thus allowing graph neural networks to be applied directly to the data defined over irregular meshes. Currently in imaging, convolutional neural networks are used most frequently in learned methods because they are spatially invariant and have the ability to leverage localized information. In addition, many images are represented by rows and columns of uniformly sized pixels which can easily be …

Go to article

How To Describe Variety Of A Probability Distribution: A Possible Answer To Yager's Question, Vladik Kreinovich Oct 2022

How To Describe Variety Of A Probability Distribution: A Possible Answer To Yager's Question, Vladik Kreinovich

Departmental Technical Reports (CS)

Entropy is a natural measure of randomness. It progresses from its smallest possible value 0 -- when we have a deterministic case in which one alternative i occurs with probability 1 (pi = 1), to the largest possible value which is attained at a uniform distribution p1 = ... = pn = 1/n. Intuitively, both in the deterministic case and in the uniform distribution case, there is not much variety in the distribution, while in the intermediate cases, when we have several different values pi, there is a strong variety. Entropy does not seem to capture this notion of variety. …

Go to article

How The Pavement Strength Changes With Time: Ai Ideas Help To Explain Semi-Empirical Formulas, Edgar Daniel Rodriguez Velasquez, Vladik Kreinovich Oct 2022

How The Pavement Strength Changes With Time: Ai Ideas Help To Explain Semi-Empirical Formulas, Edgar Daniel Rodriguez Velasquez, Vladik Kreinovich

Departmental Technical Reports (CS)

In this paper, we use AI ideas to provide a theoretical explanation for semi-empirical formulas that describe how the pavement strength changes with time, and how we can predict the pavement lifetime.

Go to article

Designing A Patient-Centered Clinical Workflow To Assess Cyberbully Experiences Of Youths In The U.S. Healthcare System, Fayika Farhat Nova Oct 2022

Designing A Patient-Centered Clinical Workflow To Assess Cyberbully Experiences Of Youths In The U.S. Healthcare System, Fayika Farhat Nova

Dissertations (1934 -)

Cyberbullying or online harassment is often defined as when someone repeatedly and intentionally harasses, mistreats, or makes fun of others aiming to scare, anger or shame them using electronic devices [296]. Youths experiencing cyberbullying report higher levels of anxiety and depression, mental distress, suicide thoughts, and substance abuse than their non-bullied peers [360, 605, 261, 354]. Even though bullying is associated with significant health problems, to date, very little youth anti-bullying efforts are initiated and directed in clinical settings. There is presently no standardized procedure or workflow across health systems for systematically assessing cyberbullying or other equally dangerous online activities …

Go to article

Investigating Accessibility Challenges And Opportunities For Users With Low Vision Disabilities In Customer-To-Customer (C2c) Marketplaces, Bektur Ryskeldiev, Kotaro Hara, Mariko Kobayashi, Koki Kusano Oct 2022

Investigating Accessibility Challenges And Opportunities For Users With Low Vision Disabilities In Customer-To-Customer (C2c) Marketplaces, Bektur Ryskeldiev, Kotaro Hara, Mariko Kobayashi, Koki Kusano

Research Collection School Of Computing and Information Systems

Inaccessible e-commerce websites and mobile applications exclude people with visual impairments (PVI) from online shopping. Customer-to-customer (C2C) marketplaces, a form of e-commerce where trading happens not between businesses and customers but between customers, could pose a unique set of challenges in the interactions that the platform brings about. Through online questionnaire and remote interviews, we investigate problems experienced by people with low vision disabilities in common C2C scenarios. Our study with low vision participants (N = 12) reveal both previously known general accessibility issues (e.g., web and mobile interface accessibility) and C2C specific accessibility issues (e.g., inability to confirm item …

Go to article

Cvfnet: Real-Time 3d Object Detection By Learning Cross View Features, Jiaqi Gu, Zhiyu Xiang, Pan Zhao, Tingming Bai, Lingxuan Wang, Xijun Zhao, Zhiyuan Zhang Oct 2022

Cvfnet: Real-Time 3d Object Detection By Learning Cross View Features, Jiaqi Gu, Zhiyu Xiang, Pan Zhao, Tingming Bai, Lingxuan Wang, Xijun Zhao, Zhiyuan Zhang

Research Collection School Of Computing and Information Systems

In recent years 3D object detection from LiDAR point clouds has made great progress thanks to the development of deep learning technologies. Although voxel or point based methods are popular in 3D object detection, they usually involve time-consuming operations such as 3D convolutions on voxels or ball query among points, making the resulting network inappropriate for time critical applications. On the other hand, 2D view-based methods feature high computing efficiency while usually obtaining inferior performance than the voxel or point based methods. In this work, we present a real-time view-based single stage 3D object detector, namely CVFNet to fulfill this …

Go to article

Overview Of The Clpsych 2022 Shared Task: Capturing Moments Of Change In Longitudinal User Posts, Adam Tsakalidis, Jenny Chim, Iman Munire Bilal, Ayah Zirikly, Dana Atzil-Slonim, Federico Nanni, Philip Resnik, Manas Gaur, Kaushik Roy, Becky Inkster, Jeff Leintz, Maria Liakata Oct 2022

Overview Of The Clpsych 2022 Shared Task: Capturing Moments Of Change In Longitudinal User Posts, Adam Tsakalidis, Jenny Chim, Iman Munire Bilal, Ayah Zirikly, Dana Atzil-Slonim, Federico Nanni, Philip Resnik, Manas Gaur, Kaushik Roy, Becky Inkster, Jeff Leintz, Maria Liakata

Publications

We provide an overview of the CLPsych 2022 Shared Task, which focusses on the automatic identification of Moments of Change in longitudinal posts by individuals on social media and its connection with information regarding mental health . This year's task introduced the notion of longitudinal modelling of the text generated by an individual online over time, along with appropriate temporally sensitive evaluation metrics. The Shared Task consisted of two subtasks: (a) the main task of capturing changes in an individual's mood (drastic changes-`Switches'- and gradual changes -`Escalations'- on the basis of textual content shared online; and subsequently (b) the sub-task …

Go to article

Control Of Dy 164 Bose-Einstein Condensate Phases And Dynamics With Dipolar Anisotropy, S. Halder, K. Mukherjee, Simeon I. Mistakidis, S. Das, P. G. Kevrekidis, P. K. Panigrahi, S. Majumder, H. R. Sadeghpour Oct 2022

Control Of Dy 164 Bose-Einstein Condensate Phases And Dynamics With Dipolar Anisotropy, S. Halder, K. Mukherjee, Simeon I. Mistakidis, S. Das, P. G. Kevrekidis, P. K. Panigrahi, S. Majumder, H. R. Sadeghpour

Physics Faculty Research & Creative Works

We Investigate The Quench Dynamics Of Quasi-One- And Two-Dimensional Dipolar Bose-Einstein Condensates Of Dy164 Atoms Under The Influence Of A Fast Rotating Magnetic Field. The Magnetic Field Thus Controls Both The Magnitude And Sign Of The Dipolar Potential. We Account For Quantum Fluctuations, Critical To Formation Of Exotic Quantum Droplet And Supersolid Phases In The Extended Gross-Pitaevskii Formalism, Which Includes The So-Called Lee-Huang-Yang Correction. An Analytical Variational Ansatz Allows Us To Obtain The Phase Diagrams Of The Superfluid And Droplet Phases. The Crossover From The Superfluid To The Supersolid Phase And To Single And Droplet Arrays Is Probed With Particle …

Go to article

Noisy Label Regularisation For Textual Regression, Yuxia Wang, Timothy Baldwin, Karin Verspoor Oct 2022

Noisy Label Regularisation For Textual Regression, Yuxia Wang, Timothy Baldwin, Karin Verspoor

Natural Language Processing Faculty Publications

Training with noisy labelled data is known to be detrimental to model performance, especially for high-capacity neural network models in low-resource domains. Our experiments suggest that standard regularisation strategies, such as weight decay and dropout, are ineffective in the face of noisy labels. We propose a simple noisy label detection method that prevents error propagation from the input layer. The approach is based on the observation that the projection of noisy labels is learned through memorisation at advanced stages of learning, and that the Pearson correlation is sensitive to outliers. Extensive experiments over real-world human-disagreement annotations as well as randomly-corrupted …

Go to article

Contact Process With Simultaneous Spatial And Temporal Disorder, Xuecheng Ye, Thomas Vojta Oct 2022

Contact Process With Simultaneous Spatial And Temporal Disorder, Xuecheng Ye, Thomas Vojta

Physics Faculty Research & Creative Works

We study the absorbing-state phase transition in the one-dimensional contact process under the combined influence of spatial and temporal random disorders. We focus on situations in which the spatial and temporal disorders decouple. Couched in the language of epidemic spreading, this means that some spatial regions are, at all times, more favorable than others for infections, and some time periods are more favorable than others independent of spatial location. We employ a generalized Harris criterion to discuss the stability of the directed percolation universality class against such disorder. We then perform large-scale Monte Carlo simulations to analyze the critical behavior …

Go to article

Sum Rules For Energy Deposition Eigenchannels In Scattering Systems, Alexey Yamilov, Nicholas Bender, Hui Cao Oct 2022

Sum Rules For Energy Deposition Eigenchannels In Scattering Systems, Alexey Yamilov, Nicholas Bender, Hui Cao

Physics Faculty Research & Creative Works

In a random-scattering system, the deposition matrix maps the incident wavefront onto the internal field distribution across a target volume. The corresponding eigenchannels have been used to enhance the wave energy delivered to the target. Here, we find the sum rules for the eigenvalues and eigenchannels of the deposition matrix in any system geometry: including two- and three-dimensional scattering systems, as well as narrow waveguides and wide slabs. We derive a number of constraints on the eigenchannel intensity distributions inside the system as well as the corresponding eigenvalues. Our results are general and applicable to random systems of arbitrary scattering …

Go to article

Quality Of Life In Older And Younger People With Hiv And Diabetes, Lauren F. O’Connor, La’Marcus Wingate, Sam Simmens, Amanda D. Castel, Anne K. Monroe Oct 2022

Quality Of Life In Older And Younger People With Hiv And Diabetes, Lauren F. O’Connor, La’Marcus Wingate, Sam Simmens, Amanda D. Castel, Anne K. Monroe

Epidemiology Faculty Posters and Presentations

No abstract provided.

Go to article

Problematic Internet Usage: The Impact Of Objectively Recorded And Categorized Usage Time, Emotional Intelligence Components And Subjective Happiness About Usage, Sameha Alshakhsi, Khansa Chemnad, Mohamed Basel Almourad, Majid Altuwairiqi, John Mcalaney, Raian Ali Oct 2022

Problematic Internet Usage: The Impact Of Objectively Recorded And Categorized Usage Time, Emotional Intelligence Components And Subjective Happiness About Usage, Sameha Alshakhsi, Khansa Chemnad, Mohamed Basel Almourad, Majid Altuwairiqi, John Mcalaney, Raian Ali

All Works

Most research on Problematic Internet Usage (PIU) relied on self-report data when measuring the time spent on the internet. Self-reporting of use, typically done through a survey, showed discrepancies from the actual amount of use. Studies exploring the association between trait emotional intelligence (EI) components and the subjective feeling on technology usage and PIU are also limited. The current cross-sectional study aims to examine whether the objectively recorded technology usage, taking smartphone usage as a representative, components of trait EI (sociability, emotionality, well-being, self-control), and happiness with phone use can predict PIU and its components (obsession, neglect, and control disorder). …

Go to article

Rootasrole: A Security Module To Manage The Administrative Privileges For Linux, Ahmad Samer Wazan, David W Chadwick, Remi Venant, Eddie Billoir, Romain Laborde, Liza Ahmad, Mustafa Kaiiali Oct 2022

Rootasrole: A Security Module To Manage The Administrative Privileges For Linux, Ahmad Samer Wazan, David W Chadwick, Remi Venant, Eddie Billoir, Romain Laborde, Liza Ahmad, Mustafa Kaiiali

All Works

Today, Linux users use sudo/su commands to attribute Linux’s administrative privileges to their programs. These commands always give the whole list of administrative privileges to Linux programs, unless there are pre-installed default policies defined by Linux Security Modules(LSM). LSM modules require users to inject the needed privileges into the memory of the process and to declare the needed privileges in an LSM policy. This approach can work for users who have good knowledge of the syntax of LSM modules’ policies. Adding or editing an existing policy is a very time-consuming process because LSM modules require adding a complete list of …

Go to article

2022 October - Tennessee Monthly Climate Report, Tennessee Climate Office, East Tennessee State University Oct 2022

2022 October - Tennessee Monthly Climate Report, Tennessee Climate Office, East Tennessee State University

Tennessee Climate Office Monthly Report

No abstract provided.

Go to article

Reversible Dioxygen Binding To Co(Ii) Complexes With Noninnocent Ligands, Praveen Kumar, Laxmi Devkota, Maximilian C. Casey, Anne A. Fischer, Sergey V. Lindeman, Adam T. Fiedler Oct 2022

Reversible Dioxygen Binding To Co(Ii) Complexes With Noninnocent Ligands, Praveen Kumar, Laxmi Devkota, Maximilian C. Casey, Anne A. Fischer, Sergey V. Lindeman, Adam T. Fiedler

Chemistry Faculty Research and Publications

A series of mononuclear Co(II) complexes with noninnocent (redox-active) ligands are prepared that exhibit metal–ligand cooperativity during the reversible binding of O2. The complexes have the general formula, [CoII(LS,N)(TpR2)] (R = Me, Ph), where LS,N is a bidentate o-aminothiophenolate and TpR2 is a hydrotris(pyrazol-1-yl)borate scorpionate with R-substituents at the 3- and 5-positions. Exposure to O2 at room temperature results in one-electron oxidation and deprotonation of LS,N. The oxidized derivatives possess substantial “singlet diradical” character arising from antiferromagnetic coupling between an iminothiosemiquinonate (ITSQ•–) …

Go to article

Chemical Interactions And Cytotoxicity Of Terpene And Diluent Vaping Ingredients, Yanira Baldovinos, Alexandra Archer, James C. Salamanca, Robert M. Strongin, Christie Sayes Oct 2022

Chemical Interactions And Cytotoxicity Of Terpene And Diluent Vaping Ingredients, Yanira Baldovinos, Alexandra Archer, James C. Salamanca, Robert M. Strongin, Christie Sayes

Chemistry Faculty Publications and Presentations

Vaping devices have risen in popularity since their inception in 2007. The practice involves using a variety of commercially available devices. Internal heating systems in devices aerosolize e-liquid formulations of complex mixtures including an active ingredient (e.g., THC, CBD, and nicotine), diluents (or cutting agents), solvents, and flavoring agents (e.g., terpenes and aldehydes). The vaping toxicology literature consists of cytotoxicity studies of individual chemicals and commercial formulas. Because of the variation of e-liquid composition, there is a limited understanding of the toxicity of ingredient combinations. This study analyzed the cytotoxic effects after exposure to individual and binary mixtures of a …

Go to article

Dynamic Temporal Filtering In Video Models, Fuchen Long, Zhaofan Qiu, Yingwei Pan, Ting Yao, Chong-Wah Ngo, Tao Mei Oct 2022

Dynamic Temporal Filtering In Video Models, Fuchen Long, Zhaofan Qiu, Yingwei Pan, Ting Yao, Chong-Wah Ngo, Tao Mei

Research Collection School Of Computing and Information Systems

Video temporal dynamics is conventionally modeled with 3D spatial-temporal kernel or its factorized version comprised of 2D spatial kernel and 1D temporal kernel. The modeling power, nevertheless, is limited by the fixed window size and static weights of a kernel along the temporal dimension. The pre-determined kernel size severely limits the temporal receptive fields and the fixed weights treat each spatial location across frames equally, resulting in sub-optimal solution for longrange temporal modeling in natural scenes. In this paper, we present a new recipe of temporal feature learning, namely Dynamic Temporal Filter (DTF), that novelly performs spatial-aware temporal modeling in …

Go to article

Wave-Vit: Unifying Wavelet And Transformers For Visual Representation Learning, Ting Yao, Yingwei Pan, Yehao Li, Chong-Wah Ngo, Tao Mei Oct 2022

Wave-Vit: Unifying Wavelet And Transformers For Visual Representation Learning, Ting Yao, Yingwei Pan, Yehao Li, Chong-Wah Ngo, Tao Mei

Research Collection School Of Computing and Information Systems

Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks, while the self-attention computation in Transformer scales quadratically w.r.t. the input patch number. Thus, existing solutions commonly employ down-sampling operations (e.g., average pooling) over keys/values to dramatically reduce the computational cost. In this work, we argue that such over-aggressive down-sampling design is not invertible and inevitably causes information dropping especially for high-frequency components in objects (e.g., texture details). Motivated by the wavelet theory, we construct a new Wavelet Vision Transformer (Wave-ViT) that formulates the invertible down-sampling with wavelet transforms and self-attention learning in a unified way. …

Go to article

Long-Term Leap Attention, Short-Term Periodic Shift For Video Classification, Hao Zhang, Lechao Cheng, Yanbin Hao, Chong-Wah Ngo Oct 2022

Long-Term Leap Attention, Short-Term Periodic Shift For Video Classification, Hao Zhang, Lechao Cheng, Yanbin Hao, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Video transformer naturally incurs a heavier computation burden than a static vision transformer, as the former processes �� times longer sequence than the latter under the current attention of quadratic complexity (�� 2�� 2 ). The existing works treat the temporal axis as a simple extension of spatial axes, focusing on shortening the spatio-temporal sequence by either generic pooling or local windowing without utilizing temporal redundancy. However, videos naturally contain redundant information between neighboring frames; thereby, we could potentially suppress attention on visually similar frames in a dilated manner. Based on this hypothesis, we propose the LAPS, a long-term “Leap …

Go to article

Interactive Video Corpus Moment Retrieval Using Reinforcement Learning, Zhixin Ma, Chong-Wah Ngo Oct 2022

Interactive Video Corpus Moment Retrieval Using Reinforcement Learning, Zhixin Ma, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Known-item video search is effective with human-in-the-loop to interactively investigate the search result and refine the initial query. Nevertheless, when the first few pages of results are swamped with visually similar items, or the search target is hidden deep in the ranked list, finding the know-item target usually requires a long duration of browsing and result inspection. This paper tackles the problem by reinforcement learning, aiming to reach a search target within a few rounds of interaction by long-term learning from user feedbacks. Specifically, the system interactively plans for navigation path based on feedback and recommends a potential target that …

Go to article

Mando: Multi-Level Heterogeneous Graph Embeddings For Fine-Grained Detection Of Smart Contract Vulnerabilities, Huu Hoang Nguyen, Nhat Minh Nguyen, Chunyao Xie, Zahra Ahmadi, Daniel Kudenko, Thanh Nam Doan, Lingxiao Jiang Oct 2022

Mando: Multi-Level Heterogeneous Graph Embeddings For Fine-Grained Detection Of Smart Contract Vulnerabilities, Huu Hoang Nguyen, Nhat Minh Nguyen, Chunyao Xie, Zahra Ahmadi, Daniel Kudenko, Thanh Nam Doan, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Learning heterogeneous graphs consisting of different types of nodes and edges enhances the results of homogeneous graph techniques. An interesting example of such graphs is control-flow graphs representing possible software code execution flows. As such graphs represent more semantic information of code, developing techniques and tools for such graphs can be highly beneficial for detecting vulnerabilities in software for its reliability. However, existing heterogeneous graph techniques are still insufficient in handling complex graphs where the number of different types of nodes and edges is large and variable. This paper concentrates on the Ethereum smart contracts as a sample of software …

Go to article

Towards Understanding The Faults Of Javascript-Based Deep Learning Systems, Lili Quan, Qianyu Guo, Xiaofei Xie, Sen Chen, Xiaohong Li, Yang Liu Oct 2022

Towards Understanding The Faults Of Javascript-Based Deep Learning Systems, Lili Quan, Qianyu Guo, Xiaofei Xie, Sen Chen, Xiaohong Li, Yang Liu

Research Collection School Of Computing and Information Systems

Quality assurance is of great importance for deep learning (DL) systems, especially when they are applied in safety-critical applications. While quality issues of native DL applications have been extensively analyzed, the issues of JavaScript-based DL applications have never been systematically studied. Compared with native DL applications, JavaScript-based DL applications can run on major browsers, making the platform- and device-independent. Specifically, the quality of JavaScript-based DL applications depends on the 3 parts: the application, the third-party DL library used and the underlying DL framework (e.g., TensorFlow.js), called JavaScript-based DL system. In this paper, we conduct the first empirical study on the …

Go to article

Compressing Pre-Trained Models Of Code Into 3 Mb, Jieke Shi, Zhou Yang, Bowen Xu, Hong Jin Kang, David Lo Oct 2022

Compressing Pre-Trained Models Of Code Into 3 Mb, Jieke Shi, Zhou Yang, Bowen Xu, Hong Jin Kang, David Lo

Research Collection School Of Computing and Information Systems

Although large pre-trained models of code have delivered significant advancements in various code processing tasks, there is an impediment to the wide and fluent adoption of these powerful models in software developers’ daily workflow: these large models consume hundreds of megabytes of memory and run slowly on personal devices, which causes problems in model deployment and greatly degrades the user experience. It motivates us to propose Compressor, a novel approach that can compress the pre-trained models of code into extremely small models with negligible performance sacrifice. Our proposed method formulates the design of tiny models as simplifying the pre-trained model …

Go to article

Improving Knowledge-Aware Recommendation With Multi-Level Interactive Contrastive Learning, Ding Zou, Wei Wei, Ziyang Wang, Xian-Ling Mao, Feida Zhu, Rui Fang, Dangyang Chen Oct 2022

Improving Knowledge-Aware Recommendation With Multi-Level Interactive Contrastive Learning, Ding Zou, Wei Wei, Ziyang Wang, Xian-Ling Mao, Feida Zhu, Rui Fang, Dangyang Chen

Research Collection School Of Computing and Information Systems

Incorporating Knowledge Graphs (KG) into recommeder system as side information has attracted considerable attention. Recently, the technical trend of Knowledge-aware Recommendation (KGR) is to develop end-to-end models based on graph neural networks (GNNs). However, the extremely sparse user-item interactions significantly degrade the performance of the GNN-based models, from the following aspects: 1) the sparse interaction, itself, means inadequate supervision signals and limits the supervised GNN-based models; 2) the combination of sparse interactions (CF part) and redundant KG facts (KG part) further results in an unbalanced information utilization. Besides, the GNN paradigm aggregates local neighbors for node representation learning, while ignoring …

Go to article

Social Access And Representation For Autistic Adult Livestreamers, Terrance Mok, Anthony Tang, Adam Mccrimmon, Lora Oehlberg Oct 2022

Social Access And Representation For Autistic Adult Livestreamers, Terrance Mok, Anthony Tang, Adam Mccrimmon, Lora Oehlberg

Research Collection School Of Computing and Information Systems

We interviewed 10 autistic livestreamers to understand their motivations for livestreaming on Twitch. Our participants explained that streaming helped them fulfill social desires by: supporting them in making meaningful social connections with others; giving them a safe space to practice social skills like “small talk”; and empowering them to be autistic role models and to share their true selves. This work offers an early report on how autistic individuals leverage livestreaming as a beneficial social platform while struggling with audience expectations.

Go to article

Pixel-Wise Energy-Biased Abstention Learning For Anomaly Segmentation On Complex Urban Driving Scenes, Yu Tian, Yuyuan Liu, Guansong Pang, Fengbei Liu, Yuanhong Chen, Gustavo Carneiro Oct 2022

Pixel-Wise Energy-Biased Abstention Learning For Anomaly Segmentation On Complex Urban Driving Scenes, Yu Tian, Yuyuan Liu, Guansong Pang, Fengbei Liu, Yuanhong Chen, Gustavo Carneiro

Research Collection School Of Computing and Information Systems

State-of-the-art (SOTA) anomaly segmentation approaches on complex urban driving scenes explore pixel-wise classification uncertainty learned from outlier exposure, or external reconstruction models. However, previous uncertainty approaches that directly associate high uncertainty to anomaly may sometimes lead to incorrect anomaly predictions, and external reconstruction models tend to be too inefficient for real-time self-driving embedded systems. In this paper, we propose a new anomaly segmentation method, named pixel-wise energy-biased abstention learning (PEBAL), that explores pixel-wise abstention learning (AL) with a model that learns an adaptive pixel-level anomaly class, and an energy-based model (EBM) that learns inlier pixel distribution. More specifically, PEBAL is …

Go to article

Physical Adversarial Attack On A Robotic Arm, Yifan Jia, Christopher M. Poskitt, Jun Sun, Sudipta Chattopadhyay Oct 2022

Physical Adversarial Attack On A Robotic Arm, Yifan Jia, Christopher M. Poskitt, Jun Sun, Sudipta Chattopadhyay

Research Collection School Of Computing and Information Systems

Collaborative Robots (cobots) are regarded as highly safety-critical cyber-physical systems (CPSs) owing to their close physical interactions with humans. In settings such as smart factories, they are frequently augmented with AI. For example, in order to move materials, cobots utilize object detectors based on deep learning models. Deep learning, however, has been demonstrated as vulnerable to adversarial attacks: a minor change (noise) to benign input can fool the underlying neural networks and lead to a different result. While existing works have explored such attacks in the context of picture/object classification, less attention has been given to attacking neural networks used …

Go to article

Outdoor Thermal Comfort Research In Transient Conditions: A Narrative Literature Review, Yuliya Dzyuban, Graces N. Y. Ching, Sin Kang Yik, Adrian J. Tan, Shreya Banerjee, Peter Jay Crank, Winston T. L. Chow Oct 2022

Outdoor Thermal Comfort Research In Transient Conditions: A Narrative Literature Review, Yuliya Dzyuban, Graces N. Y. Ching, Sin Kang Yik, Adrian J. Tan, Shreya Banerjee, Peter Jay Crank, Winston T. L. Chow

Research Collection College of Integrative Studies

In recent years, urban planners and designers are paying greater attention to Outdoor Thermal Comfort (OTC) studies due to the imminent threat of the Urban Heat Island and climate change on human health. Historically, indoor thermal comfort research assumed steady-state conditions, centralizing on the concept of thermal neutrality to determine optimal environmental parameters. Such research pivoted to investigating how non-steady-state, transient environmental conditions influence comfort. Recent studies underscore the usefulness of positive alliesthesia in providing a productive framework for OTC evaluation. In this article we first clarify the concepts related to thermal comfort-related terms, scales, and models in the literature. …

Go to article

Why We Should Remember The Soviet Information Age?, Ksenia Tatarchenko Oct 2022

Why We Should Remember The Soviet Information Age?, Ksenia Tatarchenko

Research Collection College of Integrative Studies

How to navigate the rapidly changing digital geopolitics of the world today? How do we make sense of digital transformation and its many social, political, cultural, and environmental implications at different locations around the world?

Go to article

First Prev Next Last