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

Computer Sciences Commons™

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

Discipline
Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 10651 - 10680 of 63030

Full-Text Articles in Computer Sciences

Towards Improving The Efficacy Of Windows Security Notifier For Apps From Unknown Publishers: The Role Of Rhetoric, Ankit Shrestha, Rizu Paudel, Prakriti Dumaru, Mahdi Nasrullah Al-Ameen Jul 2023

Towards Improving The Efficacy Of Windows Security Notifier For Apps From Unknown Publishers: The Role Of Rhetoric, Ankit Shrestha, Rizu Paudel, Prakriti Dumaru, Mahdi Nasrullah Al-Ameen

Computer Science Student Research

With over 1.4 billion users of Windows 10, it is the most widely used operating system in the world. In Windows, applications from unknown publishers are popular due to mass availability and ease of access. Installing such applications can lead to malware infection, including viruses and ransomware. Therefore, we explored the design of interventions to prevent the users from installing applications from unknown publishers. To this end, we conducted a lab study with nine participants to understand the perceptions and behavior of users toward the designed interventions. Then, we conducted an online study with 256 participants to evaluate the impact …

Go to article

How Do Pedestrians Perceive The Safety, Comfort, And Usefulness Of A Walking Space? An Exploratory Study Of Pedestrian Perception, Amanda Rifqa Marisa, Achmad Hery Fuad Jul 2023

How Do Pedestrians Perceive The Safety, Comfort, And Usefulness Of A Walking Space? An Exploratory Study Of Pedestrian Perception, Amanda Rifqa Marisa, Achmad Hery Fuad

Smart City

Car-oriented development has brought several negative impacts on human quality of life. Therefore, it is necessary to pay more attention to walkability as one of the essential aspects of it, especially in the urban area. In the meantime, most research on walking and walkability still overlooks the role of the pedestrian's perspective in examining walkability. Hence, this research tries to fill the gap in walkability research by exploring the pedestrian perspectives on the safety, comfort, and usefulness of walking space as the three overlapping aspects between walkability and walking needs. This research took context in Suryakencana, Bogor City, Indonesia. To …

Go to article

Exploring Mental Models For Explainable Artificial Intelligence: Engaging Cross-Disciplinary Teams Using A Design Thinking Approach, Helen Sheridan, Emma Murphy Dr., Dympna O'Sullivan Dr. Jul 2023

Exploring Mental Models For Explainable Artificial Intelligence: Engaging Cross-Disciplinary Teams Using A Design Thinking Approach, Helen Sheridan, Emma Murphy Dr., Dympna O'Sullivan Dr.

Conference papers

Exploring end-users’ understanding of Artificial Intelligence (AI) systems’ behaviours and outputs is crucial in developing accessible Explainable Artificial Intelligence (XAI) solutions. Investigating mental models of AI systems is core in understanding and explaining the often opaque, complex, and unpredictable nature of AI. Researchers engage surveys, interviews, and observations for software systems, yielding useful evaluations. However, an evaluation gulf still exists, primarily around comprehending end-users' understanding of AI systems It has been argued that by exploring theories related to human decision-making examining the fields of psychology, philosophy, and human computer interaction (HCI) in a more people-centric rather than product or technology-centric …

Go to article

Towards Enabling Haptic Communications Over 6g: Issues And Challenges, Muhammad Awais, Fasih Ullah Khan, Muhammad Zafar, Muhammad Mudassar, Muhammad Zaigham Zaheer, Khalid Mehmood Cheema, Muhammad Kamran, Woo Sung Jung Jul 2023

Towards Enabling Haptic Communications Over 6g: Issues And Challenges, Muhammad Awais, Fasih Ullah Khan, Muhammad Zafar, Muhammad Mudassar, Muhammad Zaigham Zaheer, Khalid Mehmood Cheema, Muhammad Kamran, Woo Sung Jung

Computer Vision Faculty Publications

This research paper provides a comprehensive overview of the challenges and potential solutions related to enabling haptic communication over the Tactile Internet in the context of 6G networks. The increasing demand for multimedia services and device proliferation has resulted in limited radio resources, posing challenges in their efficient allocation for Device-to-Device (D2D)-assisted haptic communications. Achieving ultra-low latency, security, and energy efficiency are crucial requirements for enabling haptic communication over TI. The paper explores various methodologies, technologies, and frameworks that can facilitate haptic communication, including backscatter communications (BsC), non-orthogonal multiple access (NOMA), and software-defined networks. Additionally, it discusses the potential of …

Go to article

Urban Memory Becomes An Idea In The Concept Of Spatial Planning (Study Case: Restoration Area Of Tambora District, West Jakarta), Riska Phillia, Antony Sihombing Jul 2023

Urban Memory Becomes An Idea In The Concept Of Spatial Planning (Study Case: Restoration Area Of Tambora District, West Jakarta), Riska Phillia, Antony Sihombing

Smart City

Urban heritage is a small part of the past of the city that holds the roots of the city's identity and culture, which are the city's identity. The strong identity of the historic area must be maintained, but this has a dilemma because of the need for change today. Therefore efforts are needed to create adaptive urban heritage areas. City spaces have a deep relationship with the people who inhabit them, with the most memorable or most memorable experiences and memories for them. This research contributes to exploring urban memory to develop conceptual spatial plans in restoration areas, using qualitative …

Go to article

Major Paths Changes In 2013-2022 To Walkability (Case Study: Dukuh Atas Tod), Daniel Harvey Tulis, Antony Sihombing Jul 2023

Major Paths Changes In 2013-2022 To Walkability (Case Study: Dukuh Atas Tod), Daniel Harvey Tulis, Antony Sihombing

Smart City

Development area with the concept of Transit Oriented Development (TOD) occurs so rapidly in big cities, which aims to create an integrated transportation system and is supported by the surrounding area. TOD area must have good road access for vehicles and space for pedestrians. Dukuh Atas TOD is one of the transit-oriented areas planned to be the largest TOD area in Jakarta so that developments are felt every year, including visuals and the road traffic system and pedestrian space. This research is using qualitative method by answering specific and actual variables. Time series analysis to see changes every year combined …

Go to article

Future Trends And Directions For Secure Infrastructure Architecture In The Education Sector: A Systematic Review Of Recent Evidence, Isaac Atta Senior Ampofo, Isaac Atta Junior Ampofo Jul 2023

Future Trends And Directions For Secure Infrastructure Architecture In The Education Sector: A Systematic Review Of Recent Evidence, Isaac Atta Senior Ampofo, Isaac Atta Junior Ampofo

Journal of Research Initiatives

The most efficient approach to giving large numbers of students’ access to computational resources is through a data center. A contemporary method for building the data center's computer infrastructure is the software-defined model, which enables user tasks to be processed in a reasonable amount of time and at a reasonable cost. The researcher examines potential directions and trends for a secured infrastructure design in this article. Additionally, interoperable, highly reusable modules that can include the newest trends in the education industry are made possible by cloud-based educational software. The Reference Architecture for University Education System Using AWS Services is presented …

Go to article

Examination Of Cybersecurity Technologies, Practices, Challenges, And Wish List In K-12 School Districts, Florence Martin, Julie Bacak, Erik Jon Byker, Weichao Wang, Jonathan Wagner, Lynn Ahlgrim-Delzell Jul 2023

Examination Of Cybersecurity Technologies, Practices, Challenges, And Wish List In K-12 School Districts, Florence Martin, Julie Bacak, Erik Jon Byker, Weichao Wang, Jonathan Wagner, Lynn Ahlgrim-Delzell

Journal of Cybersecurity Education, Research and Practice

With the growth in digital teaching and learning, there has been a sharp rise in the number of cybersecurity attacks on K-12 school networks. This has demonstrated a need for security technologies and cybersecurity education. This study examined security technologies used, effective security practices, challenges, concerns, and wish list of technology leaders in K-12 settings. Data collected from 23 district websites and from interviews with 12 district technology leaders were analyzed. Top security practices included cloud-based technologies, segregated network/V-LAN, two-factor authentication, limiting access, and use of Clever or Class Link. Top challenges included keeping users informed, lack of buy-in from …

Go to article

Cyberbullying: Senior Prospective Teachers’ Coping Knowledge And Strategies, Kürşat Arslan, İnan Aydın Jul 2023

Cyberbullying: Senior Prospective Teachers’ Coping Knowledge And Strategies, Kürşat Arslan, İnan Aydın

Journal of Cybersecurity Education, Research and Practice

This study aimed to determine senior prospective teachers’ coping knowledge and strategies for cyberbullying in terms of demographic variables. The sample consisted of 471 prospective teachers (324 female and 147 male) studying in the 4th grade in Dokuz Eylül University Buca Education Faculty in Izmir in the 2019-2020 academic year. It was a quantitative study using a causal-comparative research design to find out whether prospective teachers’ coping knowledge differed by independent variables. The "Coping with Cyberbullying Scale" developed by Koç et al. (2016) was employed to discover prospective teachers’ coping strategies for cyberbullying. A "Personal Information" form was also prepared …

Go to article

A Systematic Mapping Study On Gamification Applications For Undergraduate Cybersecurity Education, Sherri Weitl-Harms, Adam Spanier, John Hastings, Matthew Rokusek Jul 2023

A Systematic Mapping Study On Gamification Applications For Undergraduate Cybersecurity Education, Sherri Weitl-Harms, Adam Spanier, John Hastings, Matthew Rokusek

Journal of Cybersecurity Education, Research and Practice

Gamification in education presents a number of benefits that can theoretically facilitate higher engagement and motivation among students when learning complex, technical concepts. As an innovative, high-potential educational tool, many educators and researchers are attempting to implement more effective gamification into undergraduate coursework. Cyber Security Operations (CSO) education is no exception. CSO education traditionally requires comprehension of complex concepts requiring a high level of technical and abstract thinking. By properly applying gamification to complex CSO concepts, engagement in students should see an increase. While an increase is expected, no comprehensive study of CSO gamification applications (GA) has yet been undertaken …

Go to article

Editorial - 2023 - 1, Hossain Shahriar, Herbert J. Mattord, Michael E. Whitman Jul 2023

Editorial - 2023 - 1, Hossain Shahriar, Herbert J. Mattord, Michael E. Whitman

Journal of Cybersecurity Education, Research and Practice

No abstract provided.

Go to article

Sociocultural Barriers For Female Participation In Stem: A Case Of Saudi Women In Cybersecurity, Alanoud Aljuaid, Xiang Michelle Liu Jul 2023

Sociocultural Barriers For Female Participation In Stem: A Case Of Saudi Women In Cybersecurity, Alanoud Aljuaid, Xiang Michelle Liu

Journal of Cybersecurity Education, Research and Practice

The participation of women in Science, Technology, Engineering, and Mathematics (STEM) workforces is overwhelmingly low as compared to their male counterparts. The low uptake of cybersecurity careers has been documented in the previous studies conducted in the contexts of the West and Eastern worlds. However, most of the past studies mainly covered the Western world leaving more knowledge gaps in the context of Middle Eastern countries such as Saudi Arabia. Thus, to fill the existing knowledge gaps, the current study focused on women in Saudi Arabia. The aim of the study was to investigate the factors behind the underrepresentation of …

Go to article

Compete To Learn: Toward Cybersecurity As A Sport, Tj Oconnor, Dane Brown, Jasmine Jackson, Bryson Payne, Suzanna Schmeelk Jul 2023

Compete To Learn: Toward Cybersecurity As A Sport, Tj Oconnor, Dane Brown, Jasmine Jackson, Bryson Payne, Suzanna Schmeelk

Journal of Cybersecurity Education, Research and Practice

To support the workforce gap of skilled cybersecurity professionals, gamified pedagogical approaches for teaching cybersecurity have exponentially grown over the last two decades. During this same period, e-sports developed into a multi-billion dollar industry and became a staple on college campuses. In this work, we explore the opportunity to integrate e-sports and gamified cybersecurity approaches into the inaugural US Cyber Games Team. During this tenure, we learned many lessons about recruiting, assessing, and training cybersecurity teams. We share our approach, materials, and lessons learned to serve as a model for fielding amateur cybersecurity teams for future competition.

Go to article

Deep Learning-Based Diagnosis Of Disease Activity In Patients With Graves’ Orbitopathy Using Orbital Spect/Ct, Ni Yao, Longxi Li, Zhengyuan Gao, Chen Zhao, Yanting Li, Chuang Han, Jiaofen Nan, Zelin Zhu, Yi Xiao, Fubao Zhu, Min Zhao, Weihua Zhou Jul 2023

Deep Learning-Based Diagnosis Of Disease Activity In Patients With Graves’ Orbitopathy Using Orbital Spect/Ct, Ni Yao, Longxi Li, Zhengyuan Gao, Chen Zhao, Yanting Li, Chuang Han, Jiaofen Nan, Zelin Zhu, Yi Xiao, Fubao Zhu, Min Zhao, Weihua Zhou

Michigan Tech Publications, Part 1

Purpose: Orbital [99mTc]TcDTPA orbital single-photon emission computed tomography (SPECT)/CT is an important method for assessing inflammatory activity in patients with Graves’ orbitopathy (GO). However, interpreting the results requires substantial physician workload. We aim to propose an automated method called GO-Net to detect inflammatory activity in patients with GO. Materials and methods: GO-Net had two stages: (1) a semantic V-Net segmentation network (SV-Net) that extracts extraocular muscles (EOMs) in orbital CT images and (2) a convolutional neural network (CNN) that uses SPECT/CT images and the segmentation results to classify inflammatory activity. A total of 956 eyes from 478 patients with GO …

Go to article

Face Readers: The Frontier Of Computer Vision And Math Learning, Beverly Woolf, Margrit Betke, Hao Yu, Sarah Adel Bargal, Ivan Arroyo, John J. Magee Iv, Danielle Allessio, William Rebelsky Jul 2023

Face Readers: The Frontier Of Computer Vision And Math Learning, Beverly Woolf, Margrit Betke, Hao Yu, Sarah Adel Bargal, Ivan Arroyo, John J. Magee Iv, Danielle Allessio, William Rebelsky

Computer Science

The future of AI-assisted individualized learning includes computer vision to inform intelligent tutors and teachers about student affect, motivation and performance. Facial expression recognition is essential in recognizing subtle differences when students ask for hints or fail to solve problems. Facial features and classification labels enable intelligent tutors to predict students’ performance and recommend activities. Videos can capture students’ faces and model their effort and progress; machine learning classifiers can support intelligent tutors to provide interventions. One goal of this research is to support deep dives by teachers to identify students’ individual needs through facial expression and to provide immediate …

Go to article

How Effective Are Seta Programs Anyway: Learning And Forgetting In Security Awareness Training, David Sikolia, David Biros, Tianjian Zhang Jul 2023

How Effective Are Seta Programs Anyway: Learning And Forgetting In Security Awareness Training, David Sikolia, David Biros, Tianjian Zhang

Journal of Cybersecurity Education, Research and Practice

Prevalent security threats caused by human errors necessitate security education, training, and awareness (SETA) programs in organizations. Despite strong theoretical foundations in behavioral cybersecurity, field evidence on the effectiveness of SETA programs in mitigating actual threats is scarce. Specifically, with a broad range of cybersecurity knowledge crammed into in a single SETA session, it is unclear how effective different types of knowledge are in mitigating human errors in a longitudinal setting. his study investigates how knowledge gained through SETA programs affects human errors in cybersecurity to fill the longitudinal void. In a baseline experiment, we establish that SETA programs reduce …

Go to article

Anonymity And Gender Effects On Online Trolling And Cybervictimization, Gang Lee, Annalyssia Soonah Jul 2023

Anonymity And Gender Effects On Online Trolling And Cybervictimization, Gang Lee, Annalyssia Soonah

Journal of Cybersecurity Education, Research and Practice

The purpose of this study was to investigate the effects of the anonymity of the internet and gender differences in online trolling and cybervictimization. A sample of 151 college students attending a southeastern university completed a survey to assess their internet activities and online trolling and cybervictimization. Multivariate analyses of logistic regression and ordinary least squares regression were used to analyze online trolling and cybervictimization. The results indicated that the anonymity measure was not a significant predictor of online trolling and cybervictimization. Female students were less likely than male students to engage in online trolling, but there was no gender …

Go to article

Case Study: The Impact Of Emerging Technologies On Cybersecurity Education And Workforces, Austin Cusak Jul 2023

Case Study: The Impact Of Emerging Technologies On Cybersecurity Education And Workforces, Austin Cusak

Journal of Cybersecurity Education, Research and Practice

A qualitative case study focused on understanding what steps are needed to prepare the cybersecurity workforces of 2026-2028 to work with and against emerging technologies such as Artificial Intelligence and Machine Learning. Conducted through a workshop held in two parts at a cybersecurity education conference, findings came both from a semi-structured interview with a panel of experts as well as small workgroups of professionals answering seven scenario-based questions. Data was thematically analyzed, with major findings emerging about the need to refocus cybersecurity STEM at the middle school level with problem-based learning, the disconnects between workforce operations and cybersecurity operators, the …

Go to article

Target-Based Offensive Language Identification, Marcos Zampieri, Skye Morgan, Kai North, Tharindu Ranasinghe, Austin Simmons, Paridhi Khandelwal, Sara Rosenthal, Preslav Nakov Jul 2023

Target-Based Offensive Language Identification, Marcos Zampieri, Skye Morgan, Kai North, Tharindu Ranasinghe, Austin Simmons, Paridhi Khandelwal, Sara Rosenthal, Preslav Nakov

Natural Language Processing Faculty Publications

We present TBO, a new dataset for Target-based Offensive language identification. TBO contains post-level annotations regarding the harmfulness of an offensive post and token-level annotations comprising of the target and the offensive argument expression. Popular offensive language identification datasets for social media focus on annotation taxonomies only at the post level and more recently, some datasets have been released that feature only token-level annotations. TBO is an important resource that bridges the gap between post-level and token-level annotation datasets by introducing a single comprehensive unified annotation taxonomy. We use the TBO taxonomy to annotate post-level and token-level offensive language on …

Go to article

Improved Logical Reasoning Of Language Models Via Differentiable Symbolic Programming, Hanlin Zhang, Jiani Huang, Ziyang Li, Mayur Naik, Eric Xing Jul 2023

Improved Logical Reasoning Of Language Models Via Differentiable Symbolic Programming, Hanlin Zhang, Jiani Huang, Ziyang Li, Mayur Naik, Eric Xing

Machine Learning Faculty Publications

Pre-trained large language models (LMs) struggle to perform logical reasoning reliably despite advances in scale and compositionality. In this work, we tackle this challenge through the lens of symbolic programming. We propose DSR-LM, a Differentiable Symbolic Reasoning framework where pre-trained LMs govern the perception of factual knowledge, and a symbolic module performs deductive reasoning. In contrast to works that rely on hand-crafted logic rules, our differentiable symbolic reasoning framework efficiently learns weighted rules and applies semantic loss to further improve LMs. DSR-LM is scalable, interpretable, and allows easy integration of prior knowledge, thereby supporting extensive symbolic programming to robustly derive …

Go to article

Bertnet: Harvesting Knowledge Graphs With Arbitrary Relations From Pretrained Language Models, Shibo Hao, Bowen Tan, Kaiwen Tang, Bin Ni, Xiyan Shao, Hengzhe Zhang, Eric P. Xing, Zhiting Hu Jul 2023

Bertnet: Harvesting Knowledge Graphs With Arbitrary Relations From Pretrained Language Models, Shibo Hao, Bowen Tan, Kaiwen Tang, Bin Ni, Xiyan Shao, Hengzhe Zhang, Eric P. Xing, Zhiting Hu

Machine Learning Faculty Publications

It is crucial to automatically construct knowledge graphs (KGs) of diverse new relations to support knowledge discovery and broad applications. Previous KG construction methods, based on either crowdsourcing or text mining, are often limited to a small predefined set of relations due to manual cost or restrictions in text corpus. Recent research proposed to use pretrained language models (LMs) as implicit knowledge bases that accept knowledge queries with prompts. Yet, the implicit knowledge lacks many desirable properties of a full-scale symbolic KG, such as easy access, navigation, editing, and quality assurance. In this paper, we propose a new approach of …

Go to article

Phase-Aware Adversarial Defense For Improving Adversarial Robustness, Dawei Zhou, Nannan Wang, Heng Yang, Xinbo Gao, Tongliang Liu Jul 2023

Phase-Aware Adversarial Defense For Improving Adversarial Robustness, Dawei Zhou, Nannan Wang, Heng Yang, Xinbo Gao, Tongliang Liu

Machine Learning Faculty Publications

Deep neural networks have been found to be vulnerable to adversarial noise. Recent works show that exploring the impact of adversarial noise on intrinsic components of data can help improve adversarial robustness. However, the pattern closely related to human perception has not been deeply studied. In this paper, inspired by the cognitive science, we investigate the interference of adversarial noise from the perspective of image phase, and find ordinarily-trained models lack enough robustness against phase-level perturbations. Motivated by this, we propose a joint adversarial defense method: a phase-level adversarial training mechanism to enhance the adversarial robustness on the phase pattern; …

Go to article

High-Probability Bounds For Stochastic Optimization And Variational Inequalities: The Case Of Unbounded Variance, Abdurakhmon Sadiev, Marina Danilova, Eduard Gorbunov, Samuel Horváth, Gauthier Gidel, Pavel Dvurechensky, Alexander Gasnikov, Peter Richtárik Jul 2023

High-Probability Bounds For Stochastic Optimization And Variational Inequalities: The Case Of Unbounded Variance, Abdurakhmon Sadiev, Marina Danilova, Eduard Gorbunov, Samuel Horváth, Gauthier Gidel, Pavel Dvurechensky, Alexander Gasnikov, Peter Richtárik

Machine Learning Faculty Publications

During recent years the interest of optimization and machine learning communities in high-probability convergence of stochastic optimization methods has been growing. One of the main reasons for this is that high-probability complexity bounds are more accurate and less studied than in-expectation ones. However, SOTA high-probability non-asymptotic convergence results are derived under strong assumptions such as the boundedness of the gradient noise variance or of the objective's gradient itself. In this paper, we propose several algorithms with high-probability convergence results under less restrictive assumptions. In particular, we derive new high-probability convergence results under the assumption that the gradient/operator noise has bounded …

Go to article

Analysis Of Predictive Performance And Reliability Of Classifiers For Quality Assessment Of Medical Evidence Revealed Important Variation By Medical Area, Simon Šuster, Timothy Baldwin, Karin Verspoor Jul 2023

Analysis Of Predictive Performance And Reliability Of Classifiers For Quality Assessment Of Medical Evidence Revealed Important Variation By Medical Area, Simon Šuster, Timothy Baldwin, Karin Verspoor

Natural Language Processing Faculty Publications

Objectives: A major obstacle in deployment of models for automated quality assessment is their reliability. To analyze their calibration and selective classification performance. Study Design and Setting: We examine two systems for assessing the quality of medical evidence, EvidenceGRADEr and RobotReviewer, both developed from Cochrane Database of Systematic Reviews (CDSR) to measure strength of bodies of evidence and risk of bias (RoB) of individual studies, respectively. We report their calibration error and Brier scores, present their reliability diagrams, and analyze the risk–coverage trade-off in selective classification. Results: The models are reasonably well calibrated on most quality criteria (expected calibration error …

Go to article

Bertastic At Semeval-2023 Task 3: Fine-Tuning Pretrained Multilingual Transformers – Does Order Matter?, Tarek Mahmoud, Preslav Nakov Jul 2023

Bertastic At Semeval-2023 Task 3: Fine-Tuning Pretrained Multilingual Transformers – Does Order Matter?, Tarek Mahmoud, Preslav Nakov

Natural Language Processing Faculty Publications

The naïve approach for fine-tuning pretrained deep learning models on downstream tasks involves feeding them mini-batches of randomly sampled data. In this paper, we propose a more elaborate method for fine-tuning Pretrained Multilingual Transformers (PMTs) on multilingual data. Inspired by the success of curriculum learning approaches, we investigate the significance of fine-tuning PMTs on multilingual data in a sequential fashion language by language. Unlike the curriculum learning paradigm where the model is presented with increasingly complex examples, we do not adopt a notion of “easy” and “hard” samples. Instead, our experiments draw insight from psychological findings on how the human …

Go to article

Conformal Prediction For Federated Uncertainty Quantification Under Label Shift, Vincent Plassier, Mehdi Makni, Aleksandr Rubashevskii, Eric Moulines, Maxim Panov Jul 2023

Conformal Prediction For Federated Uncertainty Quantification Under Label Shift, Vincent Plassier, Mehdi Makni, Aleksandr Rubashevskii, Eric Moulines, Maxim Panov

Machine Learning Faculty Publications

Federated Learning (FL) is a machine learning framework where many clients collaboratively train models while keeping the training data decentralized. Despite recent advances in FL, the uncertainty quantification topic (UQ) remains partially addressed. Among UQ methods, conformal prediction (CP) approaches provides distribution-free guarantees under minimal assumptions. We develop a new federated conformal prediction method based on quantile regression and take into account privacy constraints. This method takes advantage of importance weighting to effectively address the label shift between agents and provides theoretical guarantees for both valid coverage of the prediction sets and differential privacy. Extensive experimental studies demonstrate that this …

Go to article

How To Best Retrain A Neural Network If We Added One More Input Variable, Saeid Tizpaz-Niari, Vladik Kreinovich Jul 2023

How To Best Retrain A Neural Network If We Added One More Input Variable, Saeid Tizpaz-Niari, Vladik Kreinovich

Departmental Technical Reports (CS)

Often, once we have trained a neural network to estimate the value of a quantity y based on the available values of inputs x1, ..., xn, we learn to measure the values of an additional quantity that have some influence on y. In such situations, it is desirable to re-train the neural network, so that it will be able to take this extra value into account. A straightforward idea is to add a new input to the first layer and to update all the weights based on the patterns that include the values of the new input. The problem with …

Go to article

Topological Explanation Of Why Complex Numbers Are Needed In Quantum Physics, Julio C. Urenda, Vladik Kreinovich Jul 2023

Topological Explanation Of Why Complex Numbers Are Needed In Quantum Physics, Julio C. Urenda, Vladik Kreinovich

Departmental Technical Reports (CS)

In quantum computing, we only use states in which all amplitudes are real numbers. So why do we need complex numbers with non-zero imaginary part in quantum physics in general? In this paper, we provide a simple topological explanation for this need, explanation based on the Second Law of Thermodynamics.

Go to article

Numerical Design And Optimization Of Near-Infrared Band- Pass Filter, Hafiza Syeeda Faiza, Ghazi Aman Nowsherwan, Basem A. Abu Izneid, Muhammad Azhar, Saira Riaz, Syed Sajjad Hussain, Saira Ikram, Mohsin Khan, Shahzad Naseem, Mohammad Kanan, Ibrahim M. Mansour Jul 2023

Numerical Design And Optimization Of Near-Infrared Band- Pass Filter, Hafiza Syeeda Faiza, Ghazi Aman Nowsherwan, Basem A. Abu Izneid, Muhammad Azhar, Saira Riaz, Syed Sajjad Hussain, Saira Ikram, Mohsin Khan, Shahzad Naseem, Mohammad Kanan, Ibrahim M. Mansour

Applied Mathematics & Information Sciences

Band-pass filters functioning in the near-infrared (IR) range are desired for laser technology, multi-photon fluorescence, and IR imaging applications. In this study, we have designed four band-pass filters in the near Infrared spectrum (900-1200 nm) by vertically stacking different high and low-index materials. The band-pass filters are modelled by Essential Macleod software with different thicknesses. The layer’s thicknesses were optimized in such a way to provide the negligible reflectance and maximum transmission on the front side. All the simulated band-pass filters exhibit high transmittance, but TiO2/Al2O3 and Ta2O5/Al2O3 outperforms other modelled structure in terms of performance due to the better …

Go to article

A Universal Unbiased Method For Classification From Aggregate Observations, Zixi Wei, Lei Feng, Bo Han, Tongliang Liu, Gang Niu, Xiaofeng Zhu, Heng Tao Shen Jul 2023

A Universal Unbiased Method For Classification From Aggregate Observations, Zixi Wei, Lei Feng, Bo Han, Tongliang Liu, Gang Niu, Xiaofeng Zhu, Heng Tao Shen

Machine Learning Faculty Publications

In conventional supervised classification, true labels are required for individual instances. However, it could be prohibitive to collect the true labels for individual instances, due to privacy concerns or unaffordable annotation costs. This motivates the study on classification from aggregate observations (CFAO), where the supervision is provided to groups of instances, instead of individual instances. CFAO is a generalized learning framework that contains various learning problems, such as multiple-instance learning and learning from label proportions. The goal of this paper is to present a novel universal method of CFAO, which holds an unbiased estimator of the classification risk for arbitrary …

Go to article

First Prev Next Last