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

Computer Sciences Commons™

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

2022

Discipline
Institution
Keyword
Publication
Publication Type
File Type

Articles 2671 - 2700 of 3613

Full-Text Articles in Computer Sciences

Forming A Decentralized Research Network: Ds4h, Eni̇s Karaarslan, Meli̇h Bi̇ri̇m, Hüseyi̇n Emre Ari Feb 2022

Forming A Decentralized Research Network: Ds4h, Eni̇s Karaarslan, Meli̇h Bi̇ri̇m, Hüseyi̇n Emre Ari

Turkish Journal of Electrical Engineering and Computer Sciences

There is a trend toward decentralized systems, but these systems are developed without conducting enough software tests. Also, the performance, scalability, and sustainability of the decentralized systems are not taken into account. One of the reasons is the time-consuming testing process. The other is the hardware requirements and the complexity of the software installations of the testing environment. Developer communities need stable and secure research networks to test and develop prototypes before releasing the working versions. Cloud-based blockchain test networks are available, but it allows using a specific framework. Also, users are required to learn how to use each framework. …

Go to article

Blocksim-Net: A Network-Based Blockchain Simulator, Prashanthi Ramachandran, Nandini Agrawal, Osman Bi̇çer, Alpteki̇n Küpçü Feb 2022

Blocksim-Net: A Network-Based Blockchain Simulator, Prashanthi Ramachandran, Nandini Agrawal, Osman Bi̇çer, Alpteki̇n Küpçü

Turkish Journal of Electrical Engineering and Computer Sciences

Since its proposal by Eyal and Sirer (CACM '13), selfish mining attacks on proof-of-work blockchains have been studied extensively. The main body of this research aims at both studying the extent of its impact and defending against it. Yet, before any practical defense is deployed in a real world blockchain system, it needs to be tested for security and dependability. However, real blockchain systems are too complex to conduct any test on or benchmark the developed protocols. Instead, some simulation environments have been proposed recently, such as BlockSim (Maher et al., SIGMETRICS Perform. Eval. Rev. '19), which is a modular …

Go to article

Block Size Optimization For Pow Consensus Algorithm Based Blockchainapplications By Using Whale Optimization Algorithm, Betül Aygün, Hi̇lal Arslan Feb 2022

Block Size Optimization For Pow Consensus Algorithm Based Blockchainapplications By Using Whale Optimization Algorithm, Betül Aygün, Hi̇lal Arslan

Turkish Journal of Electrical Engineering and Computer Sciences

Blockchain-based applications come up with cryptocurrencies, especially Bitcoin, introducing a distributed ledger technologies for peer-to-peer networks and essentially records the transactions in blocks containing hash value of the previous blocks. Block generation constitutes the basis of this technology, and the optimization of such systems is among the most crucial concerns. Determining either the block size or the number of transactions in the block brings out a remarkable problem that has been solved by the miners in recent years. First, higher block size results in higher transaction time, on the other hand, smaller block size has many disadvantages such as security, …

Go to article

Tri-Op Redactable Blockchains With Block Modification, Removal, And Insertion, Mohammad Sadeq Dousti, Alpteki̇n Küpçü Feb 2022

Tri-Op Redactable Blockchains With Block Modification, Removal, And Insertion, Mohammad Sadeq Dousti, Alpteki̇n Küpçü

Turkish Journal of Electrical Engineering and Computer Sciences

In distributed computations and cryptography, it is desirable to record events on a public ledger, such that later alterations are computationally infeasible. An implementation of this idea is called blockchain, which is a distributed protocol that allows the creation of an immutable ledger. While such an idea is very appealing, the ledger may be contaminated with incorrect, illegal, or even dangerous data, and everyone running the blockchain protocol has no option but to store and propagate the unwanted data. The ledger is bloated over time, and it is not possible to remove redundant information. Finally, missing data cannot be inserted …

Go to article

Performance Analysis Of Lightweight Internet Of Things Devices On Blockchainnetworks, Cem Kösemen, Gökhan Dalkiliç, Şafak Öksüzer Feb 2022

Performance Analysis Of Lightweight Internet Of Things Devices On Blockchainnetworks, Cem Kösemen, Gökhan Dalkiliç, Şafak Öksüzer

Turkish Journal of Electrical Engineering and Computer Sciences

Potential integration or cooperation of the Internet of things (IoT) systems and the blockchain technology is nowadays attracting remarkable interest from the researchers. These inter-operating systems often have to rely on lowcost, low-power, and robust IoT devices that can communicate with the blockchain network through smart contracts. In this work, we designed and ran a benchmark study for ESP32-based lightweight IoT devices interacting within the Quorum blockchain. A software library was built for ESP32 devices to enable elliptic-curve digital signing, Keccak-256 hashing, decoding, encoding, and secure private key generation capabilities, which all are the basic functional requirements for running a …

Go to article

Real-World Smartphone-Based Gait Recognition, Hind Alobaidi, Nathan Clarke, Fudong Li, Abdulrahman Alruban Feb 2022

Real-World Smartphone-Based Gait Recognition, Hind Alobaidi, Nathan Clarke, Fudong Li, Abdulrahman Alruban

Research outputs 2022 to 2026

As the smartphone and the services it provides are becoming targets of cybercrime, it is critical to secure smartphones. However, it is important security controls are designed to provide continuous and user-friendly security. Amongst the most important of these is user authentication, where users have experienced a significant rise in the need to authenticate to the device and individually to the numerous apps that it contains. Gait authentication has gained attention as a mean of non-intrusive or transparent authentication on mobile devices, capturing the information required to verify the authenticity of the user whilst the person is walking. Whilst prior …

Go to article

Imidazole Derivative Improves Antioxidant Status And Causes Differential Alteration Of Redox-Status In Drosophila Melanogaster, Elizabeth Temidayo Oluwayemi, Oluwakemi Josephine Awakan, Abiodun Omokehinde Eseola, Winfried Plass, Oluyomi Stephen Adeyemi Jan 2022

Imidazole Derivative Improves Antioxidant Status And Causes Differential Alteration Of Redox-Status In Drosophila Melanogaster, Elizabeth Temidayo Oluwayemi, Oluwakemi Josephine Awakan, Abiodun Omokehinde Eseola, Winfried Plass, Oluyomi Stephen Adeyemi

Karbala International Journal of Modern Science

This study investigated the toxicity of a new imidazole compound, 1-(1,4,5-triphenyl-1H-imidazol-2-yl)-naphthalen-2-ol, through the evaluation of selected oxidative stress markers and antioxidants. Both male and female D. melanogaster (3–5 days old) were fed a diet containing the imidazole derivative (20, 50, and 100 mg IMZ/kg diet) for five days. After cessation of imidazole treatment, half the population of the imidazole-exposed flies was homogenized for biochemical assays, while the other half of the flies was allowed to have a normal diet for an additional five days to see if any induced effect would be resolved. Imidazole derivatives did not significantly …

Go to article

Glcms Based Multi-Inputs 1d Cnn Deep Learning Neural Network For Covid-19 Texture Feature Extraction And Classification, Elaf Ali Abbood, Tawfiq A. Al-Assadi Jan 2022

Glcms Based Multi-Inputs 1d Cnn Deep Learning Neural Network For Covid-19 Texture Feature Extraction And Classification, Elaf Ali Abbood, Tawfiq A. Al-Assadi

Karbala International Journal of Modern Science

Coronavirus disease 2019 epidemic (COVID-19) is an infectious disease that appeared because of the newest version of discovered coronavirus. The advent and rapid spread of this disease over the world necessitated a concerted effort to contain and eradicate it. Computer Tomography (CT) imaging and X-Ray images are considered as one of the important medical examinations used for disease diagnosis. To speed up and confirm the correctness of the medical diagnosis, many artificial intelligence techniques and machine learning methods are proposed. In this paper, a new and efficient proposed system is introduced to extract appropriate and meaningful features for CT scans …

Go to article

A Convenient Green Method To Synthesize Β-Carotene From Edible Carrot And Nanoparticle Formation, Baker A. Joda, Zena M. Abed Al-Kadhim, Hussian J. Ahmed, Alaa K. H. Al-Khalaf Jan 2022

A Convenient Green Method To Synthesize Β-Carotene From Edible Carrot And Nanoparticle Formation, Baker A. Joda, Zena M. Abed Al-Kadhim, Hussian J. Ahmed, Alaa K. H. Al-Khalaf

Karbala International Journal of Modern Science

A simple green chemistry approach was used to synthesize β-carotene from edible carrot without using solvent and heat. In this study, beta-carotene was extracted from edible carrots through a natural extraction method with several physical technical steps. The extracted sample was isolated using high-performance liquid chromatography (HPLC). A β-carotene peak was detected from HPLC with an absorbance maximum (2.135 mAU). The absorption of UV-Visible spectrum indicated that beta-carotene absorbs most strongly between 230-300 and 400-500 nm. The functional groups, namely, C=C (1649 cm-1), =C-H (900-900 cm-1) vibrations of antisymmetric deformation of CH3 groups and CH …

Go to article

The Nature Of Numbers: Real Computing, Bradley J. Lucier Jan 2022

The Nature Of Numbers: Real Computing, Bradley J. Lucier

Journal of Humanistic Mathematics

While studying the computable real numbers as a professional mathematician, I came to see the computable reals, and not the real numbers as usually presented in undergraduate real analysis classes, as the natural culmination of my evolving understanding of numbers as a schoolchild. This paper attempts to trace and explain that evolution. The first part recounts the nature of numbers as they were presented to us grade-school children. In particular, the introduction of square roots induced a step change in my understanding of numbers. Another incident gave me insight into the brilliance of Alan Turing in his paper introducing both …

Go to article

Machine Learning-Based Soft Computing Regression Analysis Approach For Crime Data Prediction, Rabia Musheer Aziz, Aftab Hussain, Prajwal Sharma, Pavan Kumar Jan 2022

Machine Learning-Based Soft Computing Regression Analysis Approach For Crime Data Prediction, Rabia Musheer Aziz, Aftab Hussain, Prajwal Sharma, Pavan Kumar

Karbala International Journal of Modern Science

The crime rate in India is considerably increasing day by day. Consequently, the data associated with crime is also increasing, opening doors for data-driven approaches to these data to extract insightful knowledge, which can help police and other law enforcement organizations of the country in crime control and prevention. Crime prediction using machine learning algorithms on crime data can predict region-wise crime counts. In this paper, a machine learning-based soft computing regression analysis approach for Indian Crime Data Analysis (ICDA) is proposed. Different regression algorithms, namely, Simple Linear Regression (SLR), Multiple Linear Regression (MLR), Decision Tree Regression (DTR), Support Vector …

Go to article

Atomistic Simulation Of Na+ And Cl- Ions Binding Mechanisms To Tobermorite 14Å As A Model For Alkali Activated Cements, Ahmed Abdelkawy Jan 2022

Atomistic Simulation Of Na+ And Cl- Ions Binding Mechanisms To Tobermorite 14Å As A Model For Alkali Activated Cements, Ahmed Abdelkawy

Theses and Dissertations

The production of ordinary Portland cement (OPC) is responsible for ~8% of all man-made CO2 emissions. Unfortunately, due to the continuous increase in the number of construction projects, and since virtually all projects depend on hardened cement from the hydration of OPC as the main binding material, the production of OPC is not expected to decrease. Alkali-activated cement produced from the alkaline activation of byproducts of industries, such as iron and coal industries, or processed clays represents a potential substitute for OPC. However, the interaction of the reaction products of AAC with corrosive ions from the environment, such as Cl-, …

Go to article

Conditional Contrastive Learning With Kernel, Yao Hung Hubert Tsai, Tianqin Li, Martin Q. Ma, Han Zhao, Kun Zhang, Louis Philippe Morency, Ruslan Salakhutdinov Jan 2022

Conditional Contrastive Learning With Kernel, Yao Hung Hubert Tsai, Tianqin Li, Martin Q. Ma, Han Zhao, Kun Zhang, Louis Philippe Morency, Ruslan Salakhutdinov

Machine Learning Faculty Publications

Conditional contrastive learning frameworks consider the conditional sampling procedure that constructs positive or negative data pairs conditioned on specific variables. Fair contrastive learning constructs negative pairs, for example, from the same gender (conditioning on sensitive information), which in turn reduces undesirable information from the learned representations; weakly supervised contrastive learning constructs positive pairs with similar annotative attributes (conditioning on auxiliary information), which in turn are incorporated into the representations. Although conditional contrastive learning enables many applications, the conditional sampling procedure can be challenging if we cannot obtain sufficient data pairs for some values of the conditioning variable. This paper presents …

Go to article

Adarl: What, Where, And How To Adapt In Transfer Reinforcement Learning, Biwei Huang, Fan Feng, Chaochao Lu, Sara Magliacane, Kun Zhang Jan 2022

Adarl: What, Where, And How To Adapt In Transfer Reinforcement Learning, Biwei Huang, Fan Feng, Chaochao Lu, Sara Magliacane, Kun Zhang

Machine Learning Faculty Publications

One practical challenge in reinforcement learning (RL) is how to make quick adaptations when faced with new environments. In this paper, we propose a principled framework for adaptive RL, called AdaRL, that adapts reliably and efficiently to changes across domains with a few samples from the target domain, even in partially observable environments. Specifically, we leverage a parsimonious graphical representation that characterizes structural relationships over variables in the RL system. Such graphical representations provide a compact way to encode what and where the changes across domains are, and furthermore inform us with a minimal set of changes that one has …

Go to article

Learning Temporally Causal Latent Processes From General Temporal Data, Weiran Yao, Yuewen Sun, Alex Ho, Changyin Sun, Kun Zhang Jan 2022

Learning Temporally Causal Latent Processes From General Temporal Data, Weiran Yao, Yuewen Sun, Alex Ho, Changyin Sun, Kun Zhang

Machine Learning Faculty Publications

Our goal is to recover time-delayed latent causal variables and identify their relations from measured temporal data. Estimating causally-related latent variables from observations is particularly challenging as the latent variables are not uniquely recoverable in the most general case. In this work, we consider both a nonparametric, nonstationary setting and a parametric setting for the latent processes and propose two provable conditions under which temporally causal latent processes can be identified from their nonlinear mixtures. We propose LEAP, a theoretically-grounded framework that extends Variational AutoEncoders (VAEs) by enforcing our conditions through proper constraints in causal process prior. Experimental results on …

Go to article

Assessing Feature Representations For Instance-Based Cross-Domain Anomaly Detection In Cloud Services Univariate Time Series Data, Rahul Agrahari, Matthew Nicholson, Clare Conran, Haytham Assem, John D. Kelleher Jan 2022

Assessing Feature Representations For Instance-Based Cross-Domain Anomaly Detection In Cloud Services Univariate Time Series Data, Rahul Agrahari, Matthew Nicholson, Clare Conran, Haytham Assem, John D. Kelleher

Articles

In this paper, we compare and assess the efficacy of a number of time-series instance feature representations for anomaly detection. To assess whether there are statistically significant differences between different feature representations for anomaly detection in a time series, we calculate and compare confidence intervals on the average performance of different feature sets across a number of different model types and cross-domain time-series datasets. Our results indicate that the catch22 time-series feature set augmented with features based on rolling mean and variance performs best on average, and that the difference in performance between this feature set and the next best …

Go to article

Assessing Feature Representations For Instance-Based Cross-Domain Anomaly Detection In Cloud Services Univariate Time Series Data, Rahul Agrahari, Matthew Nicholson, Clare Conran, Haythem Assem, John D. Kelleher Jan 2022

Assessing Feature Representations For Instance-Based Cross-Domain Anomaly Detection In Cloud Services Univariate Time Series Data, Rahul Agrahari, Matthew Nicholson, Clare Conran, Haythem Assem, John D. Kelleher

Articles

In this paper, we compare and assess the efficacy of a number of time-series instance feature representations for anomaly detection. To assess whether there are statistically significant differences between different feature representations for anomaly detection in a time series, we calculate and compare confidence intervals on the average performance of different feature sets across a number of different model types and cross-domain time-series datasets. Our results indicate that the catch22 time-series feature set augmented with features based on rolling mean and variance performs best on average, and that the difference in performance between this feature set and the next best …

Go to article

The Power Of First-Order Smooth Optimization For Black-Box Non-Smooth Problems, Alexander V. Gasnikov., Anton Novitskii, Vasilii Novitskii, Farshed Abdukhakimov, Dmitry Kamzolov, Aleksandr Beznosikov, Martin Takáč, Pavel Dvurechensky, Bin Gu Jan 2022

The Power Of First-Order Smooth Optimization For Black-Box Non-Smooth Problems, Alexander V. Gasnikov., Anton Novitskii, Vasilii Novitskii, Farshed Abdukhakimov, Dmitry Kamzolov, Aleksandr Beznosikov, Martin Takáč, Pavel Dvurechensky, Bin Gu

Machine Learning Faculty Publications

Gradient-free/zeroth-order methods for black-box convex optimization have been extensively studied in the last decade with the main focus on oracle calls complexity. In this paper, besides the oracle complexity, we focus also on iteration complexity, and propose a generic approach that, based on optimal first-order methods, allows to obtain in a black-box fashion new zeroth-order algorithms for non-smooth convex optimization problems. Our approach not only leads to optimal oracle complexity, but also allows to obtain iteration complexity similar to first-order methods, which, in turn, allows to exploit parallel computations to accelerate the convergence of our algorithms. We also elaborate on …

Go to article

Security, Trust And Privacy For Cloud, Fog And Internet Of Things, Chien-Ming Chen, Shehzad Ashraf Chaudhry, Kuo-Hui Yeh, Muhammad Naveed Aman Jan 2022

Security, Trust And Privacy For Cloud, Fog And Internet Of Things, Chien-Ming Chen, Shehzad Ashraf Chaudhry, Kuo-Hui Yeh, Muhammad Naveed Aman

School of Computing: Faculty Publications

No abstract provided.

Go to article

Optimal Eavesdropping In Quantum Cryptography, Atanu Acharyya Dr. Jan 2022

Optimal Eavesdropping In Quantum Cryptography, Atanu Acharyya Dr.

Doctoral Theses

Quantum key distribution (QKD) has raised some promise for more secured communication than its classical counterpart. It allows the legitimate parties to detect eavesdropping which introduces error in the channel. If disturbed, there are ways to distill a secure key within some threshold error-rate. The amount of information gained by an attacker is generally quantified by (Shannon) mutual information. Knowing the maximum amount of information that an intruder can gain is important for post-processing purposes, and we mainly focus on that side in the thesis. Renyi information is also useful especially when post-processing is considered. The scope of this thesis …

Go to article

On The Security Of Bluetooth Low Energy In Two Consumer Wearable Heart Rate Monitors/Sensing Devices, Yesem Kurt Peker, Gabriel Bello, Alfredo J. Perez Jan 2022

On The Security Of Bluetooth Low Energy In Two Consumer Wearable Heart Rate Monitors/Sensing Devices, Yesem Kurt Peker, Gabriel Bello, Alfredo J. Perez

Computer Science Faculty Publications

Since its inception in 2013, Bluetooth Low Energy (BLE) has become the standard for short-distance wireless communication in many consumer devices, as well as special-purpose devices. In this study, we analyze the security features available in Bluetooth LE standards and evaluate the features implemented in two BLE wearable devices (a Fitbit heart rate wristband and a Polar heart rate chest wearable) and a BLE keyboard to explore which security features in the BLE standards are implemented in the devices. In this study, we used the ComProbe Bluetooth Protocol Analyzer, along with the ComProbe software to capture the BLE traffic of …

Go to article

Applications Of Unsupervised Machine Learning In Autism Spectrum Disorder Research: A Review, Chelsea Parlett-Pelleriti, Elizabeth Stevens, Dennis R. Dixon, Erik J. Linstead Jan 2022

Applications Of Unsupervised Machine Learning In Autism Spectrum Disorder Research: A Review, Chelsea Parlett-Pelleriti, Elizabeth Stevens, Dennis R. Dixon, Erik J. Linstead

Engineering Faculty Articles and Research

Large amounts of autism spectrum disorder (ASD) data is created through hospitals, therapy centers, and mobile applications; however, much of this rich data does not have pre-existing classes or labels. Large amounts of data—both genetic and behavioral—that are collected as part of scientific studies or a part of treatment can provide a deeper, more nuanced insight into both diagnosis and treatment of ASD. This paper reviews 43 papers using unsupervised machine learning in ASD, including k-means clustering, hierarchical clustering, model-based clustering, and self-organizing maps. The aim of this review is to provide a survey of the current uses of …

Go to article

Hyperparameter Optimization For Covid-19 Chest X-Ray Classification, Ibraheem Hamdi, Muhammad Ridzuan, Mohammad Yaqub Jan 2022

Hyperparameter Optimization For Covid-19 Chest X-Ray Classification, Ibraheem Hamdi, Muhammad Ridzuan, Mohammad Yaqub

Computer Vision Faculty Publications

Despite the introduction of vaccines, Coronavirus disease (COVID-19) remains a worldwide dilemma, continuously developing new variants such as Delta and the recent Omicron. The current standard for testing is through polymerase chain reaction (PCR). However, PCRs can be expensive, slow, and/or inaccessible to many people. X-rays on the other hand have been readily used since the early 20th century and are relatively cheaper, quicker to obtain, and typically covered by health insurance. With a careful selection of model, hyperparameters, and augmentations, we show that it is possible to develop models with 83% accuracy in binary classification and 64% in multi-class …

Go to article

Emotion Recognition With Audio, Video, Eeg, And Emg: A Dataset And Baseline Approaches, Jin Chen, Tony Ro, Zhigang Zhu Jan 2022

Emotion Recognition With Audio, Video, Eeg, And Emg: A Dataset And Baseline Approaches, Jin Chen, Tony Ro, Zhigang Zhu

Publications and Research

This paper describes a new posed multimodal emotional dataset and compares human emotion classification based on four different modalities - audio, video, electromyography (EMG), and electroencephalography (EEG). The results are reported with several baseline approaches using various feature extraction techniques and machine-learning algorithms. First, we collected a dataset from 11 human subjects expressing six basic emotions and one neutral emotion. We then extracted features from each modality using principal component analysis, autoencoder, convolution network, and mel-frequency cepstral coefficient (MFCC), some unique to individual modalities. A number of baseline models have been applied to compare the classification performance in emotion recognition, …

Go to article

Building Smart Contracts For Covid19 Pandemic Over The Blockchain Emerging Technologies, Ala’ Abu Hilal, Mohamad Badra, Abdallah Tubaishat Jan 2022

Building Smart Contracts For Covid19 Pandemic Over The Blockchain Emerging Technologies, Ala’ Abu Hilal, Mohamad Badra, Abdallah Tubaishat

All Works

This research aims to improve and integrate hospital’s healthcare applications with Blockchain and smart contracts technologies to provide huge and secure storage that is immutable. This application will be able to record the patients’ medical history like appointments, medical tests, etc.; As a matter of fact, these resources should be recorded to be securely retrieved, modified, and stored by an authorized party only. The utilization of these critical resources will increase the validity for participants with a high level of liability, where building a scheduling appointment system using the blockchain-based on a smart contract will enhance patients’ privacy and provides …

Go to article

Variational Autoencoders For Reliability Optimization In Multi-Access Edge Computing Networks, Arian Ahmadi, Omid Semiari, Mehdi Bennis, Méroúane Debbah Jan 2022

Variational Autoencoders For Reliability Optimization In Multi-Access Edge Computing Networks, Arian Ahmadi, Omid Semiari, Mehdi Bennis, Méroúane Debbah

Machine Learning Faculty Publications

Multi-access edge computing (MEC) is viewed as an integral part of future wireless networks to support new applications with stringent service reliability and latency requirements. However, guaranteeing ultra-reliable and low-latency MEC (URLL MEC) is very challenging due to uncertainties of wireless links, limited communications and computing resources, as well as dynamic network traffic. Enabling URLL MEC mandates taking into account the statistics of the end-to-end (E2E) latency and reliability across the wireless and edge computing systems. In this paper, a novel framework is proposed to optimize the reliability of MEC networks by considering the distribution of E2E service delay, encompassing …

Go to article

Robust Error Estimation Based On Factor-Graph Models For Non-Line-Of-Sight Localization, O. Arda Vanli, Clark N. Taylor Jan 2022

Robust Error Estimation Based On Factor-Graph Models For Non-Line-Of-Sight Localization, O. Arda Vanli, Clark N. Taylor

Faculty Publications

This paper presents a method to estimate the covariances of the inputs in a factor-graph formulation for localization under non-line-of-sight conditions. A general solution based on covariance estimation and M-estimators in linear regression problems, is presented that is shown to give unbiased estimators of multiple variances and are robust against outliers. An iteratively re-weighted least squares algorithm is proposed to jointly compute the proposed variance estimators and the state estimates for the nonlinear factor graph optimization. The efficacy of the method is illustrated in a simulation study using a robot localization problem under various process and measurement models and measurement …

Go to article

Transformers In Medical Imaging: A Survey, Fahad Shamshad, Salman Khan, Syed Waqas Zamir, Muhammad Haris Khan, Munawar Hayat, Fahad Shahbaz Khan, Huazhu Fu Jan 2022

Transformers In Medical Imaging: A Survey, Fahad Shamshad, Salman Khan, Syed Waqas Zamir, Muhammad Haris Khan, Munawar Hayat, Fahad Shahbaz Khan, Huazhu Fu

Computer Vision Faculty Publications

Following unprecedented success on the natural language tasks, Transformers have been successfully applied to several computer vision problems, achieving state-of-the-art results and prompting researchers to reconsider the supremacy of convolutional neural networks (CNNs) as de facto operators. Capitalizing on these advances in computer vision, the medical imaging field has also witnessed growing interest for Transformers that can capture global context compared to CNNs with local receptive fields. Inspired from this transition, in this survey, we attempt to provide a comprehensive review of the applications of Transformers in medical imaging covering various aspects, ranging from recently proposed architectural designs to unsolved …

Go to article

An Empirical Study On The Efficacy Of Evolutionary Algorithms For Automated Neural Architecture Search, Andrew D. Cuccinello Jan 2022

An Empirical Study On The Efficacy Of Evolutionary Algorithms For Automated Neural Architecture Search, Andrew D. Cuccinello

Theses and Dissertations

The configuration and architecture design of neural networks is a time consuming process that has been shown to provide significant training speed and prediction improvements. Traditionally, this process is done manually, but this requires a large amount of expert knowledge and significant investment of labor. As a result it is beneficial to have automated ways to optimize model architectures. In this thesis, we study the use of evolutionary algorithm for neural architecture search (NAS). Moreover, we investigate the effect of integrating evolutionary NAS into deep reinforcement learning to learn control policy for ATARI game playing. Empirical classification results on the …

Go to article

Optimal Transport For Causal Discovery, Ruibo Tu, Kun Zhang, Hedvig Kjellström, Cheng Zhang Jan 2022

Optimal Transport For Causal Discovery, Ruibo Tu, Kun Zhang, Hedvig Kjellström, Cheng Zhang

Machine Learning Faculty Publications

To determine causal relationships between two variables, approaches based on Functional Causal Models (FCMs) have been proposed by properly restricting model classes; however, the performance is sensitive to the model assumptions, which makes it difficult to use. In this paper, we provide a novel dynamical-system view of FCMs and propose a new framework for identifying causal direction in the bivariate case. We first show the connection between FCMs and optimal transport, and then study optimal transport under the constraints of FCMs. Furthermore, by exploiting the dynamical interpretation of optimal transport under the FCM constraints, we determine the corresponding underlying dynamical …

Go to article

First Prev Next Last