Search Results for author: Muhammad Usman

Found 37 papers, 8 papers with code

Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation

no code implementations22 Dec 2022 Shu Lok Tsang, Maxwell T. West, Sarah M. Erfani, Muhammad Usman

A subclass of QML methods is quantum generative adversarial networks (QGANs) which have been studied as a quantum counterpart of classical GANs widely used in image manipulation and generation tasks.

Dimensionality Reduction Image Generation +2

MEDS-Net: Self-Distilled Multi-Encoders Network with Bi-Direction Maximum Intensity projections for Lung Nodule Detection

no code implementations30 Oct 2022 Muhammad Usman, Azka Rehman, Abdullah Shahid, Siddique Latif, Shi Sub Byon, Byoung Dai Lee, Sung Hyun Kim, Byung il Lee, Yeong Gil Shin

Particularly, we exploit Bi-Directional Maximum intensity projection (MIP) images of various thicknesses (i. e., 3, 5 and 10mm) along with a 3D patch of CT scan, consisting of 10 adjacent slices to feed into self-distillation-based Multi-Encoders Network (MEDS-Net).

Lung Nodule Detection

Secure and Trustworthy Artificial Intelligence-Extended Reality (AI-XR) for Metaverses

no code implementations24 Oct 2022 Adnan Qayyum, Muhammad Atif Butt, Hassan Ali, Muhammad Usman, Osama Halabi, Ala Al-Fuqaha, Qammer H. Abbasi, Muhammad Ali Imran, Junaid Qadir

Metaverse is expected to emerge as a new paradigm for the next-generation Internet, providing fully immersive and personalised experiences to socialize, work, and play in self-sustaining and hyper-spatio-temporal virtual world(s).

An Overview of Structural Coverage Metrics for Testing Neural Networks

1 code implementation5 Aug 2022 Muhammad Usman, Youcheng Sun, Divya Gopinath, Rishi Dange, Luca Manolache, Corina S. Pasareanu

Deep neural network (DNN) models, including those used in safety-critical domains, need to be thoroughly tested to ensure that they can reliably perform well in different scenarios.

DNN Testing

Automated Quantum Circuit Design with Nested Monte Carlo Tree Search

no code implementations1 Jul 2022 Pei-Yong Wang, Muhammad Usman, Udaya Parampalli, Lloyd C. L. Hollenberg, Casey R. Myers

Quantum algorithms based on variational approaches are one of the most promising methods to construct quantum solutions and have found a myriad of applications in the last few years.

Performance analysis of coreset selection for quantum implementation of K-Means clustering algorithm

no code implementations16 Jun 2022 Fanzhe Qu, Sarah M. Erfani, Muhammad Usman

However, the impact of coreset selection on the performance of quantum K-Means clustering has not been explored.

Optimizing Indoor Navigation Policies For Spatial Distancing

no code implementations4 Jun 2022 Xun Zhang, Mathew Schwartz, Muhammad Usman, Petros Faloutsos, Mubbasir Kapadia

In this paper, we focus on the modification of policies that can lead to movement patterns and directional guidance of occupants, which are represented as agents in a 3D simulation engine.

VPN: Verification of Poisoning in Neural Networks

no code implementations8 May 2022 Youcheng Sun, Muhammad Usman, Divya Gopinath, Corina S. Păsăreanu

Neural networks are successfully used in a variety of applications, many of them having safety and security concerns.

Data Poisoning Image Classification +1

Multiplier with Reduced Activities and Minimized Interconnect for Inner Product Arrays

no code implementations11 Apr 2022 Muhammad Usman, Jeong-A Lee, Milos D. Ercegovac

Synthesis results of the proposed designs have been presented and compared with the non-pipelined online multiplier, pipelined online multiplier with full working precision and conventional serial-parallel and array multipliers.

AntidoteRT: Run-time Detection and Correction of Poison Attacks on Neural Networks

1 code implementation31 Jan 2022 Muhammad Usman, Youcheng Sun, Divya Gopinath, Corina S. Pasareanu

For correction, we propose an input correction technique that uses a differential analysis to identify the trigger in the detected poisoned images, which is then reset to a neutral color.

Image Classification

QuantifyML: How Good is my Machine Learning Model?

no code implementations25 Oct 2021 Muhammad Usman, Divya Gopinath, Corina S. Păsăreanu

The efficacy of machine learning models is typically determined by computing their accuracy on test data sets.

BIG-bench Machine Learning

A scalable and fast artificial neural network syndrome decoder for surface codes

no code implementations12 Oct 2021 Spiro Gicev, Lloyd C. L. Hollenberg, Muhammad Usman

Surface code error correction offers a highly promising pathway to achieve scalable fault-tolerant quantum computing.

Semi-supervised Learning with Missing Values Imputation

no code implementations3 Jun 2021 Buliao Huang, Yunhui Zhu, Muhammad Usman, Huanhuan Chen

SSCFlow explicitly utilizes the label information to facilitate the imputation and classification simultaneously by estimating the conditional distribution of incomplete instances with a novel semi-supervised normalizing flow.

Classification Denoising +2

q-RBFNN:A Quantum Calculus-based RBF Neural Network

1 code implementation2 Jun 2021 Syed Saiq Hussain, Muhammad Usman, Taha Hasan Masood Siddique, Imran Naseem, Roberto Togneri, Mohammed Bennamoun

In this research a novel stochastic gradient descent based learning approach for the radial basis function neural networks (RBFNN) is proposed.

Envisioning security control in renewable dominated power systems through stochastic multi-period AC security constrained optimal power flow

no code implementations30 Apr 2021 Mohammad Iman Alizadeh, Muhammad Usman, Florin Capitanescu

To address the latter issue, this paper envisions N-1 security control in RES dominated power systems through stochastic multi-period AC security constrained optimal power flow (SCOPF).


NNrepair: Constraint-based Repair of Neural Network Classifiers

1 code implementation23 Mar 2021 Muhammad Usman, Divya Gopinath, Youcheng Sun, Yannic Noller, Corina Pasareanu

We present novel strategies to enable precise yet efficient repair such as inferring correctness specifications to act as oracles for intermediate layer repair, and generation of experts for each class.

Fault localization

Compliance Requirements in Large-Scale Software Development: An Industrial Case Study

no code implementations2 Mar 2021 Muhammad Usman, Michael Felderer, Michael Unterkalmsteiner, Eriks Klotins, Daniel Mendez, Emil Alegroth

Regulatory compliance is a well-studied area, including research on how to model, check, analyse, enact, and verify compliance of software.

Software Engineering

The Diabetic Buddy: A Diet Regulator andTracking System for Diabetics

no code implementations8 Jan 2021 Muhammad Usman, Kashif Ahmad, Amir Sohail, Marwa Qaraqe

In this regard, there is a need to build automatic tools to monitor the blood glucose levels of diabetics and their daily food intake.

Food Recognition

Graph-Based Generative Representation Learning of Semantically and Behaviorally Augmented Floorplans

no code implementations8 Dec 2020 Vahid Azizi, Muhammad Usman, Honglu Zhou, Petros Faloutsos, Mubbasir Kapadia

We present a floorplan embedding technique that uses an attributed graph to represent the geometric information as well as design semantics and behavioral features of the inhabitants as node and edge attributes.

Representation Learning

AFP-SRC: Identification of Antifreeze Proteins Using Sparse Representation Classifier

1 code implementation11 Sep 2020 Shujaat Khan, Muhammad Usman, Abdul Wahab

In this research, we propose a computational framework for the prediction of AFPs which is essentially based on a sample-specific classification method using the sparse reconstruction.


A Systematic Survey of Regularization and Normalization in GANs

1 code implementation19 Aug 2020 Ziqiang Li, Muhammad Usman, Rentuo Tao, Pengfei Xia, Chaoyue Wang, Huanhuan Chen, Bin Li

Although a handful number of regularization and normalization methods have been proposed for GANs, to the best of our knowledge, there exists no comprehensive survey that primarily focuses on objectives and development of these methods, apart from some in-comprehensive and limited scope studies.

Data Augmentation

Security and Privacy in IoT Using Machine Learning and Blockchain: Threats & Countermeasures

no code implementations10 Feb 2020 Nazar Waheed, Xiangjian He, Muhammad Ikram, Saad Sajid Hashmi, Muhammad Usman

In this paper, we provide a summary of research efforts made in the past few years, starting from 2008 to 2019, addressing security and privacy issues using ML algorithms and BCtechniques in the IoT domain.

BIG-bench Machine Learning

Volumetric Lung Nodule Segmentation using Adaptive ROI with Multi-View Residual Learning

no code implementations31 Dec 2019 Muhammad Usman, Byoung-Dai Lee, Shi Sub Byon, Sung Hyun Kim, Byung-ilLee

The proposed technique can be segregated into two stages, at the first stage, it takes a 2-D ROI containing the nodule as input and it performs patch-wise investigation along the axial axis with a novel adaptive ROI strategy.

Lung Nodule Segmentation

A Study of the Learnability of Relational Properties: Model Counting Meets Machine Learning (MCML)

no code implementations25 Dec 2019 Muhammad Usman, Wenxi Wang, Kaiyuan Wang, Marko Vasic, Haris Vikalo, Sarfraz Khurshid

However, MCML metrics based on model counting show that the performance can degrade substantially when tested against the entire (bounded) input space, indicating the high complexity of precisely learning these properties, and the usefulness of model counting in quantifying the true performance.

BIG-bench Machine Learning

AFP-CKSAAP: Prediction of Antifreeze Proteins Using Composition of k-Spaced Amino Acid Pairs with Deep Neural Network

no code implementations11 Sep 2019 Muhammad Usman, Jeong A Lee

Antifreeze proteins (AFPs) are the sub-set of ice binding proteins indispensable for the species living in extreme cold weather.


Chaotic Time Series Prediction using Spatio-Temporal RBF Neural Networks

no code implementations17 Aug 2019 Alishba Sadiq, Muhammad Sohail Ibrahim, Muhammad Usman, Muhammad Zubair, Shujaat Khan

The proposed RBF architecture is explored for the prediction of Mackey-Glass time series and results are compared with the standard RBF.

Time Series Prediction

Motion Corrected Multishot MRI Reconstruction Using Generative Networks with Sensitivity Encoding

no code implementations20 Feb 2019 Muhammad Usman, Muhammad Umar Farooq, Siddique Latif, Muhammad Asim, Junaid Qadir

The downside of multishot MRI is that it is very sensitive to subject motion and even small amounts of motion during the scan can produce artifacts in the final MR image that may cause misdiagnosis.

Motion Correction In Multishot Mri MRI Reconstruction

q-LMF: Quantum Calculus-based Least Mean Fourth Algorithm

no code implementations4 Dec 2018 Alishba Sadiq, Muhammad Usman, Shujaat Khan, Imran Naseem, Muhammad Moinuddin, Ubaid M. Al-Saggaf

The proposed $q$-least mean fourth ($q$-LMF) is an extension of least mean fourth (LMF) algorithm and it is based on the $q$-calculus which is also known as Jackson derivative.

Automating Motion Correction in Multishot MRI Using Generative Adversarial Networks

no code implementations24 Nov 2018 Siddique Latif, Muhammad Asim, Muhammad Usman, Junaid Qadir, Rajib Rana

Multishot Magnetic Resonance Imaging (MRI) has recently gained popularity as it accelerates the MRI data acquisition process without compromising the quality of final MR image.

Image Reconstruction Motion Correction In Multishot Mri

Using Deep Autoencoders for Facial Expression Recognition

no code implementations25 Jan 2018 Muhammad Usman, Siddique Latif, Junaid Qadir

Feature descriptors involved in image processing are generally manually chosen and high dimensional in nature.

Dimensionality Reduction Facial Expression Recognition (FER)

Phonocardiographic Sensing using Deep Learning for Abnormal Heartbeat Detection

no code implementations25 Jan 2018 Siddique Latif, Muhammad Usman, Rajib Rana, Junaid Qadir

Our choice of RNNs is motivated by the great success of deep learning in medical applications and by the observation that RNNs represent the deep learning configuration most suitable for dealing with sequential or temporal data even in the presence of noise.

Heartbeat Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.