Search Results for author: Muhammad Usman

Found 24 papers, 6 papers with code

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

NEUROSPF: A tool for the Symbolic Analysis of Neural Networks

1 code implementation27 Feb 2021 Muhammad Usman, Yannic Noller, Corina Pasareanu, Youcheng Sun, Divya Gopinath

This paper presents NEUROSPF, a tool for the symbolic analysis of neural networks.

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

no code implementations19 Aug 2020 Ziqiang Li, Xintian Wu, Muhammad Usman, Rentuo Tao, Pengfei Xia, Huanhuan Chen, Bin Li

In this work, we conduct a comprehensive survey on the regularization and normalization techniques from different perspectives of GANs training.

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.

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.

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 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 +1

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.