Searcharxiv⌕ Search

arXiv subjects

Muhammad Usman

Publications and source records attributed to Muhammad Usman.

At least 181 records · Page 10Linked to original sources

Semi-supervised Learning with Missing Values Imputation

Incomplete instances with various missing attributes in many real-world applications have brought challenges to the classification tasks. Missing values imputation methods are often employed to replace the missing values with substitute values. However, this process often separates the imputation and classification, which may lead to inferior performance since label information are often ignored during imputation. Moreover, traditional methods may rely on improper assumptions to initialize the missing values, whereas the unreliability of such initialization might lead to inferior performance. To address these problems, a novel semi-supervised conditional normalizing flow (SSCFlow) is proposed in this paper. 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. Moreover, SSCFlow treats the initialized missing values as corrupted initial imputation and iteratively reconstructs their latent representations with an overcomplete denoising autoencoder to approximate their true conditional distribution. Experiments on real-world datasets demonstrate the robustness and effectiveness of the proposed algorithm.

cs.LG↗

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

The accelerated penetration rate of renewable energy sources (RES) brings environmental benefits at the expense of increasing operation cost and undermining the satisfaction of the N-1 security criterion. 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). The paper extends the state-of-the-art, i.e. deterministic and single time period AC SCOPF, to capture two new dimensions, RES stochasticity and multiple time periods, as well as emerging sources of flexibility such as flexible loads (FL) and energy storage systems (ESS). Accordingly, the paper proposes and solves for the first time a new problem formulation in the form of stochastic multi-period AC SCOPF (S-MP-SCOPF). The S-MP-SCOPF is formulated as a non-linear programming (NLP) problem. It computes optimal setpoints of flexibility resources and other conventional control means for congestion management and voltage control in day-ahead operation. Another salient feature of this paper is the comprehensive and accurate modelling, using: AC power flow model for both pre-contingency and post-contingency states, inter-temporal constraints for resources such as FL and ESS in a 24-hours time horizon and RES uncertainties. The importance and performances of the proposed model through a direct approach, pushing the problem size up to the solver limit, are illustrated on two test systems of 5 nodes and 60 nodes, respectively, while future work will develop a tractable algorithm.

eess.SY↗

NNrepair: Constraint-based Repair of Neural Network Classifiers

We present NNrepair, a constraint-based technique for repairing neural network classifiers. The technique aims to fix the logic of the network at an intermediate layer or at the last layer. NNrepair first uses fault localization to find potentially faulty network parameters (such as the weights) and then performs repair using constraint solving to apply small modifications to the parameters to remedy the defects. 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. We demonstrate the technique in the context of three different scenarios: (1) Improving the overall accuracy of a model, (2) Fixing security vulnerabilities caused by poisoning of training data and (3) Improving the robustness of the network against adversarial attacks. Our evaluation on MNIST and CIFAR-10 models shows that NNrepair can improve the accuracy by 45.56 percentage points on poisoned data and 10.40 percentage points on adversarial data. NNrepair also provides small improvement in the overall accuracy of models, without requiring new data or re-training.

cs.LG↗

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

In this research a novel stochastic gradient descent based learning approach for the radial basis function neural networks (RBFNN) is proposed. The proposed method is based on the q-gradient which is also known as Jackson derivative. In contrast to the conventional gradient, which finds the tangent, the q-gradient finds the secant of the function and takes larger steps towards the optimal solution. The proposed $q$-RBFNN is analyzed for its convergence performance in the context of least square algorithm. In particular, a closed form expression of the Wiener solution is obtained, and stability bounds of the learning rate (step-size) is derived. The analytical results are validated through computer simulation. Additionally, we propose an adaptive technique for the time-varying $q$-parameter to improve convergence speed with no trade-offs in the steady state performance.

cs.LG↗

On the flat galactic rotational curves in $f(\mathcal{R})$ gravity

A mysterious dark matter is supposed to exist in the galactic halos. In this contrast, we discuss the possibility of explaining the flat rotational velocity curves in f(R) gravity by solving field equations numerically in vacuum and for different matter distributions. For a spherically symmetric static space-time (as the galactic environment) we give metric for constant rotational velocity regions. For a constant rotational velocity region, we prove that all values of rotational velocities (most importantly observed rotational velocity ~200-300Km/s) do not lead to an analytic solution of the vacuum field equations. We then obtain numerical solutions of the field equations in vacuum and for three types of mass distributions named: (1) power law density profile, (2) simple model for galaxy with a core and, (3) Navarro, Frank and White (NFW) profile, for M31 and Milky way galaxy. The solutions suggest a slight modification from linear relations from R for vacuum whereas a significant deviation from R for the distributions can give flat rotational curves. Using Brans-Dicke theory, we also relate obtained modified gravity function with the equivalent scalar fields, the procedure gives us very interesting phenomena and behavior of dark matter in the galactic environment. We observe that the scalar dark matter, coming from different modified gravity functions of matter profiles, does not accumulate as the baryonic matter. These results then can be used to explain the spatial offset of the center of the total mass from the center of the baryonic mass peaks of the bullet cluster and Abell-520.

physics.gen-ph↗

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

Regulatory compliance is a well-studied area, including research on how to model, check, analyse, enact, and verify compliance of software. However, while the theoretical body of knowledge is vast, empirical evidence on challenges with regulatory compliance, as faced by industrial practitioners particularly in the Software Engineering domain, is still lacking. In this paper, we report on an industrial case study which aims at providing insights into common practices and challenges with checking and analysing regulatory compliance, and we discuss our insights in direct relation to the state of reported evidence. Our study is performed at Ericsson AB, a large telecommunications company, which must comply to both locally and internationally governing regulatory entities and standards such as GDPR. The main contributions of this work are empirical evidence on challenges experienced by Ericsson that complement the existing body of knowledge on regulatory compliance.

cs.SE↗

NEUROSPF: A tool for the Symbolic Analysis of Neural Networks

This paper presents NEUROSPF, a tool for the symbolic analysis of neural networks. Given a trained neural network model, the tool extracts the architecture and model parameters and translates them into a Java representation that is amenable for analysis using the Symbolic PathFinder symbolic execution tool. Notably, NEUROSPF encodes specialized peer classes for parsing the model's parameters, thereby enabling efficient analysis. With NEUROSPF the user has the flexibility to specify either the inputs or the network internal parameters as symbolic, promoting the application of program analysis and testing approaches from software engineering to the field of machine learning. For instance, NEUROSPF can be used for coverage-based testing and test generation, finding adversarial examples and also constraint-based repair of neural networks, thus improving the reliability of neural networks and of the applications that use them. Video URL: https://youtu.be/seal8fG78LI

cs.LG↗

The Diabetic Buddy: A Diet Regulator andTracking System for Diabetics

The prevalence of Diabetes mellitus (DM) in the Middle East is exceptionally high as compared to the rest of the world. In fact, the prevalence of diabetes in the Middle East is 17-20%, which is well above the global average of 8-9%. Research has shown that food intake has strong connections with the blood glucose levels of a patient. In this regard, there is a need to build automatic tools to monitor the blood glucose levels of diabetics and their daily food intake. This paper presents an automatic way of tracking continuous glucose and food intake of diabetics using off-the-shelf sensors and machine learning, respectively. Our system not only helps diabetics to track their daily food intake but also assists doctors to analyze the impact of the food in-take on blood glucose in real-time. For food recognition, we collected a large-scale Middle-Eastern food dataset and proposed a fusion-based framework incorporating several existing pre-trained deep models for Middle-Eastern food recognition.

cs.CV↗

Recent Trends in Food Intake Monitoring using Wearable Sensors

Obesity and being over-weight add to the risk of some major life threatening diseases. According to W.H.O., a considerable population suffers from these disease whereas poor nutrition plays an important role in this context. Traditional food activity monitoring systems like Food Diaries allow manual record keeping of eating activities over time, and conduct nutrition analysis. However, these systems are prone to the problems of manual record keeping and biased-reporting. Therefore, recently, the research community has focused on designing automatic food monitoring systems since the last decade which consist of one or multiple wearable sensors. These systems aim at providing different macro and micro activity detections like chewing, swallowing, eating episodes, and food types as well as estimations like food mass and eating duration. Researchers have emphasized on high detection accuracy, low estimation errors, un-intrusive nature, low cost and real life implementation while designing these systems, however a comprehensive automatic food monitoring system has yet not been developed. Moreover, according to the best of our knowledge, there is no comprehensive survey in this field that delineates the automatic food monitoring paradigm, covers a handful number of research studies, analyses these studies against food intake monitoring tasks using various parameters, enlists the limitations and sets up future directions. In this research work, we delineate the automatic food intake monitoring paradigm and present a survey of research studies. With special focus on studies with wearable sensors, we analyze these studies against food activity monitoring tasks. We provide brief comparison of these studies along with shortcomings based upon experimentation results conducted under these studies. We setup future directions at the end to facilitate the researchers working in this domain.

cs.HC↗

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

Floorplans are commonly used to represent the layout of buildings. In computer aided-design (CAD) floorplans are usually represented in the form of hierarchical graph structures. Research works towards computational techniques that facilitate the design process, such as automated analysis and optimization, often use simple floorplan representations that ignore the semantics of the space and do not take into account usage related analytics. 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. A Long Short-Term Memory (LSTM) Variational Autoencoder (VAE) architecture is proposed and trained to embed attributed graphs as vectors in a continuous space. A user study is conducted to evaluate the coupling of similar floorplans retrieved from the embedding space with respect to a given input (e.g., design layout). The qualitative, quantitative and user-study evaluations show that our embedding framework produces meaningful and accurate vector representations for floorplans. In addition, our proposed model is a generative model. We studied and showcased its effectiveness for generating new floorplans. We also release the dataset that we have constructed and which, for each floorplan, includes the design semantics attributes as well as simulation generated human behavioral features for further study in the community.

cs.LG↗

Lightweight Encryption for the Low Powered IoT Devices

The internet of things refers to the network of devices connected to the internet and can communicate with each other. The term things is to refer non-conventional devices that are usually not connected to the internet. The network of such devices or things is growing at an enormous rate. The security and privacy of the data flowing through these things is a major concern. The devices are low powered and the conventional encryption algorithms are not suitable to be employed on these devices. In this correspondence a survey of the contemporary lightweight encryption algorithms suitable for use in the IoT environment has been presented.

cs.CR↗

Long-Range Surface-Assisted Molecule-Molecule Hybridization

Metalated phthalocyanines (Pc's) are robust and versatile molecular complexes, whose properties can be tuned by changing their functional groups and central metal atom. The electronic structure of magnesium Pc (MgPc) - structurally and electronically similar to chlorophyll - adsorbed on the Ag(100) surface is investigated by low-temperature scanning tunneling microscopy (STM) and spectroscopy (STS), non-contact atomic force microscopy (ncAFM) and density functional theory (DFT). Single, isolated MgPc's exhibit a flat, four-fold rotationally symmetric morphology, with doubly degenerate, partially populated (due to surface-to-molecule electron transfer) lowest unoccupied molecular orbitals (LUMOs). In contrast, MgPc's with neighbouring molecules in proximity undergo a lift of LUMOs degeneracy, with a near-Fermi local density of states with reduced two-fold rotational symmetry, indicative of a long-range attractive intermolecular interaction. The latter is assigned to a surface-mediated two-step electronic hybridization process. First, LUMOs interact with Ag(100) conduction electrons, forming hybrid molecule-surface orbitals with enhanced spatial extension. Then, these delocalized molecule-surface states further hybridize with those of neighbouring molecules. This work highlights how the electronic structure of molecular adsorbates - including orbital degeneracies and symmetries - can be significantly altered via surface-mediated intermolecular hybridization, over extended distances (beyond 3 nm), having important implications for prospects of molecule-based solid-state technologies.

cond-mat.mtrl-sci↗

KaFHCa: Key-establishment via Frequency Hopping Collisions

The massive deployment of IoT devices being utilized by home automation, industrial and military scenarios demands for high security and privacy standards to be achieved through innovative solutions. This paper proposes KaFHCa, a crypto-less protocol that generates shared secret keys by combining random frequency hopping collisions and source indistinguishability independently of the radio channel status. While other solutions tie the secret bit rate generation to the current radio channel conditions, thus becoming unpractical in static environments, KaFHCa guarantees almost the same secret bitrate independently of the channel conditions. KaFHCa generates shared secrets through random collisions of the transmitter and the receiver in the radio spectrum, and leverages on the fading phenomena to achieve source indistinguishability, thus preventing unauthorized eavesdroppers from inferring the key. The proposed solution is (almost) independent of the adversary position, works under the conservative assumption of channel fading (σ = 8dB), and is capable of generating a secret key of 128 bits with less than 564 transmissions.

cs.CR↗

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

This paper introduces the MCML approach for empirically studying the learnability of relational properties that can be expressed in the well-known software design language Alloy. A key novelty of MCML is quantification of the performance of and semantic differences among trained machine learning (ML) models, specifically decision trees, with respect to entire (bounded) input spaces, and not just for given training and test datasets (as is the common practice). MCML reduces the quantification problems to the classic complexity theory problem of model counting, and employs state-of-the-art model counters. The results show that relatively simple ML models can achieve surprisingly high performance (accuracy and F1-score) when evaluated in the common setting of using training and test datasets - even when the training dataset is much smaller than the test dataset - indicating the seeming simplicity of learning relational properties. 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.

cs.LG↗

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

Security and privacy of the users have become significant concerns due to the involvement of the Internet of things (IoT) devices in numerous applications. Cyber threats are growing at an explosive pace making the existing security and privacy measures inadequate. Hence, everyone on the Internet is a product for hackers. Consequently, Machine Learning (ML) algorithms are used to produce accurate outputs from large complex databases, where the generated outputs can be used to predict and detect vulnerabilities in IoT-based systems. Furthermore, Blockchain (BC) techniques are becoming popular in modern IoT applications to solve security and privacy issues. Several studies have been conducted on either ML algorithms or BC techniques. However, these studies target either security or privacy issues using ML algorithms or BC techniques, thus posing a need for a combined survey on efforts made in recent years addressing both security and privacy issues using ML algorithms and BC techniques. 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. First, we discuss and categorize various security and privacy threats reported in the past twelve years in the IoT domain. Then, we classify the literature on security and privacy efforts based on ML algorithms and BC techniques in the IoT domain. Finally, we identify and illuminate several challenges and future research directions in using ML algorithms and BC techniques to address security and privacy issues in the IoT domain.

cs.CR↗

Phonocardiographic Sensing using Deep Learning for Abnormal Heartbeat Detection

Cardiac auscultation involves expert interpretation of abnormalities in heart sounds using stethoscope. Deep learning based cardiac auscultation is of significant interest to the healthcare community as it can help reducing the burden of manual auscultation with automated detection of abnormal heartbeats. However, the problem of automatic cardiac auscultation is complicated due to the requirement of reliability and high accuracy, and due to the presence of background noise in the heartbeat sound. In this work, we propose a Recurrent Neural Networks (RNNs) based automated cardiac auscultation solution. 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. We explore the use of various RNN models, and demonstrate that these models deliver the abnormal heartbeat classification score with significant improvement. Our proposed approach using RNNs can be potentially be used for real-time abnormal heartbeat detection in the Internet of Medical Things for remote monitoring applications.

cs.CV↗

Cross Lingual Speech Emotion Recognition: Urdu vs. Western Languages

Cross-lingual speech emotion recognition is an important task for practical applications. The performance of automatic speech emotion recognition systems degrades in cross-corpus scenarios, particularly in scenarios involving multiple languages or a previously unseen language such as Urdu for which limited or no data is available. In this study, we investigate the problem of cross-lingual emotion recognition for Urdu language and contribute URDU---the first ever spontaneous Urdu-language speech emotion database. Evaluations are performed using three different Western languages against Urdu and experimental results on different possible scenarios suggest various interesting aspects for designing more adaptive emotion recognition system for such limited languages. In results, selecting training instances of multiple languages can deliver comparable results to baseline and augmentation a fraction of testing language data while training can help to boost accuracy for speech emotion recognition. URDU data is publicly available for further research.

cs.CL↗

Tunable band-gap and isotropic light absorption from bismuth-containing GaAs core$-$shell and multi$-$shell nanowires

Semiconductor core$-$shell nanowires based on the GaAs substrate are building blocks of many photonic, photovoltaic and electronic devices, thanks to the associated direct band-gap and the highly tunable optoelectronic properties. The selection of a suitable material system is crucial for custom designed nanowires tailored for optimised device performance. The bismuth containing GaAs materials are an imminent class of semiconductors which not only enable an exquisite control over the alloy strain and electronic structure but also offer the possibility to suppress internal loss mechanisms in photonic devices. Whilst the experimental efforts to incorporate GaBiAs alloys in the nanowire active region are still in primitive stage, the theoretical understanding of the optoelectronic properties of such nanowires is only rudimentary. This work elucidates and quantifies the role of nanowire physical attributes such as its geometry parameters and bismuth incorporation in designing light absorption wavelength and polarisation response. Based on multi-million atom tight-binding simulations of the GaBiAs/GaAs core$-$shell and GaAs/GaBiAs/GaAs multi$-$shell nanowires, our results predict a large tuning of the absorption wavelength, ranging from 0.9 $μ$m to 1.6 $μ$m, which can be controlled by engineering either Bi composition or nanowire diameter. The analysis of the strain profiles indicates a tensile character leading to significant light-hole mixing in the valence band states. This offers a possibility to achieve polarisation-insensitive light interaction, which is desirable for several photonic devices involving amplification and modulation of light. Furthermore, at low Bi compositions, the carrier confinement is quasi type-II, which further broadens the suitability of these nanowires for myriad applications demanding large carrier separations...

cond-mat.mtrl-sci↗