arXiv subjects

Muhammad Bilal

Publications and source records attributed to Muhammad Bilal.

At least 73 records · Page 4Linked to original sources

arXiv2021

With Great Freedom Comes Great Opportunity: Rethinking Resource Allocation for Serverless Functions

Current serverless offerings give users a limited degree of flexibility for configuring the resources allocated to their function invocations by either coupling memory and CPU resources together or providing no knobs at all. These configuration choices simplify resource allocation decisions on behalf of users, but at the same time, create deployments that are resource inefficient. In this paper, we take a principled approach to the problem of resource allocation for serverless functions, allowing this choice to be made in an automatic way that leads to the best combination of performance and cost. In particular, we systematically explore the opportunities that come with decoupling memory and CPU resource allocations and also enabling the use of different VM types. We find a rich trade-off space between performance and cost. The provider can use this in a number of ways: from exposing all these parameters to the user, to eliciting preferences for performance and cost from users, or by simply offering the same performance with lower cost. This flexibility can also enable the provider to optimize its resource utilization and enable a cost-effective service with predictable performance. Our results show that, by decoupling memory and CPU allocation, there is potential to have up to 40% lower execution cost than the preset coupled configurations that are the norm in current serverless offerings. Similarly, making the correct choice of VM instance type can provide up to 50% better execution time. Furthermore, we demonstrate that providers can utilize different instance types for the same functions to maximize resource utilization while providing performance within 10-20% of the best resource configuration for each respective function.

cs.DC↗

arXiv2021

Measuring Novelty in Autonomous Vehicles Motion Using Local Outlier Factor Algorithm

Under unexpected conditions or scenarios, autonomous vehicles (AV) are more likely to follow abnormal unplanned actions, due to the limited set of rules or amount of experience they possess at that time. Enabling AV to measure the degree at which their movements are novel in real-time may help to decrease any possible negative consequences. We propose a method based on the Local Outlier Factor (LOF) algorithm to quantify this novelty measure. We extracted features from the inertial measurement unit (IMU) sensor's readings, which captures the vehicle's motion. We followed a novelty detection approach in which the model is fitted only using the normal data. Using datasets obtained from real-world vehicle missions, we demonstrate that the suggested metric can quantify to some extent the degree of novelty. Finally, a performance evaluation of the model confirms that our novelty metric can be practical.

cs.LG↗

arXiv2021

Use of Transfer Learning and Wavelet Transform for Breast Cancer Detection

Breast cancer is one of the most common cause of deaths among women. Mammography is a widely used imaging modality that can be used for cancer detection in its early stages. Deep learning is widely used for the detection of cancerous masses in the images obtained via mammography. The need to improve accuracy remains constant due to the sensitive nature of the datasets so we introduce segmentation and wavelet transform to enhance the important features in the image scans. Our proposed system aids the radiologist in the screening phase of cancer detection by using a combination of segmentation and wavelet transforms as pre-processing augmentation that leads to transfer learning in neural networks. The proposed system with these pre-processing techniques significantly increases the accuracy of detection on Mini-MIAS.

cs.CV↗

arXiv2021

On the Impact of Device and Behavioral Heterogeneity in Federated Learning

Federated learning (FL) is becoming a popular paradigm for collaborative learning over distributed, private datasets owned by non-trusting entities. FL has seen successful deployment in production environments, and it has been adopted in services such as virtual keyboards, auto-completion, item recommendation, and several IoT applications. However, FL comes with the challenge of performing training over largely heterogeneous datasets, devices, and networks that are out of the control of the centralized FL server. Motivated by this inherent setting, we make a first step towards characterizing the impact of device and behavioral heterogeneity on the trained model. We conduct an extensive empirical study spanning close to 1.5K unique configurations on five popular FL benchmarks. Our analysis shows that these sources of heterogeneity have a major impact on both model performance and fairness, thus sheds light on the importance of considering heterogeneity in FL system design.

cs.LG↗

arXiv2020

A Comprehensive Utility Function for Resource Allocation in Mobile Edge Computing

In mobile edge computing (MEC), one of the important challenges is how much resources of which mobile edge server (MES) should be allocated to which user equipment (UE). The existing resource allocation schemes only consider CPU as the requested resource and assume utility for MESs as either a random variable or dependent on the requested CPU only. This paper presents a novel comprehensive utility function for resource allocation in MEC. The utility function considers the heterogeneous nature of applications that a UE offloads to MES. The proposed utility function considers all important parameters, including CPU, RAM, hard disk space, required time, and distance, to calculate a more realistic utility value for MESs. Moreover, we improve upon some general algorithms, used for resource allocation in MEC and cloud computing, by considering our proposed utility function. We name the improved versions of these resource allocation schemes as comprehensive resource allocation schemes. The UE requests are modeled to represent the amount of resources requested by the UE as well as the time for which the UE has requested these resources. The utility function depends upon the UE requests and the distance between UEs and MES, and serves as a realistic means of comparison between different types of UE requests. Choosing (or selecting) an optimal MES with the optimal amount of resources to be allocated to each UE request is a challenging task. We show that MES resource allocation is sub-optimal if CPU is the only resource considered. By taking into account the other resources, i.e., RAM, disk space, request time, and distance in the utility function, we demonstrate improvement in the resource allocation algorithms in terms of service rate, utility, and MES energy consumption.

cs.NI↗

arXiv2020

Single Board Computers (SBC): The Future of Next Generation Pedagogies in Pakistan

ARM processors have taken over the mobile industry from a long time now. Future of data centers and the IT industry is estimated to make use of ARM Processors. Projects like Openstack on ARM are enabling use of ARM in data centers . Single board computers (SBCs) based on ARM processors have become the norm these days. Reason for their popularity lies in their cost effective and power efficient nature. There are hundreds of them available in the market having different sizes, compute power and prices. The reason for their popularity is largely due to the rise of new technology called IoT (Internet of Things) but there is another perspective where they can become handy. Low Price and Power Usage of single board computers makes them top candidate to be used for teaching many courses with hands-on experience in developing countries like Pakistan. Many boards support full Linux distributions and can be used as general-purpose computers while many of them are open hardware based. In this paper, we have reviewed the famous options available and tried to figure out which of them are better for teaching what kind of courses.

cs.CY↗

arXiv2020

Remote Sensing to Control Respiratory Viral Diseases Outbreaks using Internet of Vehicles

The respiratory viral diseases, such as those caused by the family of coronaviruses, can be extremely contagious and spread through saliva droplets generated by coughing, sneezing, or breathing. In humans, the most common symptoms of the infection include fever and difficulty in breathing. In order to reduce the diffusion of the current "Coronavirus disease 2019 (COVID-19)" pandemic, the Internet of Things (IoT) technologies can play an important role; for instance, they can be effectively used for implementing a real-time patient tracking and warning system at a city scale. Crucial places to install the tracking IoT devices are the public/private vehicles that, augmented with multiple connectivity solutions, can implement the Internet of Vehicles (IoV) paradigm. In such a ubiquitous network environment, vehicles are equipped with a variety of sensors, including regular cameras that can be replaced with thermal cameras. Therefore, this paper proposes a new design for widely detecting respiratory viral diseases that leverages IoV to collect real-time body temperature and breathing rate measurements of pedestrians. This information can be used to recognize geographic areas affected by possible COVID-19 cases and to implement proactive preventive strategies that would further limit the spread of the disease.

physics.soc-ph↗

arXiv2020

Unsupervised Adversarial Domain Adaptation for Cross-Lingual Speech Emotion Recognition

Cross-lingual speech emotion recognition (SER) is a crucial task for many real-world applications. The performance of SER systems is often degraded by the differences in the distributions of training and test data. These differences become more apparent when training and test data belong to different languages, which cause a significant performance gap between the validation and test scores. It is imperative to build more robust models that can fit in practical applications of SER systems. Therefore, in this paper, we propose a Generative Adversarial Network (GAN)-based model for multilingual SER. Our choice of using GAN is motivated by their great success in learning the underlying data distribution. The proposed model is designed in such a way that can learn language invariant representations without requiring target-language data labels. We evaluate our proposed model on four different language emotional datasets, including an Urdu-language dataset to also incorporate alternative languages for which labelled data is difficult to find and which have not been studied much by the mainstream community. Our results show that our proposed model can significantly improve the baseline cross-lingual SER performance for all the considered datasets including the non-mainstream Urdu language data without requiring any labels.

cs.SD↗

arXiv2020

Classification of Arrhythmia by Using Deep Learning with 2-D ECG Spectral Image Representation

The electrocardiogram (ECG) is one of the most extensively employed signals used in the diagnosis and prediction of cardiovascular diseases (CVDs). The ECG signals can capture the heart's rhythmic irregularities, commonly known as arrhythmias. A careful study of ECG signals is crucial for precise diagnoses of patients' acute and chronic heart conditions. In this study, we propose a two-dimensional (2-D) convolutional neural network (CNN) model for the classification of ECG signals into eight classes; namely, normal beat, premature ventricular contraction beat, paced beat, right bundle branch block beat, left bundle branch block beat, atrial premature contraction beat, ventricular flutter wave beat, and ventricular escape beat. The one-dimensional ECG time series signals are transformed into 2-D spectrograms through short-time Fourier transform. The 2-D CNN model consisting of four convolutional layers and four pooling layers is designed for extracting robust features from the input spectrograms. Our proposed methodology is evaluated on a publicly available MIT-BIH arrhythmia dataset. We achieved a state-of-the-art average classification accuracy of 99.11\%, which is better than those of recently reported results in classifying similar types of arrhythmias. The performance is significant in other indices as well, including sensitivity and specificity, which indicates the success of the proposed method.

eess.SP↗

arXiv2020

Amateur Drones Detection: A machine learning approach utilizing the acoustic signals in the presence of strong interference

Owing to small size, sensing capabilities and autonomous nature, the Unmanned Air Vehicles (UAVs) have enormous applications in various areas, e.g., remote sensing, navigation, archaeology, journalism, environmental science, and agriculture. However, the unmonitored deployment of UAVs called the amateur drones (AmDr) can lead to serious security threats and risk to human life and infrastructure. Therefore, timely detection of the AmDr is essential for the protection and security of sensitive organizations, human life and other vital infrastructure. AmDrs can be detected using different techniques based on sound, video, thermal, and radio frequencies. However, the performance of these techniques is limited in sever atmospheric conditions. In this paper, we propose an efficient unsupervise machine learning approach of independent component analysis (ICA) to detect various acoustic signals i.e., sounds of bird, airplanes, thunderstorm, rain, wind and the UAVs in practical scenario. After unmixing the signals, the features like Mel Frequency Cepstral Coefficients (MFCC), the power spectral density (PSD) and the Root Mean Square Value (RMS) of the PSD are extracted by using ICA. The PSD and the RMS of PSD signals are extracted by first passing the signals from octave band filter banks. Based on the above features the signals are classified using Support Vector Machines (SVM) and K Nearest Neighbor (KNN) to detect the presence or absence of AmDr. Unique feature of the proposed technique is the detection of a single or multiple AmDrs at a time in the presence of multiple acoustic interfering signals. The proposed technique is verified through extensive simulations and it is observed that the RMS values of PSD with KNN performs better than the MFCC with KNN and SVM.

eess.AS↗

arXiv2020

Classification of Chest Diseases using Wavelet Transforms and Transfer Learning

Chest X-ray scan is a most often used modality by radiologists to diagnose many chest related diseases in their initial stages. The proposed system aids the radiologists in making decision about the diseases found in the scans more efficiently. Our system combines the techniques of image processing for feature enhancement and deep learning for classification among diseases. We have used the ChestX-ray14 database in order to train our deep learning model on the 14 different labeled diseases found in it. The proposed research shows the significant improvement in the results by using wavelet transforms as pre-processing technique.

eess.IV↗

arXiv2020

Secure and Robust Machine Learning for Healthcare: A Survey

Recent years have witnessed widespread adoption of machine learning (ML)/deep learning (DL) techniques due to their superior performance for a variety of healthcare applications ranging from the prediction of cardiac arrest from one-dimensional heart signals to computer-aided diagnosis (CADx) using multi-dimensional medical images. Notwithstanding the impressive performance of ML/DL, there are still lingering doubts regarding the robustness of ML/DL in healthcare settings (which is traditionally considered quite challenging due to the myriad security and privacy issues involved), especially in light of recent results that have shown that ML/DL are vulnerable to adversarial attacks. In this paper, we present an overview of various application areas in healthcare that leverage such techniques from security and privacy point of view and present associated challenges. In addition, we present potential methods to ensure secure and privacy-preserving ML for healthcare applications. Finally, we provide insight into the current research challenges and promising directions for future research.

cs.LG↗

arXiv2020

RDSP: Rapidly Deployable Wireless Ad Hoc System for Post-Disaster Management

In post-disaster scenarios, such as after floods, earthquakes, and in war zones, the cellular communication infrastructure may be destroyed or seriously disrupted. In such emergency scenarios, it becomes very important for first aid responders to communicate with other rescue teams in order to provide feedback to both the central office and the disaster survivors. To address this issue, rapidly deployable systems are required to re-establish connectivity and assist users and first responders in the region of incident. In this work, we describe the design, implementation, and evaluation of a rapidly deployable system for first response applications in post-disaster situations, named RDSP. The proposed system helps early rescue responders and victims by sharing their location information to remotely located servers by utilizing a novel routing scheme. This novel routing scheme consists of the Dynamic ID Assignment (DIA) algorithm and the Minimum Maximum Neighbor (MMN) algorithm. The DIA algorithm is used by relay devices to dynamically select their IDs on the basis of all the available IDs of networks. Whereas, the MMN algorithm is used by the client and relay devices to dynamically select their next neighbor relays for the transmission of messages. The RDSP contains three devices; the client device sends the victim's location information to the server, the relay device relays information between client and server device, the server device receives messages from the client device to alert the rescue team. We deployed and evaluated our system in the outdoor environment of the university campus. The experimental results show that the RDSP system reduces the message delivery delay and improves the message delivery ratio with lower communication overhead.

cs.NI↗

arXiv2019

Secure Distribution of Protected Content in Information-Centric Networking

The benefits of the ubiquitous caching in ICN are profound, such features make ICN promising for content distribution, but it also introduces a challenge to content protection against the unauthorized access. The protection of a content against unauthorized access requires consumer authentication and involves the conventional end-to-end encryption. However, in information-centric networking (ICN), such end-to-end encryption makes the content caching ineffective since encrypted contents stored in a cache are useless for any consumers except those who know the encryption key. For effective caching of encrypted contents in ICN, we propose a secure distribution of protected content (SDPC) scheme, which ensures that only authenticated consumers can access the content. SDPC is lightweight and allows consumers to verify the originality of the published content by using a symmetric key encryption. Moreover, SDPC naming scheme provides protection against privacy leakage. The security of SDPC was proved with the BAN logic and Scyther tool verification, and simulation results show that SDPC can reduce the content download delay.

cs.NI↗

arXiv2019

Software-Defined Network-Based Vehicular Networks: A Position Paper on Their Modeling and Implementation

There is a strong devotion in the automotive industry to be part of a wider progression towards the Fifth Generation (5G) era. In-vehicle integration costs between cellular and vehicle-to-vehicle networks using Dedicated Short Range Communication could be avoided by adopting Cellular Vehicle-to-Everything (C-V2X) technology with the possibility to re-use the existing mobile network infrastructure. More and more, with the emergence of Software Defined Networks, the flexibility and the programmability of the network have not only impacted the design of new vehicular network architectures but also the implementation of V2X services in future intelligent transportation systems. In this paper, we define the concepts that help evaluate software-defined-based vehicular network systems in the literature based on their modeling and implementation schemes. We first overview the current studies available in the literature on C-V2X technology in support of V2X applications. We then present the different architectures and their underlying system models for LTE-V2X communications. We later describe the key ideas of software-defined networks and their concepts for V2X services. Lastly, we provide a comparative analysis of existing SDN-based vehicular network system grouped according to their modeling and simulation concepts. We provide a discussion and highlight vehicular ad-hoc networks' challenges handled by SDN-based vehicular networks.

cs.NI↗

arXiv2019

Crowd Density Estimation using Novel Feature Descriptor

Crowd density estimation is an important task for crowd monitoring. Many efforts have been done to automate the process of estimating crowd density from images and videos. Despite series of efforts, it remains a challenging task. In this paper, we proposes a new texture feature-based approach for the estimation of crowd density based on Completed Local Binary Pattern (CLBP). We first divide the image into blocks and then re-divide the blocks into cells. For each cell, we compute CLBP and then concatenate them to describe the texture of the corresponding block. We then train a multi-class Support Vector Machine (SVM) classifier, which classifies each block of image into one of four categories, i.e. Very Low, Low, Medium, and High. We evaluate our technique on the PETS 2009 dataset, and from the experiments, we show to achieve 95% accuracy for the proposed descriptor. We also compare other state-of-the-art texture descriptors and from the experimental results, we show that our proposed method outperforms other state-of-the-art methods.

cs.CV↗

arXiv2019

A deep learning approach for analyzing the composition of chemometric data

We propose novel deep learning based chemometric data analysis technique. We trained L2 regularized sparse autoencoder end-to-end for reducing the size of the feature vector to handle the classic problem of the curse of dimensionality in chemometric data analysis. We introduce a novel technique of automatic selection of nodes inside the hidden layer of an autoencoder through Pareto optimization. Moreover, Gaussian process regressor is applied on the reduced size feature vector for the regression. We evaluated our technique on orange juice and wine dataset and results are compared against 3 state-of-the-art methods. Quantitative results are shown on Normalized Mean Square Error (NMSE) and the results show considerable improvement in the state-of-the-art.

cs.LG↗

arXiv2019

Socially-Aware Congestion Control in Ad-Hoc Networks: Current Status and The Way Forward

Ad-hoc social networks (ASNETs) represent a special type of traditional ad-hoc network in which a user's social properties (such as the social connections and communications metadata as well as application data) are leveraged for offering enhanced services in a distributed infrastructureless environments. However, the wireless medium, due to limited bandwidth, can easily suffer from the problem of congestion when social metadata and application data are exchanged among nodes---a problem that is compounded by the fact that some nodes may act selfishly and not share its resources. While a number of congestion control schemes have been proposed for the traditional ad-hoc networks, there has been limited focus on incorporating social awareness into congestion control schemes. We revisit the existing traditional ad-hoc congestion control and data distribution protocols and motivate the need for embedding social awareness into these protocols to improve performance. We report that although some work is available in opportunistic network that uses socially-aware techniques to control the congestion issue, this area is largely unexplored and warrants more research attention. In this regards, we highlight the current research progress and identify multiple future directions of research.

cs.NI↗