Papers by Raza ul Mustafa
Journal of Network and Systems Management
Proceedings of the 1st Mile-High Video Conference, 2022
With the recent rise of video traffic, it is imperative to ensure Quality of Experience (QoE). Th... more With the recent rise of video traffic, it is imperative to ensure Quality of Experience (QoE). The increasing adoption of end-to-end encryption hampers any payload inspection method for QoE assessments. This poses an additional challenge for network operators to monitor DASH video QoE of a user, which by itself is tricky due to the adaptive behaviour of HTTP Adaptive Streaming (HAS) mechanisms. To tackle these issues, we present a time-slot (window) QoE experience detection method based on network level Quality of Service (QoS) features for encrypted traffic. The proposed method continuously extracts relevant QoE features for HTTP Adaptive Streaming (HAS) from encrypted stream in real-time fashion basically, packet size and arrival time in a time-slot of (1,2,3,4,5)-seconds. Then, we derive Inter Packet Gap (IPG) metrics from arrival time that result in three recursive flow features (EMA, DEMA, CUSUM) to estimate the objective QoE following the ITU-P.1203 standard. Finally, we compute (packet size, throughput) distributions into (10-90)-percentile within each time-slot along with other QoS features such as throughput and total packets. The proposed QoS features are lightweight and do not require any chunk-detection approaches to estimate QoE, significantly reducing the complexity of the monitoring approach, and potentially improving on generalization to different HAS algorithms. We use different Machine Learning (ML) classifiers to feed the QoS features and yield a QoE category (Less QoE, Good, Excellent) based on bitrate, resolution and stall. We achieve an accuracy of 79% on predicting QoE using all ABS algorithms. Our experimental evaluation framework is based on the Mininet-WiFi wireless network emulator replaying real 5G traces. The obtained results validate the proposed methods and show high accuracy of QoE estimation of encrypted DASH traffic.
Advances in Intelligent Systems and Computing, 2020
Depression is a common mental health disorder. Despite its high prevalence, the only way of diagn... more Depression is a common mental health disorder. Despite its high prevalence, the only way of diagnosing depression is through self-reporting. However, 70% of the patients would not consult doctors at an early stage of depression. Meanwhile people increasingly relying on social media for sharing emotions, and daily life activities thus helpful for detecting their mental health. Inspired by these a total of 179 depressive individuals selected from Twitter, who have reported depression and they are on medical treatment. A sample of their recent tweets collected ranges from (200 to 3200) tweets per person. From their tweets, we selected 100 most frequently used words using Term Frequency-Inverse Document Frequency (TF-IDF). Later, we used the 14 psychological attributes in Linguistic Inquiry and Word Count (LIWC) to classify these words into emotions. Moreover, weights were assigned to each word from happy to unhappy after classification by LIWC and trained machine learning classifiers to classify the users into three classes of depression High, Medium, and Low. According to our study, better features selections and their combination will help to improve performance and accuracy of classifiers.
Advances in Bioinformatics and Biomedical Engineering, 2018
Search engines and social media are two different online data sources where search engines can pr... more Search engines and social media are two different online data sources where search engines can provide health related queries logs and Internet users' discuss their diseases, symptoms, causes, preventions and even suggest treatment by sharing their views, experiences and opinions on social media. This chapter hypothesizes that online data from Google and Twitter can provide vital first-hand healthcare information. An approach is provided for collecting twitter data by exploring contextual information gleaned from Google search queries logs. Furthermore, it is investigated that whether it is possible to use tweets to track, monitor and predict diseases, especially Influenza epidemics. Obtained results show that healthcare institutes and professional's uses social media to provide up-to date health related information and interact with public. Moreover, proposed approach is beneficial for extracting useful information regarding disease symptoms, side effects, medications and t...
Proceedings of the 16th ACM Symposium on QoS and Security for Wireless and Mobile Networks, 2020
Future fifth generation (5G) networks are envisioned to provide improved Quality-of-Experience (Q... more Future fifth generation (5G) networks are envisioned to provide improved Quality-of-Experience (QoE) for applications by means of higher data rates, low and ultra-reliable latency and very high reliability. Proving increasing beneficial for mobile devices running multimedia applications. However, there exist two main co-related challenges in multimedia delivery in 5G. Namely, balancing operator provisioning and client expectations. To this end, we investigate how to build a QoE-aware network that guarantees at run-time that the end-to-end user experience meets the end users' expectations at the same that the network's Quality of Service (QoS) varies. The contribution of this paper is twofold: First, we consider a Dynamic Adaptive Streaming over HTTP (DASH) video application in a realistic emulation environment derived from real 5G traces in static and mobility scenarios to assess the QoE performance of three state-of-art Adaptive Bitrate Streaming (ABS) algorithm categories: Hybrid-Elastic and Arbiter+; buffer-based-BBA and Logistic; and rate-based-Exponential and Conventional. Second, we propose a Machine Learning (ML) classifier to predict user satisfaction which considers network metrics, such as RTT, throughput, and number of packets. Our proposed model does not rely on knowledge about the application or specific traffic information. We show that our ML classifiers achieves a QoE prediction accuracy of 87.63 % and 79 % for static and mobility scenarios, respectively.
2020 16th International Conference on Network and Service Management (CNSM), 2020
Fifth Generation (5G) networks provide high throughput and low delay, contributing to enhanced Qu... more Fifth Generation (5G) networks provide high throughput and low delay, contributing to enhanced Quality of Experience (QoE) expectations. The exponential growth of multimedia traffic pose dichotomic challenges to simultaneously satisfy network operators, service providers, and end-user expectations. Building QoE-aware networks that provide run-time mechanisms to satisfy end-users' expectations while the end-toend network Quality of Service (QoS) varies is challenging, and motivates many ongoing research efforts. The contribution of this work is twofold. Firstly, we present a reproducible datadriven framework with a series of pre-installed Dynamic Adaptive Streaming over HTTP (DASH) tools to analyse state-of-art Adaptive Bitrate Streaming (ABS) algorithms by varying key QoS parameters in static and mobility scenarios. Secondly, we introduce an interactive Jupyter notebook and Binder service providing a live analytical environment, which processes the output dataset of the framework and compares the relationship of five QoE models, three QoS parameters (RTT, throughput, packets), and seven different video KPIs.
2021 6th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM), 2021
This work demonstrates performance results of Software-Defined Networking (SDN) testing that were... more This work demonstrates performance results of Software-Defined Networking (SDN) testing that were carried out on typical network topologies by using simulation. Specifically, the performance metrics that were examined included: the topology setup and tear down time, the CPU and RAM usage of the system and the latency of packet transfer between nodes. The entire investigation was conducted on a Windows PC using a Virtual Machine for running a Mininet emulator. From the meticulous analysis of the results, it is worth mentioning the following: (i) the total number of switches in a SDN architecture has a significant influence on CPU load. (ii) The RAM (Random Access Memory) consumption dependents on the number of hosts and in circumstances of excessive load it shows much higher increase compared to the usage of the CPU. (iii) The overall performance depends significantly on the type of topology and its properties.
2021 IEEE Statistical Signal Processing Workshop (SSP), 2021
5G communication technologies promise reduced latency and increased throughput, among other featu... more 5G communication technologies promise reduced latency and increased throughput, among other features. The so-called enhanced Mobile Broadband (eMBB) type of services will contribute to further adoption of video streaming services. In this work, we use a realistic emulation environment based on 5G traces to investigate how Dynamic Adaptive Streaming over HTTP (DASH) video content using three state-of-art Adaptive Bitrate Streaming (ABS) algorithms is impacted in static and mobility scenarios. Given the wide adoption of end-to-end encryption, we use machine learning (ML) models to estimate multiple key video Quality of Experience (QoE) indicators (KQIs) taking network-level Quality of Service (QoS) metrics as input features. The proposed feature extraction method does not require chunk-detection, significantly reducing the complexity of the monitoring approach and providing new means for QoE evaluation of HAS protocols. We show that our ML classifiers achieve a QoE prediction accuracy above 91%.
2020 6th IEEE Conference on Network Softwarization (NetSoft), 2020
Intent-Based Networking (IBN) proposals are based on autonomous closed-loop orchestration archite... more Intent-Based Networking (IBN) proposals are based on autonomous closed-loop orchestration architectures that monitor and tune network performance. To this end, IBN defines high-level policies and actions implemented by a closed-loop system. This work demonstrates a Closed Control Loop (CCL) architecture for video service assurance using Machine Learning (ML) based Quality of Experience (QoE) estimation at edge nodes. As part of the solution, network-level Quality of Service (QoS) metrics patterns (e.g., RTT, Throughput) collected through flow-level monitoring are used to build a QoS-to-QoE correlation model tailored to specific target network regions, user groups, and services, in our case DASH video streaming. The demo will showcase the CCL workflow triggering the Orchestrator to take appropriate network-level actions to overcome network QoS degradations and restore the QoE target based on the intent associated with the video service.
Journal of Ambient Intelligence and Humanized Computing, 2020
The quality of this reproduction is dependent upon the quality of the copy submitted. Broken or i... more The quality of this reproduction is dependent upon the quality of the copy submitted. Broken or indistinct print, colored or poor quality illustrations and photographs, print bleed-through, substandard margins, and improper alignment can adversely affect reproduction. In the unlikely event that the author did not send a complete manuscript and there are missing pages, these will be noted. Also, if unauthorized copyright material had to be removed, a note will indicate the deletion.
Mehran University Research Journal of Engineering and Technology, 2017
Internet has revolutionized the human life. SEs (Search Engines) are one of the major tools being... more Internet has revolutionized the human life. SEs (Search Engines) are one of the major tools being used for finding information over the Internet. SEs enlist the information into links as per relevance to the searched query. A searcher usually visits the top web links retrieved on SERPs (Search Engine Results Pages) in response to a search query. With the evolving nature of Internet and the increasing number of competitors; it is hard to maintain high ranking in SERPs even for professional correspondents. However, correspondents can apply the techniques of web micro-data to achieve high CTR (Click through Rate) in SERPs. Ranking in major SEs is still a critical factor, although in certain cases such as movies, books, recipes rich snippets proved profitable for webmasters. This study aims to address the gap in micro-data moving from top category such as Animals to their limited scope. Animals with information such as name, price, category will have high CTR and hence more user satisfaction for specified result will lead to high ranking in SERPs.
ABSTRACTIntroductionDiverticulitis is the inflammation and/or infection of small pouches known as... more ABSTRACTIntroductionDiverticulitis is the inflammation and/or infection of small pouches known as diverticula that develop along the walls of the intestines. Patients with diverticulitis are at risk of mortality as high as 17% with abscess formation and 45% with secondary perforation, especially patients that get admitted to the inpatient services are at risk of complications including mortality. We developed a deep neural networks (DNN) based machine learning framework that could predict premature death in patients that are admitted with diverticulitis using electronic health records (EHR) to calculate the statistically significant risk factors first and then to apply deep neural network.MethodsOur proposed framework (Deep FLAIM) is a two-phase hybrid works framework. In the first phase, we used National In-patient Sample 2014 dataset to extract patients with diverticulitis patients with and without hemorrhage with the ICD-9 codes 562.11 and 562.13 respectively and analyzed these p...
Mehran University Research Journal of Engineering and Technology, 2018
Background and Objective: Paralytic Ileus (PI) is the pseudo-obstruction of the intestine seconda... more Background and Objective: Paralytic Ileus (PI) is the pseudo-obstruction of the intestine secondary to intestinal muscle paralysis. PI is caused by several reasons such as overuse of medications, spinal injuries, inflammation, abdominal surgery, etc. We have developed an early mortality prediction framework that can help intensivist, surgeons, and other medical professionals to optimize clinical management for PI patients in terms of optimal treatment strategy and resource planning. Methods: We used a publicly available ICU database called MIMIC III v1.4, extracted patients that had paralytic ileus as a primary diagnosis over the age of 18 years old. We developed the FLAIM Framework a two-phase model (Phase I: Statistical testing and Phase II: Machine Learning application) that compared to traditional methods of machine learning. We used five different machine learning algorithms to test the validity of our Framework. We evaluated the effectiveness of the proposed framework by compa...
Journal of Medical Imaging and Health Informatics, 2017
Malaysian Journal of Computer Science, 2017
Social media has become a platform of first choice where one can express his/her feelings with fr... more Social media has become a platform of first choice where one can express his/her feelings with freedom. The sports and matches being played are also discussed on social media such as Twitter. In this article, efforts are made to investigate the feasibility of using collective knowledge obtained from microposts posted on Twitter to predict the winner of a Cricket match. For predictions, we use three different methods that depend on the total number of tweets before the game for each team, fans sentiments toward each team and fans score predictions on Twitter. By combining these three methods, we classify winning team prediction in a Cricket game before the start of game. Our results are promising enough to be used for winning team forecast. Furthermore, the effectiveness of supervised learning algorithms is evaluated where Support Vector Machine (SVM) has shown advantage over other classifiers.
Information Discovery and Delivery, 2017
Purpose Twitter users’ generated data, known as tweets, are now not only used for communication a... more Purpose Twitter users’ generated data, known as tweets, are now not only used for communication and opinion sharing, but they are considered an important source of trendsetting, future prediction, recommendation systems and marketing. Using network features in tweet modeling and applying data mining and deep learning techniques on tweets is gaining more and more interest. Design/methodology/approach In this paper, user interests are discovered from Twitter Trends using a modeling approach that uses network-based text data (tweets). First, the popular trends are collected and stored in separate documents. These data are then pre-processed, followed by their labeling in respective categories. Data are then modeled and user interest for each Trending topic is calculated by considering positive tweets in that trend, average retweet and favorite count. Findings The proposed approach can be used to infer users’ topics of interest on Twitter and to categorize them. Support vector machine c...
Microprocessors and Microsystems, 2000
In the automatic synthesis of Finite State Machines (FSMs), the state assignment and the choice o... more In the automatic synthesis of Finite State Machines (FSMs), the state assignment and the choice of flip-flops significantly affect the cost of the combinational logic. To meet the demands of the increasing complexity of integrated circuits, we present an integrated state assignment and sequential element selection approach to synthesize area-efficient FSMs. The FSM synthesis approach is modeled as an optimization problem and is solved by using the guided evolutionary simulated annealing (GESA) technique. The GESA is a new type of parallel and distributed processing approach for searching the optimal solutions. Since the optimization problem at hand is NP-hard, a distributed algorithm for the GESA technique is developed and implemented on Network of Workstations (NOW) to speedup the search process. Promising speedups are obtained by running the distributed GESA algorithm on a NOW. Efficacy of the proposed technique is demonstrated by carrying out a comparison with other state-of-the-art techniques such as the MUSTANG, NOVA and JEDI for MCNC benchmarks. The proposed integrated state assignment and sequential element selection approach allows all types of flip-flops and offers considerable improvement in PLA area as compared to the existing techniques that use only D type flip-flops as the sequential element.
IEE Proceedings - Computers and Digital Techniques, 1998
Scheduling a parallel program is a crucial step in effectively harnessing the computing power of ... more Scheduling a parallel program is a crucial step in effectively harnessing the computing power of a heterogeneous computing system. Obtaining a minimum finish time schedule for a set of precedence constrained tasks is a well known NP-complete problem. Heterogeneity in parallel systems introduces an additional degree of complexity to the scheduling problem, i.e. varying speed of processors. A nonpreemptive, compile-time scheduling heuristic has been developed, designated as DPS, that uses dynamic priorities based on the difference between 6-level and t-level to map and schedule directed acyclic graphs (DAGS) onto heterogeneous processors, with the objective of minimising the schedule length. In the case of homogeneous processors, it is not difficult to compute the b-level and t-level, since the task execution costs are fixed. However, in the case of heterogeneous processors, as each task has a different execution cost on each processor, the blevel and t-level lose their traditional meaning. The b-level and t-level have been computed in a different and effective way that captures the changes which occurred in the DAG during scheduling. Dynamic priorities are thus determined during the scheduling process in order to avoid scheduling less important tasks before the more important ones. Moreover, the effect of changing the task execution cost to compute the 6-level and t-level has also been studied. The effectiveness of the algorithm is demonstrated by comparing it against two of the existing closely related algorithms for randomly generated graphs. DPS outperforms both algorithms by a considerable margin and has a reasonable time complexity.
Uploads
Papers by Raza ul Mustafa