arXiv subjects

Yehia Massoud

Publications and source records attributed to Yehia Massoud.

At least 19 recordsLinked to original sources

arXiv2023

Best Memory Architecture Exploration under Parameters Variations accelerated with Machine Learning

The design of effective memory architecture is of utmost importance in modern computing systems. However, the design of memory subsystems is even more difficult today because process variation and modern design techniques like dynamic voltage scaling make performance metrics for memory assessment be treated as random variables instead of scalars at design time. Most of the previous works have studied the design of memory design from the yield analysis perspective leaving the question of the best memory organization on average open. Because examining all possible combinations of design parameter values of a memory chip would require prohibitively much time, in this work, we propose Best Arm Identification (BAI) algorithms to accelerate the exploration for the best memory architecture on average under parameter variations. Our experimental results demonstrate that we can arrive at the best memory organization 99% of the time in x5 faster than an exhaustive search of all possible conditions.

cs.AR↗

arXiv2022

Polarization-decoupled Flat Displays

Many modern applications like entertainment displays, data encryption, security, and virtual reality (VR) technology require asymmetric light manipulation. Symmetric spin-orbit interactions (SOI) apply a limit in achieving an asymmetrical metahologram. However, different reported asymmetric SOI's based on propagation and geometric phase mergence techniques effectively break this limit at the expense of design complexity and greater computation cost. This work proposes a novel helicity multiplexing technique that breaks all the aforementioned barriers in achieving on-axis dual side holograms. Benefiting from the geometric phase modulation of anisotropic nano-resonating antennas, we have employed a single unit cell to achieve helicity multiplexing. A low extinction coefficient material a-Si:H is used for device analysis. Due to the simple single unit cell-based designing technique, simulation and fabrication complexities were significantly reduced. As a result, based on the helicity and incidence direction of electromagnetic wave, we have achieved highly transmissive dual holographic images in the visible band. Our simulated efficiencies are 55%, 75%, and 80% for the blue (λ = 488 nm), green (λ = 532 nm), and red light (λ = 633 nm).

physics.optics↗

arXiv2022

Service Discovery in Social Internet of Things using Graph Neural Networks

Internet-of-Things (IoT) networks intelligently connect thousands of physical entities to provide various services for the community. It is witnessing an exponential expansion, which is complicating the process of discovering IoT devices existing in the network and requesting corresponding services from them. As the highly dynamic nature of the IoT environment hinders the use of traditional solutions of service discovery, we aim, in this paper, to address this issue by proposing a scalable resource allocation neural model adequate for heterogeneous large-scale IoT networks. We devise a Graph Neural Network (GNN) approach that utilizes the social relationships formed between the devices in the IoT network to reduce the search space of any entity lookup and acquire a service from another device in the network. This proposed resource allocation approach surpasses standardization issues and embeds the structure and characteristics of the social IoT graph, by the means of GNNs, for eventual clustering analysis process. Simulation results applied on a real-world dataset illustrate the performance of this solution and its significant efficiency to operate on large-scale IoT networks.

cs.LG↗

arXiv2022

A Hybrid Artificial Neural Network for Task Offloading in Mobile Edge Computing

Edge Computing (EC) is about remodeling the way data is handled, processed, and delivered within a vast heterogeneous network. One of the fundamental concepts of EC is to push the data processing near the edge by exploiting front-end devices with powerful computation capabilities. Thus, limiting the use of centralized architecture, such as cloud computing, to only when it is necessary. This paper proposes a novel edge computer offloading technique that assigns computational tasks generated by devices to potential edge computers with enough computational resources. The proposed approach clusters the edge computers based on their hardware specifications. Afterwards, the tasks generated by devices will be fed to a hybrid Artificial Neural Network (ANN) model that predicts, based on these tasks, the profiles, i.e., features, of the edge computers with enough computational resources to execute them. The predicted edge computers are then assigned to the cluster they belong to so that each task is assigned to a cluster of edge computers. Finally, we choose for each task the edge computer that is expected to provide the fastest response time. The experiment results show that our proposed approach outperforms other state-of-the-art machine learning approaches using real-world IoT dataset.

cs.DC↗

arXiv2022

A Machine Learning Smartphone-based Sensing for Driver Behavior Classification

Driver behavior profiling is one of the main issues in the insurance industries and fleet management, thus being able to classify the driver behavior with low-cost mobile applications remains in the spotlight of autonomous driving. However, using mobile sensors may face the challenge of security, privacy, and trust issues. To overcome those challenges, we propose to collect data sensors using Carla Simulator available in smartphones (Accelerometer, Gyroscope, GPS) in order to classify the driver behavior using speed, acceleration, direction, the 3-axis rotation angles (Yaw, Pitch, Roll) taking into account the speed limit of the current road and weather conditions to better identify the risky behavior. Secondly, after fusing inter-axial data from multiple sensors into a single file, we explore different machine learning algorithms for time series classification to evaluate which algorithm results in the highest performance.

cs.LG↗

arXiv2021

Low Complexity Recruitment for Collaborative Mobile Crowdsourcing Using Graph Neural Networks

Collaborative Mobile crowdsourcing (CMCS) allows entities, e.g., local authorities or individuals, to hire a team of workers from the crowd of connected people, to execute complex tasks. In this paper, we investigate two different CMCS recruitment strategies allowing task requesters to form teams of socially connected and skilled workers: i) a platform-based strategy where the platform exploits its own knowledge about the workers to form a team and ii) a leader-based strategy where the platform designates a group leader that recruits its own suitable team given its own knowledge about its Social Network (SN) neighbors. We first formulate the recruitment as an Integer Linear Program (ILP) that optimally forms teams according to four fuzzy-logic-based criteria: level of expertise, social relationship strength, recruitment cost, and recruiter's confidence level. To cope with NP-hardness, we design a novel low-complexity CMCS recruitment approach relying on Graph Neural Networks (GNNs), specifically graph embedding and clustering techniques, to shrink the workers' search space and afterwards, exploiting a meta-heuristic genetic algorithm to select appropriate workers. Simulation results applied on a real-world dataset illustrate the performance of both proposed CMCS recruitment approaches. It is shown that our proposed low-complexity GNN-based recruitment algorithm achieves close performances to those of the baseline ILP with significant computational time saving and ability to operate on large-scale mobile crowdsourcing platforms. It is also shown that compared to the leader-based strategy, the platform-based strategy recruits a more skilled team but with lower SN relationships and higher cost.

cs.LG↗

arXiv2021

Topic Modeling and Progression of American Digital News Media During the Onset of the COVID-19 Pandemic

Currently, the world is in the midst of a severe global pandemic, which has affected all aspects of people's lives. As a result, there is a deluge of COVID-related digital media articles published in the United States, due to the disparate effects of the pandemic. This large volume of information is difficult to consume by the audience in a reasonable amount of time. In this paper, we develop a Natural Language Processing (NLP) pipeline that is capable of automatically distilling various digital articles into manageable pieces of information, while also modelling the progression topics discussed over time in order to aid readers in rapidly gaining holistic perspectives on pressing issues (i.e., the COVID-19 pandemic) from a diverse array of sources. We achieve these goals by first collecting a large corpus of COVID-related articles during the onset of the pandemic. After, we apply unsupervised and semi-supervised learning procedures to summarize articles, then cluster them based on their similarities using the community detection methods. Next, we identify the topic of each cluster of articles using the BART algorithm. Finally, we provide a detailed digital media analysis based on the NLP-pipeline outputs and show how the conversation surrounding COVID-19 evolved over time.

cs.CL↗

arXiv2021

Towards Collaborative Mobile Crowdsourcing

Mobile Crowdsourcing (MC) is an effective way of engaging large groups of smart devices to perform tasks remotely while exploiting their built-in features. It has drawn great attention in the areas of smart cities and urban computing communities to provide decentralized, fast, and flexible ubiquitous technological services. The vast majority of previous studies focused on non-cooperative MC schemes in Internet of Things (IoT) systems. Advanced collaboration strategies are expected to leverage the capability of MC services and enable the execution of more complicated crowdsourcing tasks. In this context, Collaborative Mobile Crowdsourcing (CMC) enables task requesters to hire groups of IoT devices' users that must communicate with each other and coordinate their operational activities in order to accomplish complex tasks. In this paper, we present and discuss the novel CMC paradigm in IoT. Then, we provide a detailed taxonomy to classify the different components forming CMC systems. Afterwards, we investigate the challenges in designing CMC tasks and discuss different team formation strategies involving the crowdsourcing platform and selected team leaders. We also analyze and compare the performances of certain proposed CMC recruitment algorithms. Finally, we shed the light on open research directions to leverage CMC service design.

cs.SI↗

arXiv2021

A Social IoT-driven Pedestrian Routing Approach during Epidemic Time

The unprecedented worldwide spread of coronavirus disease has significantly sped up the development of technology-based solutions to prevent, combat, monitor, or predict pandemics and/or its evolution. The omnipresence of smart Internet-of-things (IoT) devices can play a predominant role in designing advanced techniques helping in minimizing the risk of contamination. In this paper, we propose a practical framework that uses the Social IoT (SIoT) concept to improve pedestrians safely navigate through a real-wold map of a smart city. The objective is to mitigate the risks of exposure to the virus in high-dense areas where social distancing might not be well-practiced. The proposed routing approach recommends pedestrians' route in a real-time manner while considering other devices' mobility. First, the IoT devices are clustered into communities according to two SIoT relations that consider the devices' locations and the friendship levels among their owners. Accordingly, the city map roads are assigned weights representing their safety levels. Afterward, a navigation algorithm, namely the Dijkstra algorithm, is applied to recommend the safest route to follow. Simulation results applied on a real-world IoT data set have shown the ability of the proposed approach in achieving trade-offs between both safest and shortest paths according to the pedestrian preference.

cs.SI↗

arXiv2020

Elevated LiDAR Placement under Energy and Throughput Capacity Constraints

Elevated LiDAR (ELiD) has the potential to hasten the deployment of Autonomous Vehicles (AV), as ELiD can reduce energy expenditures associated with AVs, and can also be utilized for other intelligent Transportation Systems applications such as urban 3D mapping. In this paper, we address the need for a planning framework in order for ITS operators to have an effective tool for determining what resources are required to achieve a desired level of coverage of urban roadways. To this end, we develop a mixed-integer nonlinear constrained optimization problem, with the aim of maximizing effective area coverage of a roadway, while satisfying energy and throughput capacity constraints. Due to the non-linearity of the problem, we utilize Particle Swarm Optimization (PSO) to solve the problem. After demonstrating its effectiveness in finding a solution for a realistic scenario, we perform a sensitivity analysis to test the model's general ability.

eess.SP↗

arXiv2020

A Generative Graph Method to Solve the Travelling Salesman Problem

The Travelling Salesman Problem (TSP) is a challenging graph task in combinatorial optimization that requires reasoning about both local node neighborhoods and global graph structure. In this paper, we propose to use the novel Graph Learning Network (GLN), a generative approach, to approximately solve the TSP. GLN model learns directly the pattern of TSP instances as training dataset, encodes the graph properties, and merge the different node embeddings to output node-to-node an optimal tour directly or via graph search technique that validates the final tour. The preliminary results of the proposed novel approach proves its applicability to this challenging problem providing a low optimally gap with significant computation saving compared to the optimal solution.

cs.AI↗

arXiv2020

Graph Neural Networks-based Clustering for Social Internet of Things

In this paper, we propose a machine learning process for clustering large-scale social Internet-of-things (SIoT) devices into several groups of related devices sharing strong relations. To this end, we generate undirected weighted graphs based on the historical dataset of IoT devices and their social relations. Using the adjacency matrices of these graphs and the IoT devices' features, we embed the graphs' nodes using a Graph Neural Network (GNN) to obtain numerical vector representations of the IoT devices. The vector representation does not only reflect the characteristics of the device but also its relations with its peers. The obtained node embeddings are then fed to a conventional unsupervised learning algorithm to determine the clusters accordingly. We showcase the obtained IoT groups using two well-known clustering algorithms, specifically the K-means and the density-based algorithm for discovering clusters (DBSCAN). Finally, we compare the performances of the proposed GNN-based clustering approach in terms of coverage and modularity to those of the deterministic Louvain community detection algorithm applied solely on the graphs created from the different relations. It is shown that the framework achieves promising preliminary results in clustering large-scale IoT systems.

cs.SI↗

arXiv2020

Computational Resource Allocation for Edge Computing in Social Internet-of-Things

The heterogeneity of the Internet-of-things (IoT) network can be exploited as a dynamic computational resource environment for many devices lacking computational capabilities. A smart mechanism for allocating edge and mobile computers to match the need of devices requesting external computational resources is developed. In this paper, we employ the concept of Social IoT and machine learning to downgrade the complexity of allocating appropriate edge computers. We propose a framework that detects different communities of devices in SIoT enclosing trustworthy peers having strong social relations. Afterwards, we train a machine learning algorithm, considering multiple computational and non-computational features of the requester as well as the edge computers, to predict the total time needed to process the required task by the potential candidates belonging to the same community of the requester. By applying it to a real-world data set, we observe that the proposed framework provides encouraging results for mobile computer allocation.

cs.SI↗

arXiv2020

A Photo-Based Mobile Crowdsourcing Framework for Event Reporting

Mobile Crowdsourcing (MCS) photo-based is an arising field of interest and a trending topic in the domain of ubiquitous computing. It has recently drawn substantial attention of the smart cities and urban computing communities. In fact, the built-in cameras of mobile devices are becoming the most common way for visual logging techniques in our daily lives. MCS photo-based frameworks collect photos in a distributed way in which a large number of contributors upload photos whenever and wherever it is suitable. This inevitably leads to evolving picture streams which possibly contain misleading and redundant information that affects the task result. In order to overcome these issues, we develop, in this paper, a solution for selecting highly relevant data from an evolving picture stream and ensuring correct submission. The proposed photo-based MCS framework for event reporting incorporates (i) a deep learning model to eliminate false submissions and ensure photos credibility and (ii) an A-Tree shape data structure model for clustering streaming pictures to reduce information redundancy and provide maximum event coverage. Simulation results indicate that the implemented framework can effectively reduce false submissions and select a subset with high utility coverage with low redundancy ratio from the streaming data.

cs.CY↗

arXiv2020

Optimal Team Recruitment Strategies for Collaborative Mobile Crowdsourcing Systems

The wide spread of mobile devices has enabled a new paradigm of innovation called Mobile Crowdsourcing (MCS) where the concept is to allow entities, e.g., individuals or local authorities, to hire workers to help from the crowd of connected people, to execute a task or service. Some complex tasks require the collaboration of multiple workers to ensure its successful completion. In this context, the task requester needs to hire a group of socially connected and collaborative workers that, at the same time, have sufficient skills to accomplish the task. In this paper, we develop two recruitment strategies for collaborative MCS frameworks in which, virtual teams are formed according to four different criteria: level of expertise, social relationship strength, recruitment cost, and recruiter's confidence level. The first proposed strategy is a platform-based approach which exploits the platform knowledge to form the team. The second one is a leader-based approach that uses team members' knowledge about their social network (SN) neighbors to designate a group leader that recruits its suitable team. Both approaches are modeled as integer linear programs resulting in optimal team formation. Experimental results show a performance trade-off between the two virtual team grouping strategies when varying the members SN edge degree. Compared to the leader-based strategy, the platform-based strategy recruits a more skilled team but with lower SN relationships and higher cost.

cs.SI↗

arXiv2020

A Stochastic Team Formation Approach for Collaborative Mobile Crowdsourcing

Mobile Crowdsourcing (MCS) is the generalized act of outsourcing sensing tasks, traditionally performed by employees or contractors, to a large group of smart-phone users by means of an open call. With the increasing complexity of the crowdsourcing applications, requesters find it essential to harness the power of collaboration among the workers by forming teams of skilled workers satisfying their complex tasks' requirements. This type of MCS is called Collaborative MCS (CMCS). Previous CMCS approaches have mainly focused only on the aspect of team skills maximization. Other team formation studies on social networks (SNs) have only focused on social relationship maximization. In this paper, we present a hybrid approach where requesters are able to hire a team that, not only has the required expertise, but also is socially connected and can accomplish tasks collaboratively. Because team formation in CMCS is proven to be NP-hard, we develop a stochastic algorithm that exploit workers knowledge about their SN neighbors and asks a designated leader to recruit a suitable team. The proposed algorithm is inspired from the optimal stopping strategies and uses the odds-algorithm to compute its output. Experimental results show that, compared to the benchmark exponential optimal solution, the proposed approach reduces computation time and produces reasonable performance results.

cs.CY↗

arXiv2020

Word Embedding-based Text Processing for Comprehensive Summarization and Distinct Information Extraction

In this paper, we propose two automated text processing frameworks specifically designed to analyze online reviews. The objective of the first framework is to summarize the reviews dataset by extracting essential sentence. This is performed by converting sentences into numerical vectors and clustering them using a community detection algorithm based on their similarity levels. Afterwards, a correlation score is measured for each sentence to determine its importance level in each cluster and assign it as a tag for that community. The second framework is based on a question-answering neural network model trained to extract answers to multiple different questions. The collected answers are effectively clustered to find multiple distinct answers to a single question that might be asked by a customer. The proposed frameworks are shown to be more comprehensive than existing reviews processing solutions.

cs.CL↗

arXiv2020

Leveraging Personal Navigation Assistant Systems Using Automated Social Media Traffic Reporting

Modern urbanization is demanding smarter technologies to improve a variety of applications in intelligent transportation systems to relieve the increasing amount of vehicular traffic congestion and incidents. Existing incident detection techniques are limited to the use of sensors in the transportation network and hang on human-inputs. Despite of its data abundance, social media is not well-exploited in such context. In this paper, we develop an automated traffic alert system based on Natural Language Processing (NLP) that filters this flood of information and extract important traffic-related bullets. To this end, we employ the fine-tuning Bidirectional Encoder Representations from Transformers (BERT) language embedding model to filter the related traffic information from social media. Then, we apply a question-answering model to extract necessary information characterizing the report event such as its exact location, occurrence time, and nature of the events. We demonstrate the adopted NLP approaches outperform other existing approach and, after effectively training them, we focus on real-world situation and show how the developed approach can, in real-time, extract traffic-related information and automatically convert them into alerts for navigation assistance applications such as navigation apps.

cs.CL↗