Abstract

short-paper

Transfer Learning Based Architecture for Urban Transportation Big Data Fusion

Authors: Salah Ghodhbani, Sabeur Elkosantini, Wonho Suh, Mark LeeAuthors Info & Claims

MEDES ’22: Proceedings of the 14th International Conference on Management of Digital EcoSystems

Pages 80 – 83

https://doi.org/10.1145/3508397.3564844

Published: 08 December 2022 Publication History

0citation68Downloads

Get Access

Abstract

Recently, intelligent transportation system (ITS) is considered as one of the most important issues in smart city applications. Its supports urban and regional development and promotes economic growth, social development, and enhances human well-being. ITS integrates new technologies of information and communication including sensors, social media IoT devices which can generate a massive amount of heterogeneous and multimodal data known as big data term. In this context, Data Fusion techniques (DF) seem promising and have emerged from transportation applications and hold a promising opportunities to deal with imperfect raw data for capturing reliable, valuable and accurate information. Literature. In literature many DF techniques based on machine learning remarkably renovates fusion techniques by offering the strong ability of computing and predicting. In this paper, we propose new Hybrid method based on TL (transfer learning) combine tow pertained DL models such as irregular CNN [1], and bi-directional LSTM [2] models to fuse multimodal and spatial temporal data. the propose method use CBOA algorithm for feature selection in to order to provide effective exploration of significant features with faster convergence. The proposed model demonstrated its effective results on the applied dataset by offering good results and outcome over traditional methods.

Abstract

Graph clustering is one of the key techniques to understand structures that are presented in networks. In addition to clusters, bridges and outliers detection is also a critical task as it plays an important role in the analysis of networks. Recently, several graph clustering methods are developed and used in multiple application domains such as biological network analysis, recommendation systems and community detection. Most of these algorithms are based on the structural clustering algorithm. Yet, this kind of algorithm is based on the structural similarity. This latter requires to parse all graph’ edges in order to compute the structural similarity. However, the height needs of similarity computing make this algorithm more adequate for small graphs, without significant support to deal with large-scale networks. In this paper, we propose a novel distributed graph clustering algorithm based on structural graph clustering. The experimental results show the efficiency in terms of running time of the proposed algorithm in large networks compared to existing structural graph clustering methods.

Abstract

Due to the sharp increase in global industrial production, as well as the over-exploitation of land and sea resources, the quality of drinking water has deteriorated considerably. Furthermore, nowadays, many water supply systems serving growing human populations suffer from shortages since many rivers, lakes, and aquifers are drying up because of global climate change. To cope with these serious threats, smart water management systems are in great demand to ensure vigorous control of the quality and quantity of drinking water. Indeed, water monitoring is essential today since it allows to ensure the real-time control of water quality indicators and the appropriate management of resources in cities to provide an adequate water supply to citizens. In this context, a novel IoT-based framework is proposed to support smart water monitoring and management. The proposed framework, named SmartWater, combines cutting-edge technologies in the field of sensor clouds, deep learning, knowledge reasoning, and data processing and analytics. First, knowledge graphs are exploited to model the water network in a semantic and multi-relational manner. Then, incremental network embedding is performed to learn rich representations of water entities, in particular the affected water zones. Finally, a decision mechanism is defined to generate a water management plan depending on the water zones’ current states. A real-world dataset has been used in this study to experimentally validate the major features of the proposed smart water monitoring framework.

Abstract

With the increasing adoption of cloud computing, the deployment and management of business processes over cloud environments have become an essential operation for most enterprises, leading to the emergence of BPaaS (Business Process as a Service) as a new cloud service model. This SaaS-like service, like its ancestors, should be strategically distributed and managed over multiple cloud zones, while taking into account several constraints and conditions (e.g., sensitivity of BPaaS fragments, insecure and untrusted cloud zones, lack of resources, and workload changes). However, current BPaaS approaches are static, which means that they are no longer suitable to manage such enterprise-oriented cloud service model and to deal with the uncertain and dynamic nature of cloud availability zones. To fill this gap, we adopt a predictive BPaaS management strategy by proposing a model that forecasts the next-short time overload of cloud zones. These latter, as hosting environments for the managed BPaaS, are categorized as overloaded or underloaded, which triggers the migration of BPaaS fragments to high-performance cloud zones. The proposed neural network prediction model (called QGA-NN) is enhanced with a quantum genetic algorithm to optimize the prediction of cloud zones’ overload. QGA-NN is evaluated using a BPaaS placement algorithm, which we defined as a triggered management operation. Experimental results have proved the accuracy and effectiveness of our predictive approach, compared with state-of-the-art solutions.

Abstract

Over the last decade, service selection and recommendation had been two strongly related service filtering steps. While service selection aims to filter the best available services according to QoS and contextual criteria, service recommendation refines the selection results by taking into account additional criteria, such as users feedbacks and ratings, similarities between users tastes, etc. However, the ever changing services environment, users tastes, as well as the perception and popularity of available services, rise a question regarding the appropriate means to capture and analyze such changes over time. Most service recommendation solutions are static and do not offer a multi-relational modeling of user-service interactions over time. Time is a contextual dimension that has, recently, received a lot of attention, leading to a new class of recommender systems, called time-aware recommender systems. In this work, we propose a service recommendation method that takes advantage of temporal knowledge graphs. As a de facto standard to model multiple and complex interactions between heterogeneous entities, knowledge graphs will serve as a historical knowledge base for our TASR system. We, first, model the user-service interactions over time, by constructing a temporal service knowledge graph (TSKG) that will be later enriched through a completion step. Second, to explore the TSKG and extract top-rated services, we use Convolutional Neural Networks (CNN) to embed the TSKG into a low-dimensional vector space, facilitating then its mining. Experimental studies have proven the effectiveness and accuracy of our approach, compared to traditional TASR methods and time-unaware KG-based recommendation.

Abstract

Abstract

Inference systems are intelligent software performed generally to help people take appropriate decisions and solve problems in specific domains. Fuzzy inference systems are a kind of these systems that are based on fuzzy knowledge. To handle the fuzziness in the inference, the compositional rule of inference is used, which has two parameters: a t-norm and an implication operator. However, most of the combinations of t-norm/implication do not give an adequate inference result that coincides with human intuitions. This was the motivation for several works to study these combinations and to identify those that are compatible, in order to guarantee a performance close to that of humans. We are interested in this paper to a more general form of rules, which is complex rules, whose premise is a conjunction of propositions. To obtain the consequence in a fuzzy inference system using the compositional rule of inference with a complex rule, we study, in this work, Lukasiewicz t-norm which was not investigated before in this context. We combine it with known implications, and we verify the satisfaction of some criteria that model human intuitions.

Abstract

In recent years, Home Health Care (HHC) has gained popularity in different countries around the world (e.g. France, US, Germany, etc.). The HHC consists in providing medical services to patients at home. During the HHC service, caregivers’ planning may be disrupted by some unexpected events (e.g. urgent request, caregiver absence, traffic congestion, etc.), which makes HHC activities infeasible. This paper addresses the daily HHC routing and scheduling problem by considering unpredicted events. To solve this problem, we propose a Case-Based Reasoning (CBR) methodology. Our purpose is to create the HHC case base which contains the knowledge about the perturbation.

Abstract

Bag-of-Tasks is a well-known model that processes big-data applications supporting embarrassingly parallel jobs with independent tasks. Scheduling Bag-of-Tasks in a dynamic multi-cloud environment is an NP-hard problem that has attracted a lot of attention in the last years. Such a problem can be modeled using a bi-level optimization framework due to its hierarchical scheme. Motivated by this issue, in this paper, an efficient bi-level multi-follower algorithm, based on hybrid metaheuristics, is proposed to solve the multi-objective budget-constrained dynamic Bag-of-Tasks scheduling problem in a heterogeneous multi-cloud environment. In our proposed model, the objective function differs depending on the scheduling level: The upper level aims to minimize the makespan of the whole Bag-of-Tasks under budget constraints; while each follower aims to minimize the makespan and the execution cost of tasks belonging to the Bag-of-Tasks. Since multiple conflicting objectives exist in the lower level, we propose an improved variant of the Non-dominated Sorting Genetic Algorithm II (NSGA-II) called Efficient NSGA-II (E-NSGA-II), applying a recently proposed quick non-dominated sorting algorithm (QNDSA) with quasi-linear average time complexity. By performing experiments on proposed synthetic datasets, our algorithm demonstrates high performance in terms of makespan and execution cost while respecting budget constraints. Statistical analysis validates the outperformance of our proposal regarding the considering metrics.