Showing papers by "S. M. K. Quadri published in 2022"

CAMM: Cross-Attention Multimodal Classification of Disaster-Related Tweets

Abstract: During the past decade, social media platforms have been extensively used for information dissemination by the affected community and humanitarian agencies during a disaster. Although many studies have been done recently to classify the informative and non-informative messages from social media posts, most are unimodal, i.e., have independently used textual or visual data to build deep learning models. In the present study, we integrate the complementary information provided by the text and image messages about the same event posted by the affected community on the social media platform Twitter and build a multimodal deep learning model based on the concept of the attention mechanism. The attention mechanism is a recent breakthrough that has revolutionized the field of deep learning. Just as humans pay more attention to a specific part of the text or image, ignoring the rest, neural networks can also be trained to concentrate on more relevant features through the attention mechanism. We propose a novel Cross-Attention Multi-Modal (CAMM) deep neural network for classifying multimodal disaster data, which uses the attention mask of the textual modality to highlight the features of the visual modality. We compare CAMM with unimodal models and the most popular bilinear multimodal models, MUTAN and BLOCK, generally used for visual question answering. CAMM achieves an average F1-score of 84.08%, better than the MUTAN and BLOCK methods by 6.31% and 5.91%, respectively. The proposed cross-attention-based multimodal deep learning method outperforms the current state-of-the-art fusion methods on the benchmark multimodal disaster dataset by highlighting more relevant cross-domain features of text and image tweets.

Multi-source domain adaptation of social media data for disaster management

Abstract: Labeled data scarcity at the time of an ongoing disaster has encouraged the researchers to use the labeled data from some previous disaster for training and transferring the knowledge to the current disaster task using Domain Adaptation (DA). However, often labeled data from more than one previous disaster may be available. As all deep learning models are data-hungry and perform better if fed with more annotated data, it is advisable to use data from multiple sources for training a Deep Convolutional Neural Network (DCNN). One of the easiest ways is to simply combine the data from multiple sources and use it for training. However, this arrangement is not that straightforward. The models trained on the combined data from various sources do not perform well on the target, mainly due to distribution discrepancies between multiple sources. This has motivated us to explore the challenging area of multi-source domain adaptation for disaster management. The aim is to learn the domain invariant features and representations across the domains and transfer more related knowledge to solve the target task with improved accuracy than single-source or combined-source domain adaptation. This study proposes a Multi-Source Domain Adaptation framework for Disaster Management (MSDA-DM) to classify disaster images posted on social media based on unsupervised DA with adversarial training. The empirical results obtained confirm that the proposed model MSDA-DM performs better than single-source DA by up to 10.83% and combined-source DA by up to 5.06% in terms of F1-score for different sets of source and target disaster domains. We also compare our model with current state-of-the-art models. The main challenge of multi-source DA is the choice of the relevant sources taken for training since, unlike single-source DA that handles only source-target distribution drift, the multi-source DA network has to address both source-target and source-source distribution drifts.

Feature-driven label generation for congestion detection in smart cities under big data

Abstract: Due to rapid urbanization and the emergence of smart cities, the problem of traffic congestion has materialized into a major issue for smart city planners. Therefore, traffic congestion prediction is needed to effectively reduce traffic congestion and enhance the road capacity. There have been various studies which have tried to solve the problem of traffic congestion. However, it is difficult to properly judge the effectiveness of such studies given the absence of properly labeled datasets. Additionally, current studies use datasets with relatively lesser number of data instances, which does not correctly reflect the big data nature of the traffic data. Motivated by these problems and challenges, in this paper, we aim to study the problem of traffic congestion with respect to effective label-generation under big data perspective. Essentially, we provide two sound and intuitive techniques for label generation which help in the correct annotation of unlabeled data. One of the techniques is based on the number of vehicles plying on the road and the other is based on the amalgamation of average speed and number of vehicles. For this purpose, we consider a publicly available CityPulse traffic dataset with 13.5 million data instances. Using our techniques, we generate “congested” and “not-congested” labels depicting whether there is congestion on the road or not. To tackle the class imbalance problem, besides using random undersampling and oversampling techniques, we also introduce a mixture of the two techniques to negate any bias inherent to two individual sampling techniques. To test the effectiveness of our label generation approaches, we make the extensive use of various machine learning techniques and for performance evaluation we use all the standard classification evaluation metrics. Finally, we compare our techniques with a previous work which only considered average speed for label generation. Our results demonstrate the effectiveness of the proposed approaches against the comparing method. For example, in random undersampling the F1-score of every classifier under the proposed techniques is close to 1, whereas that under the comparing method, F1-score is as low as 0.70 in multinomial naïve Bayes (MNB) classifier and 0.88 in support vector machine (SVM). Similarly, in oversampling, our approaches have a close F1score of 1 across all the classifiers, whereas the comparing method gets as low as 0.70 in MNB. The same trend can be seen in the mixture of both the sampling techniques.

Uses of Data Fusion Technology for Establishing Scalable Data Solutions in the Marketing Sector

Abstract: Data fusion involves code-free and fully managed data-integration service, which assists users in marketing sector to manage and build ELT/ETL information pipelines. Data-fusion is all about integration of different data-sources for production of accurate, useful and consistent information, which is more efficient as compared to data provided by individual information sources. Data-fusion on web user interface allows organisations in marketing sectors to establish a system of scalable information integration for preparing, transferring, preparing, blending without the need for managing infrastructure. This will remove the need for managing a robust information infrastructure within organisations while proper integration of the data-sources. It enables users to use graphical interface, which is inferable easily and allows marketers to use faster data transfer system. Aim of this study is to analyse the impact of using data-fusion technologies to establish scalable data-solutions in marketing sector. In literature-review chapter of this study, concepts regarding technological advancements, data-fusion sensors and their impact on easy transfer and management of information have been analysed. Further, in methodology chapter of present study, the data-collection method, research design and data-analysis method have been analysed in an effective manner. This study has considered implementation of mixed data-collection for collecting information from various secondary and primary sources. Interview has been conducted for collection of primary information in this study and in the analysis and results chapter of this study; positive relations between use of data-fusion and establishment of scalable data-solutions have been found.

Power and Performance Issues and Management Approaches in Cloud Computing

Abstract: Cloud computing is a relatively new developing technology that allows users to pay for services on a pay-as-you-go basis. It provides internet-based information and communication technology services, while virtualization enables it to deliver computer resources. Datacenters are the backbone of this technology, consisting of networked computers, cables, power supply units, and other components that host and store corporate data. In cloud datacenters, high performance has always been the most important consideration, but it comes at the expense of power consumption. The key problem is finding a balance between the system's performance and power consumption by lowering power usage without compromising the quality and performance of services. As a result, several attempts are now being done to reduce datacenter energy usage. All concerns relating to energy efficiency are explored and researched in this work. This paper also presents an overview of various power and performance management strategies in cloud computing.