Research built to ship into the industries we serve.

Abstract

As our active and passive digital footprints continuously aggregate into Big Data (bData); correspondingly, the field of Artificial Intelligence (AI) has continually provided methodologies and tools for exploiting this Big Data. Taking into consideration the prevalence of Big Data, Sentiment Mining (SM) and Opinion Mining (OM) or Aspect-based Sentiment Analysis (ABSA) have increasingly become interesting and relevant topics — within the subfield of Social Network Analysis (SNA) — with respect to the field of Artificial Intelligence. Thus, “fine-grained” Sentiment Mining or Opinion Mining essentially focuses on determining deeper intensities of users’ emotions or viewpoints with respect to a given topic. Our work herein aims at examining and exploiting Big Data collections, with the goal of extracting fine-grained sentiment(s) on a given topic, using state-of-the-art representation-based transformer architectures. Several existing literature have exploited Structured Data for Sentiment Mining using Recurrent Neural Network (RNN) and Recursive Neural Network (RvNN) architectures. However, and majorly due to computational constraints, only a few existing literature have exploited Big Data for Sentiment Mining using transformer-based architectures. To this end, our research herein contributes to the latter existing literature and fills the literature-gap via employing a dedicated, high-end, enterprise-grade data center Graphics Processing Unit (GPU) in a bid to overcome common computational constraints associated with harnessing Big Data and post-training transformer architectures. Our proposed framework leverages the fundamental architecture of encoder-only transformers, irrespective of noisy data, with respect to a pre-trained Modern Bidirectional Encoder Representations from Transformers (ModernBERT) architecture. In this regard, the results of our experiments aggregated herein have been very auspicious with respect to the objective functions employed in our research.

Abstract

This paper proposes a Machine Learning-based approach for detecting Denial-of-Service (DoS) attacks using different datasets for training and testing. The study evaluates the performance of the proposed approach on a unique dataset; thereafter, compares it to existing approaches in a bid to demonstrate its superiority in terms of accuracy, false-positive rate, and computational efficiency. Furthermore, the impacts of different Machine Learning algorithms and hypertuning configurations on the performance of the proposed approach are investigated. Also, via Feature Importance Analysis, this study examines the influence of each feature (present in the dataset) on our proposed model. The contributions of our work herein demonstrate the potentials of the proposed approach in detecting DoS attacks; and our research highlights the importance of employing Machine Learning in this domain. Future research directions have been suggested based on insights acquired from the investigations of different algorithms and hyperparameters.

Abstract

The Internet of Things (IoT) is a very crucial aspect of Computing, and it fosters the interconnection of physical nodes on the Internet via enabling them to interact and share data. However, the potentials for security and privacy breaches increase as the number of connected devices/nodes (in the network) rises. Blockchain technology, with its capacity to provide secure and tamper-proof data storage, possess the potentials to mitigate the aforementioned vulnerabilities in the IoT. Hence, this paper gives a detailed review of the present state of blockchain-based applications in the IoT as well as the prospective benefits of employing blockchain technology with the aim/goal of securing IoT devices and its infrastructure. Also mentioned in this paper are the obstacles, research gaps, etc., currently impeding the implementation of some blockchain-based technologies; and the potential solutions toward surmounting these challenges.

Abstract

Image classification, a topic of pattern recognition in computer vision, is an approach of classification based on contextual information in images. Contextual here means this approach is focusing on the relationship of the nearby pixels, also called neighborhood. An open topic of research in computer vision is to devise an effective means of transferring human’s informal knowledge into computers, such that computers can also perceive their environment. However, the occurrence of object with respect to image representation is usually associated with various features of variation causing noise in the image representation. Hence, it tends to be very difficult to actually disentangle these abstract factors of influence from the principal object. In this paper, we have proposed a hybrid model: FUSIONET, which has been modeled for studying and extracting meaning facts from images. Our proposition combines two distinct stacks of convolution operation (3×3 and 1×1, respectively). Successively, these relatively low-feature maps from the above operation are fed as input to a downstream classifier for classification of the image in question.