Computer Engineering Commons^™

Effective Short Text Classification Via The Fusion Of Hybrid Features For Iot Social Data, Xiong Luo, Zhijian Yu, Zhigang Zhao, Wenbing Zhao, Jenq-Haur Wang

Electrical and Computer Engineering Faculty Publications

Nowadays short texts can be widely found in various social data in relation to the 5G-enabled Internet of Things (IoT). Short text classification is a challenging task due to its sparsity and the lack of context. Previous studies mainly tackle these problems by enhancing the semantic information or the statistical information individually. However, the improvement achieved by a single type of information is limited, while fusing various information may help to improve the classification accuracy more effectively. To fuse various information for short text classification, this article proposes a feature fusion method that integrates the statistical feature and the comprehensive …

Generating Reality-Analogous Datasets For Autonomous Uav Navigation Using Digital Twin Areas, Thomas Lee, Susan Mckeever, Jane Courtney

Conference papers

In order for autonomously navigating Unmanned Air Vehicles(UAVs) to be implemented in day-to-day life, proof of safe operation will be necessary for all realistic navigation scenarios. For Deep Learning powered navigation protocols, this requirement is challenging to fulfil as the performance of a network is impacted by how much the test case deviates from data that the network was trained on. Though networks can generalise to manage multiple scenarios in the same task, they require additional data representing those cases which can be costly to gather. In this work, a solution to this data acquisition problem is suggested by way …

Estimating Animal Pose Using Deep Learning A Trained Deep Learning Model Outperforms Morphological Analysis, Sanghoon Lee, Jarod Banzon, Kevin Le, Dal Hyung Kim

Computer Sciences and Electrical Engineering Faculty Research

INTRODUCTION: Analyzing animal behavior helps researchers understand their decision-making process and helper tools are rapidly becoming an indispensable part of many interdisciplinary studies. However, researchers are often challenged to estimate animal pose because of the limitation of the tools and its vulnerability to a specific environment. Over the years, deep learning has been introduced as an alternative solution to overcome these challenges.

OBJECTIVES: This study investigates how deep learning models can be applied for the accurate prediction of animal behavior, comparing with traditional morphological analysis based on image pixels.

METHODS: Transparent Omnidirectional Locomotion Compensator (TOLC), a tracking device, is used …

A Deep Learning-Based Approach To Extraction Of Filler Morphology In Sem Images With The Application Of Automated Quality Inspection, Md. Fashiar Rahman, Tzu-Liang Bill Tseng, Jianguo Wu, Yuxin Wen, Yirong Lin

Engineering Faculty Articles and Research

Automatic extraction of filler morphology (size, orientation, and spatial distribution) in Scanning Electron Microscopic (SEM) images is essential in many applications such as automatic quality inspection in composite manufacturing. Extraction of filler morphology greatly depends on accurate segmentation of fillers (fibers and particles), which is a challenging task due to the overlap of fibers and particles and their obscure presence in SEM images. Convolution Neural Networks (CNNs) have been shown to be very effective at object recognition in digital images. This paper proposes an automatic filler detection system in SEM images, utilizing a Mask Region-based CNN architecture. The proposed system …

Ensemble Approach To The Semantic Segmentation Of Satellite Images, Brendan Kent

Dissertations

Automatic classification and segmentation of land use land cover(LULC) is extremely important for understanding the relationship between humans and nature. Human pressures on the environment have drastically accelerated in the last decades, risking biodiversity and ecosystem services. Remote sensing via satellite imagery is an excellent tool to study LULC. Research has shown that deep learning encoder-decoder architectures have achieved worthy results in the area of LULC, however the application of an ensemble approach has not been well quantified. Studies have shown it to be useful in the area of medical imaging. Ensembling by pooling together predictions to produce better predictions …

Evaluating The Performance Of Vision Transformer Architecture For Deepfake Image Classification, Devesan Govindasamy

Dissertations

Deepfake classification has seen some impressive results lately, with the experimentation of various deep learning methodologies, researchers were able to design some state-of-the art techniques. This study attempts to use an existing technology “Transformers” in the field of Natural Language Processing (NLP) which has been a de-facto standard in text processing for the purposes of Computer Vision. Transformers use a mechanism called “self-attention”, which is different from CNN and LSTM. This study uses a novel technique that considers images as 16x16 words (Dosovitskiy et al., 2021) to train a deep neural network with “self-attention” blocks to detect deepfakes. It creates …

Evaluation Of Automated Eye Blink Artefact Removal Using Stacked Dense Autoencoder, Matthew Rigney

Dissertations

The presence of artefacts in Electroencephalograph (EEG) signals can have a considerable impact on the information they portray. In this comparative study, the automated removal of eye blink artefacts using the constrained latent representation of a stacked dense autoencoders (SDAE) and comparing its ability to that of the manual independent component analysis (ICA) approach was evaluated. A comparative evaluation of 5 stacked dense autoencoder architectures lead to a chosen architecture for which the ability to automatically detect and remove eye blink artefacts were both statistically and humanistically evaluated. The ability of the stacked dense autoencoder was statistically evaluated with the …

Bfv-Based Homomorphic Encryption For Privacy-Preserving Cnn Models, Febrianti Wibawa, Ferhat Ozgur Catak, Salih Sarp, Murat Kuzlu

Engineering Technology Faculty Publications

Medical data is frequently quite sensitive in terms of data privacy and security. Federated learning has been used to increase the privacy and security of medical data, which is a sort of machine learning technique. The training data is disseminated across numerous machines in federated learning, and the learning process is collaborative. There are numerous privacy attacks on deep learning (DL) models that attackers can use to obtain sensitive information. As a result, the DL model should be safeguarded from adversarial attacks, particularly in medical data applications. Homomorphic encryption-based model security from the adversarial collaborator is one of the answers …

Modeling Cognitive Load As A Self-Supervised Brain Rate With Electroencephalography And Deep Learning, Luca Longo

Articles

The principal reason for measuring mental workload is to quantify the cognitive cost of performing tasks to predict human performance. Unfortunately, a method for assessing mental workload that has general applicability does not exist yet. This is due to the abundance of intuitions and several operational definitions from various fields that disagree about the sources or workload, its attributes, the mechanisms to aggregate these into a general model and their impact on human performance. This research built upon these issues and presents a novel method for mental workload modelling from EEG data employing deep learning. This method is self-supervised, employing …