UNT College of Engineering - 339 Matching Results
Search Results
- Accuracy-Constrained Efficiency Optimization and GPU Profiling of CNN Inference for Detecting Drainage Crossing Locations
- Article describes how the accurate and efficient determination of hydrologic connectivity has garnered significant attention from both academic and industrial sectors due to its critical implications for environment management. To address these challenges, the focus of the author's study is on detecting drainage crossings through the application of advanced convolutional neural networks.
- Pareto Optimization of CNN Models via Hardware-Aware Neural Architecture Search for Drainage Crossing Classification on Resource-Limited Devices
- Article describes how embedded devices, constrained by limited memory and processors, require deep learning models to be tailored to their specifications. This research explores customized model architectures for classifying drainage crossing images.
- Securing Industrial Control Systems: Components, Cyber Threats, and Machine Learning-Driven Defense Strategies
- Article describes how Industrial Control Systems (ICS), which include Supervisory Control and Data Acquisition (SCADA) systems, Distributed Control Systems (DCS), and Programmable Logic Controllers (PLC), play a crucial role in managing and regulating industrial processes. This article presents an overview of ICS security, covering its components, protocols, industrial applications, and performance aspects.
- FZ-GPU: A Fast and High-Ratio Lossy Compressor for Scientific Computing Applications on GPUs
- Article describes how today's large-scale scientific applications running on high-performance computing (HPC) systems generate vast data volumes. Thus, data compression is becoming a critical technique to mitigate the storage burden and data-movement cost. In this paper, the authors develop a fast and high- ratio error-bounded lossy compressor on GPUs for scientific data (called FZ-GPU).
- PPAD: a deep learning architecture to predict progression of Alzheimer’s disease
- Article asserts that Alzheimer’s disease (AD) is a neurodegenerative disease that affects millions of people worldwide. The authors of the article propose two deep learning architectures based on RNN, namely Predicting Progression of Alzheimer’s Disease (PPAD) and PPAD-Autoencoder.
- SUPREME: multiomics data integration using graph convolutional networks
- Article states that, to pave the road towards precision medicine in cancer, patients with similar biology ought to be grouped into same cancer subtypes. On breast cancer subtyping, unlike existing tools, SUPREME generates patient embeddings from multiple similarity networks utilizing multiomics features and integrates them with raw features to capture complementary signals.
- NextGen-Malloc: Giving Memory Allocator Its Own Room in the House
- Article describes how memory allocation and management have a significant impact on performance and energy of modern applications. The authors observe that performance can vary by as much as 72% in some applications based on which memory allocator is used, and in this paper, the authors make a case for offloading memory allocation (and other similar management functions) from main processing cores to other processing units to boost performance, reduce energy consumption, and customize services to specific applications or application domains.
- NRPreTo: A Machine Learning-Based Nuclear Receptor and Subfamily Prediction Tool
- Article asserts that the nuclear receptor (NR) superfamily includes phylogenetically related ligand-activated proteins, which play a key role in various cellular activities. The authors developed Nuclear Receptor Prediction Tool (NRPreTo), a two-level NR prediction tool with a unique training approach where in addition to the sequence-based features used by existing NR prediction tools, six additional feature groups depicting various physiochemical, structural, and evolutionary features of proteins were utilized.
- Feasibility of PROMIS using computerized adaptive testing during inpatient rehabilitation
- Article describes how there has been an increased significance on patient-reported outcomes in clinical settings. The authors aimed to evaluate the feasibility of administering patient-reported outcome measures by computerized adaptive testing (CAT) using a tablet computer with rehabilitation inpatients, assess workload demands on staff, and estimate the extent to which rehabilitation inpatients have elevated T-scores on six Patient Reported Outcomes Measurement Information System (PROMIS) measures.
- FlexiChain 3.0: Distributed Ledger Technology-Based Intelligent Transportation for Vehicular Digital Asset Exchange in Smart Cities
- Article describes how, due to the enormous amounts of data being generated between users, Intelligent Transportation Systems (ITS) are complex Cyber-Physical Systems that necessitate a reliable and safe infrastructure. In this work, the authors explore Distributed Ledger Technology (DLT) and collect data about consensus algorithms and their applicability to be used in the IoV as the backbone of ITS.
- Visual object tracking: Progress, challenge, and future
- Article discusses how visual object tracking aims to continuously localize the target object of interest in a video sequence. To provide the community an overview, in this commentary, the authors discuss visual tracking from different aspects.
- OptiFit: Computer-Vision-Based Smartphone Application to Measure the Foot from Images and 3D Scans
- Article asserts that the foot is a vital organ, as it stabilizes the impact forces between the human skeletal system and the ground. The authors present an instep girth measurement algorithm, and they used a pixel per metric algorithm for measurement; these algorithms were accordingly integrated with the application.
- Privacy-Preserving Object Detection with Secure Convolutional Neural Networks for Vehicular Edge Computing
- Article discusses how with the wider adoption of edge computing services, intelligent edge devices, and high-speed V2X communication, compute-intensive tasks for autonomous vehicles, such as object detection using camera, LiDAR, and/or radar data, can be partially offloaded to road-side edge servers. The authors aim to address the privacy problem by protecting both vehicles' sensor data and the detection results.
- agroString: Visibility and Provenance through a Private Blockchain Platform for Agricultural Dispense towards Consumers
- Article discusses the large quantities of farm and meat products that rot and are wasted if correct actions are not taken leading to serious health concerns if consumed. Because there is no proper system for tracking and communicating the status of goods to consumers, a right which according to the authors should be a given, they propose a method of increased communication using Corda private blockchain.
- Autoencoder Composite Scoring to Evaluate Prosthetic Performance in Individuals with Lower Limb Amputation
- Authors of the article created an overall assessment metric using a deep learning autoencoder to directly compare clinical outcomes in a comparison of lower limb amputees using two different prosthetic devices—a mechanical knee and a microprocessor-controlled knee. The proposed methods were used on data collected from ten participants with a dysvascular transfemoral amputation recruited for a prosthetics research study.
- Electroencephalogram Signals for Detecting Confused Students in Online Education Platforms with Probability-Based Features
- Article discusses how despite the advantages of online education, it lacks face-to-face settings, which makes it very difficult to analyze the students’ level of interaction, understanding, and confusion. This study proposes a novel engineering approach that uses probability-based features (PBF) for increasing the efficacy of machine learning models.
- Role of Artificial Intelligence for Analysis of COVID-19 Vaccination-Related Tweets: Opportunities, Challenges, and Future Trends
- Article states that vaccines, though reliable preventative measures for diseases, also raise public concerns; public apprehension and doubts challenge the acceptance of new vaccines including the COVID-19 vaccines. This study is the first attempt to review the role of AI approaches in COVID-19 vaccination-related sentiment analysis.
- A Gaze into the Internal Logic of Graph Neural Networks, with Logic
- Article exploring graph node property prediction. Originally presented as part of the application track at the 38th International Conference on Logic Programming in Haifa, Israel.
- A Parallel Convolution and Decision Fusion-Based Flower Classification Method
- This article proposes a novel flower classification method that combines enhanced VGG16 (E-VGG16) with decision fusion.
- PharmaChain: A blockchain to ensure counterfeit‐free pharmaceutical supply chain
- Article discusses how globalisation has facilitated different industries to eliminate geographical boundaries and equipped organisations to work collectively to produce goods. The authors of the article propose a novel Distributed Ledger Technology (DLT) based transparent supply chain for PSC and proof-of-concept is implemented to analyse the scalability and efficiency of the proposed architecture.
- Detecting Covid-19 chaos driven phishing/malicious URL attacks by a fuzzy logic and data mining based intelligence system
- Article analyses the impact of Covid-19 on various cyber-security related aspects.
- Computing microRNA-gene interaction networks in pan-cancer using miRDriver
- This article is a study where the authors integrated the multi-omics datasets such as copy number aberration, DNA methylation, gene and microRNA expression to identify the signature microRNA-gene associations from frequently aberrated DNA regions across pan-cancer utilizing a LASSO-based regression approach.
- COVID-19 Vaccination-Related Sentiments Analysis: A Case Study Using Worldwide Twitter Dataset
- Article is a study analyzing the global perceptions and perspectives towards COVID-19 vaccination using a worldwide Twitter dataset, natural language processing, and machine learning.
- Blood cancer prediction using leukemia microarray gene data and hybrid logistic vector trees model
- Article is a study proposing an approach for blood cancer disease prediction using the supervised machine learning approach to perform blood cancer prediction with high accuracy using microarray gene data.
- Racism Detection by Analyzing Differential Opinions Through Sentiment Analysis of Tweets Using Stacked Ensemble GCR-NN Model
- This article presents a study detecting Tweets that contain racist text by performing the sentiment analysis of Tweets. The proposed GCR-NN model can detect 97% of the tweets that contain racist comments.
- Detection of DDoS Attack in Software-Defined Networking Environment and Its Protocol-wise Analysis using Machine Learning
- Article describes how distributed-denial-of-service (DDoS) attacks can cause a great menace to numerous organizations and their stakeholders. The authors assert that the objective of this research work is to take into account a DDoS afflicted SDN specific dataset and detect the malicious traffic by using various machine learning algorithms namely., K-Nearest Neighbours, Logistic Regression, Multilayer Perceptron, Iterative Dichotomiser 3, and Stochastic Gradient Descent.
- Vector mosquito image classification using novel RIFS feature selection and machine learning models for disease epidemiology
- Article proposes a Machine Learning (ML) and Deep Learning based system to detect the presence of two critical disease spreading classes of mosquitoes in order to prevent mosquito-borne infection.
- Recent advances in processing negation
- This article surveys previous work on negation with an emphasis on computational approaches.
- [Transdisciplinary Ancestral Genomic Research Investigations (TAGRI) II Conference Presentations on Artificial Intelligence in Health Research]
- Video recording of Dr. Mark V. Albert's presentation, "Artificial Intelligence and Applications in Genomics Research: Assessment of Mobility in Diverse Patient Populations" and Dr. Heather Wheeler's presentation, "Transcriptome Prediction Performance Across Machine Learning Models and Diverse Ancestries." They were presented at the Transdisciplinary Ancestral Genomic Research Investigations (TAGRI) II Conference held online November 5-6, 2021.
- Predicting psoriasis using routine laboratory tests with random forest
- Article describes how psoriasis is a chronic inflammatory skin disease that affects approximately 125 million people worldwide. The goal of the authors' study is to derive a powerful predictive model for psoriasis disease based on only routine hospital tests.
- Natlog: a Lightweight Logic Programming Language with a Neuro-symbolic Touch
- Article that introduces Natlog, a lightweight Logic Programming language, sharing Prolog's unification-driven execution model, but with a simplified syntax and semantics. The authors' proof-of-concept Natlog implementation is tightly embedded in the Python-based deep-learning ecosystem with focus on content-driven indexing of ground term datasets. As an overriding of the authors symbolic indexing algorithm, the same function can be delegated to a neural network, serving ground facts to Natlog's resolution engine. The open-source implementation is available as a Python package at t https://pypi.org/project/natlog/.
- Measuring the impact of suspending Umrah, a global mass gathering in Saudi Arabia on the COVID‑19 pandemic
- This article uses a stratified SEIR epidemic model to evaluate the impact of Umrah, a global Muslim pilgrimage to Mecca, on the spread of the COVID-19 pandemic during the month of Ramadan, the peak of the Umrah season. The analyses provide insights into the effects of global mass gatherings on the progression of the COVID-19 pandemic locally and globally.
- A smartphone-based online system for fall detection with alert notifications and contextual information of real-life falls
- This article presents the results of a prospective study investigating a proof-of-concept, smartphone-based, online system for fall detection and notification. Apart from functioning as a practical fall monitoring instrument, this system may serve as a valuable research tool, enable future studies to scale their ability to capture fall-related data, and help researchers and clinicians to investigate real-falls.
- Artificial Intelligence for Colonoscopy: Past, Present, and Future
- Article summarizing the past and present development of colonoscopy video analysis methods, focusing on two categories of artificial intelligence (AI) technologies used in clinical trials, (1) analysis and feedback for improving colonoscopy quality and (2) detection of abnormalities.
- PhenoGeneRanker: Gene and Phenotype Prioritization Using Multiplex Heterogeneous Networks
- Article
- Deep learning for peptide identification from metaproteomics datasets
- This article explores a proposed deep-learning-based algorithm called DeepFilter for improving peptide identifications from a collection of tandem mass spectra. The authors find that DeepFilter is believed to generalize properly to new, previously unseen peptide-spectrum-matches and can be readily applied in peptide identification from metaproteomics data.
- Weak-Light Image Enhancement Method Based on Adaptive Local Gamma Transform and Color Compensation
- This article proposes a correction method for image enhancement models based on an adaptive local gamma transformation and color compensation inspired by the illumination reflection model. It is demonstrated that the proposed method adaptively reduces the influence of uneven illumination to avoid overenhancement and improves the visual effect of low-light images.
- Protein functional module identification method combining topological features and gene expression data
- Article conducting an intensive study on the problems of low recognition efficiency and noise in the overlapping structure of protein functional modules, based on topological characteristics of PPI network. Developing a protein function module recognition method ECTG based on Topological Features and Gene expression data for Protein Complex Identification. The experimental results show that the ECTG algorithm can detect protein functional modules better.
- Using a microprocessor knee (C-Leg) with appropriate foot transitioned individuals with dysvascular transfemoral amputations to higher performance levels: a longitudinal randomized clinical trial
- Article evaluating whether advanced prostheses can provide better safety and performance capabilities to maintain and improve quality of life in individuals who are predominantly designated MFCL level K2. This study used a 13 month longitudinal clinical trial to determine the benefits of using a C-Leg and 1M10 foot in individuals at K2 level with transfemoral amputation due to vascular disease.
- Identifying Degree and Sources of Non-Determinism in MPI Applications Via Graph Kernels
- This article proposes a software framework for identifying the percentage and sources of communication non-determinism.
- Personal Internet of Things (PIoT): What Is It Exactly?
- This article provides a big picture of PIoT architecture, vision, and future research scope. The exploratory study of PIoT is in its infancy, which will explore the expansion of new use cases, service requirements, and the proliferation of PIoT devices. This is a preprint version of this article.
- Crinet: A computational tool to infer genome-wide competing endogenous RNA (ceRNA) interactions
- This article develops a computational tool named Crinet to infer genome-wide ceRNA networks addressing critical drawbacks. Crinet-inferred ceRNA groups that were consistently involved in the immune system related processes could be important assets in the light of the studies confirming the relation between immunotherapy and cancer. The source code of Crinet is in R and available at https://github.com/bozdaglab/crinet.
- COS: A new MeSH term embedding incorporating corpus, ontology, and semantic predications
- Article studying the problem of incorporating corpus, ontology, and semantic predications to learn the embeddings of MeSH terms. The authors propose a novel framework, Corpus, Ontology, and Semantic predications-based MeSH term embedding (COS), to generate high-quality MeSH term embeddings.
- Urban land-use analysis using proximate sensing imagery: a survey
- This article reviews and summarizes the state-of-the-art methods and publicly available data sets from proximate sensing to support land-use analysis. Discussions highlight the challenges, strategies, and opportunities faced by the existing methods using proximate sensing imagery in urban land-use studies.
- Action unit classification for facial expression recognition using active learning and SVM
- Article utilizing active learning and support vector machine (SVM) algorithms to classify facial action units (AU) for human facial expression recognition. Experimental results show that the proposed algorithm can effectively suppress correlated noise and achieve higher recognition rates than principal component analysis and a human observer on seven different facial expressions.
- Detection of Parkinson's Disease Through Automated Pupil Tracking of the Post-illumination Pupillary Response
- This article describes a system for pupil size estimation with a user interface to allow rapid adjustment of parameters and extraction of pupil parameters of interest in order to identify Parkinson's disease (PD) as early as possible.
- SSOR Preconditioned Gauss-Seidel Detection and Its Hardware Architecture for 5G and beyond Massive MIMO Networks
- This article proposes a novel preconditioned and accelerated Gauss–Siedel algorithm referred to as Symmetric Successive Overrelaxation Preconditioned Gauss-Seidel (SSORGS) to address the signal detection challenges associated with massive MIMO technology.
- On Comparing the Similarity and Dissimilarity Between Two Distinct Vehicular Trajectories
- This article studies the problem of comparing the similarity and dissimilarity between two distinct vehicular trajectories by proposing an adjacency-based metric. This approach has a broad application in building truthfulness by comparing the similarity between two vehicles and evaluating the dissimilarity between two distinct paths in hazardous materials transportation.
- Classifying Abdominal Fat Distribution Patterns by Using Body Measurement Data
- This article aims to explore new categorization that characterizes the distribution clusters of visceral and subcutaneous adipose tissues (VAT and SAT) measured by magnetic resonance imaging (MRI), to analyze the relationship between the VAT-SAT distribution patterns and the novel body shape descriptors (BSDs), and to develop a classifier to predict the fat distribution clusters using the BSDs.
- Investing Data with Untrusted Parties using HE
- Article proposing the use of anonymization techniques coupled with graph algorithms over homomorphically encrypted (HE) graphs as a basis of analysis for this accumulated data. This approach ensures individuals’ privacy and anonymity while preserving the usefulness of the plaintext data. This article was originally presented at the 18th International Conference on Security and Cryptography - SECRYPT.