Framework For Identification Research Articles

Ensemble learning and skip connection-based CNN framework for COVID-19 identification using CXR and CT images

Ensemble learning and skip connection-based CNN framework for COVID-19 identification using CXR and CT images

The framework of large group identification

The framework of large group identification

Med-Query: Steerable Parsing of 9-DoF Medical Anatomies with Query Embedding.

Automatic parsing of human anatomies at the instance-level from 3D computed tomography (CT) is a prerequisite step for many clinical applications. The presence of pathologies, broken structures or limited field-of-view (FOV) can all make anatomy parsing algorithms vulnerable. In this work, we explore how to leverage and implement the successful detection-then-segmentation paradigm for 3D medical data, and propose a steerable, robust, and efficient computing framework for detection, identification, and segmentation of anatomies in CT scans. Considering the complicated shapes, sizes, and orientations of anatomies, without loss of generality, we present a nine degrees of freedom (9-DoF) pose estimation solution in full 3D space using a novel single-stage, non-hierarchical representation. Our whole framework is executed in a steerable manner where any anatomy of interest can be directly retrieved to further boost inference efficiency. We have validated our method on three medical imaging parsing tasks: ribs, spine, and abdominal organs. For rib parsing, CT scans have been annotated at the rib instance-level for quantitative evaluation, similarly for spine vertebrae and abdominal organs. Extensive experiments on 9-DoF box detection and rib instance segmentation demonstrate the high efficiency and effectiveness of our framework (with the identification rate of 97.0% and the segmentation Dice score of 90.9%), compared favorably against several strong baselines (e.g., CenterNet, FCOS, and nnU-Net). For spine parsing and abdominal multi-organ segmentation, our method achieves competitive results on par with stateof-the-art methods on the public CTSpine1K dataset and FLARE22 competition, respectively. Our annotations, code, and models are available at: Med-Query.

Image-Decomposition-Enhanced Deep Learning for Detection of Rotor Cores in Cardiac Fibrillation.

Rotors, regions of spiral wave reentry in cardiac tissues, are considered as the drivers of atrial fibrillation (AF), the most common arrhythmia. Whereas physics-based approaches have been widely deployed to detect the rotors, in-depth knowledge in cardiac physiology and electrogram interpretation skills are typically needed. The recent leap forward in smart sensing, data acquisition, and Artificial Intelligence (AI) has offered an unprecedented opportunity to transform diagnosis and treatment in cardiac ailment, including AF. This study aims to develop an image-decomposition-enhanced deep learning framework for automatic identification of rotor cores on both simulation and optical mapping data. We adopt the Ensemble Empirical Mode Decomposition algorithm (EEMD) to decompose the original image, and the most representative component is then fed into a You-Only-Look-Once (YOLO) object-detection architecture for rotor detection. Simulation data from a bi-domain simulation model and optical mapping acquired from isolated rabbit hearts are used for training and validation. This integrated EEMD-YOLO model achieves high accuracy on both simulation and optical mapping data (precision: 97.2%, 96.8%, recall: 93.8%, 92.2%, and F1 score: 95.5%, 94.4%, respectively). The proposed EEMD-YOLO yields comparable accuracy in rotor detection with the gold standard in literature.

A Data-Driven Framework for Power System Event Type Identification via Safe Semi-Supervised Techniques

This paper investigates the use of phasor measurement unit (PMU) data with deep learning techniques to construct real-time event identification models for transmission networks. Increasing penetration of distributed energy resources represents a great opportunity to achieve decarbonization, as well as challenges in systematic situational awareness. When high-resolution PMU data and sufficient manually recorded event labels are available, the power event identification problem is defined as a statistical classification problem that can be solved by numerous cutting-edge classifiers. However, in real grids, collecting tremendous high-quality event labels is quite expensive. Utilities frequently have a large number of event records without in-depth details (i.e., unlabeled events). To bridge this gap, we propose a novel semi-supervised learning-based method to improve the performance of event classifiers trained with a limited number of labeled events by exploiting the information from massive unlabeled events. In other words, compared to existing data-driven methods, our method requires only a small portion of labeled data to achieve a similar level of accuracy. Meanwhile, this work discusses and addresses the performance degradation caused by class distribution mismatch between the training set and the real applications. Specifically, this method utilizes pseudo-labeling technique to investigate the value of unlabeled events and incrementally expands the training dataset. Moreover, a safe learning mechanism is developed to mitigate the impacts of class distribution mismatch and prevent performance degradation. Based on the proposed safe learning mechanism, our model does not directly use all unlabeled events during model training, but selectively uses them through a comprehensive evaluation procedure. Numerical studies on a sizable PMU dataset have been used to validate the performance of the proposed method.

Nurses and Nursing Students With Substance Use Disorders.

Substance use disorder (SUD) is a significant problem for millions of Americans. The incidence of SUDs among nurses and nursing students is thought to be like that found in the general population. Some studies suggest increases in substance use among college students given stressors related to the COVID-19 pandemic. Nurses are in unique positions to care for one another as we care for our patients. Identification, referral, and treatment of SUDs can prevent both nurses and nursing students from terminating their careers or nursing programs of study. The purposes of this article were to increase nurses' knowledge of SUDs among nurses and nursing students, provide an organizing framework for identification of substance problems among nurses/nursing students, and discuss ways to create a culture of support and recovery for nurses/nursing students with SUDs.

Supervised Learning Framework for Identification of Inverter Control Mode and Estimation of Inverter-based-Resource & Load Parameters

Supervised Learning Framework for Identification of Inverter Control Mode and Estimation of Inverter-based-Resource & Load Parameters

A global approach to estimate continuous-time LPV models for wastewater nitrification

In wastewater treatment, understanding and modeling the nitrification process is crucial to implement control. However, the complexity of this process makes it challenging to create simplified models. This study introduces an innovative method for estimating linear parameter-varying (LPV) models in the context of biological nitrification processes. The research focuses on the development of a continuous-time LPV model for a submerged aerated biofiltration system, considering the conversion of ammonium to nitrate in wastewater treatment. The methodology adopts the reinitialized partial moment approach within a global identification framework. The resultant LPV model is structured to capture the dynamics of the biological nitrification process, considering various factors like flow rates, feed concentrations and environmental regulations. Application of this approach to measured data from a wastewater treatment plant, demonstrates its effectiveness in accurately estimating the LPV model parameters. The results not only offer valuable insights into the dynamics and the nonlinear behaviour of the nitrification process but also contribute to the design and optimization of wastewater treatment plants, particularly those employing submerged aerated nitrifying biofilters.

Modal identification of existing concrete half-joint bridges through free vibration tests

Vibration-based tests are widely used for the assessment of existing structures. They allow the estimation of modal parameters, a possible deviation of which may be symptomatic of the onset of damage in the structure. Specifically, in the case of bridges, free vibration testing is a rapid, low-cost method that requires the installation of a limited number of sensors on the structure. This contribution presents the results of the dynamic identification for a series of existing concrete half-joint bridges based on free vibrations recorded after the transit of heavy trucks. The bridge deck modal characteristics (frequencies, damping ratios and mode shapes) are obtained via a recently developed identification framework based on the variation mode decomposition. These experimental estimates are also analyzed and used to calibrate a finite element model of the bridge deck, based on in-situ material characterization tests. Negligible fluctuations both in frequency and mode shapes are observed between experimental and numerical findings, which suggests that the analyzed overpasses do not present any relevant damage or cracking process under the service loads.

Road Traffic Accident Risk Prediction and Key Factor Identification Framework Based on Explainable Deep Learning

Road Traffic Accident Risk Prediction and Key Factor Identification Framework Based on Explainable Deep Learning

An AI-Enabled Framework to Defend Ingenious MDT-Based Attacks on the Emerging Zero Touch Cellular Networks

Deep automation provided by self-organizing network (SON) features and their emerging variants such as zero touch automation solutions is a key enabler for increasingly dense wireless networks and pervasive Internet of Things (IoT). To realize their objectives, most automation functionalities rely on the Minimization of Drive Test (MDT) reports. The MDT reports are used to generate inferences about network state and performance, thus dynamically change network parameters accordingly. However, the collection of MDT reports from commodity user devices, particularly low cost IoT devices, make them a vulnerable entry point to launch an adversarial attack on emerging deeply automated wireless networks. This adds a new dimension to the security threats in the IoT and cellular networks. Existing literature on IoT, SON, or zero touch automation does not address this important problem. In this paper, we investigate an impactful, first of its kind adversarial attack that can be launched by exploiting the malicious MDT reports from the compromised user equipment (UE). We highlight the detrimental repercussions of this attack on the performance of common network automation functions. We also propose a novel Malicious MDT Reports Identification framework (MRIF) as a countermeasure to detect and eliminate the malicious MDT reports using Machine Learning and verify it through a use-case. Thus, the defense mechanism can provide the resilience and robustness for zero touch automation SON engines against the adversarial MDT attacks.

AGI-P: A Gender Identification Framework for Authorship Analysis Using Customized Fine-Tuning of Multilingual Language Model

AGI-P: A Gender Identification Framework for Authorship Analysis Using Customized Fine-Tuning of Multilingual Language Model

Data-Driven Approach to Risk Identification for Major Transportation Projects: A Common Risk Breakdown Structure

Identifying and evaluating risks is one of the most essential steps in risk management in construction projects. When technical and managerial complexity increases in major transportation projects, this becomes even more important. Currently, project teams are assumed to identify risks mostly based on their experience and expertise. It is a major issue that some state departments of transportation (DOT) project teams lack the risk management experience. This study proposes using a data-driven approach to unify and summarize existing risk documents to create a comprehensive risk breakdown structure (RBS). As a preliminary risk identification framework, a consolidated RBS were developed, using content analysis of public risk reports by various DOTs. Then, comparison was made between the developed RBS with 70 US transportation projects' risk registers. Natural language processing techniques, bidirectional encoder representations from transformers, were employed to calculate semantic text similarity to determine what percentage of risks are covered by generic RBS. The results showed that 70 generic risk templates cover almost 81% of the identified risks in the database of 70 major projects which is about 6000 individual risks. Project parties can use these results to discuss and identify context-specific risks as a starting point. The study also determined the interactions between risk items based on their co-occurrence using historical data. Research findings revealed the importance of considering interdependencies between risks in future studies.

BINDTI: A bi-directional Intention network for drug-target interaction identification based on attention mechanisms.

The identification of drug-target interactions (DTIs) is an essential step in drug discovery. In vitro experimental methods are expensive, laborious, and time-consuming. Deep learning has witnessed promising progress in DTI prediction. However, how to precisely represent drug and protein features is a major challenge for DTI prediction. Here, we developed an end-to-end DTI identification framework called BINDTI based on bi-directional Intention network. First, drug features are encoded with graph convolutional networks based on its 2D molecular graph obtained by its SMILES string. Next, protein features are encoded based on its amino acid sequence through a mixed model called ACmix, which integrates self-attention mechanism and convolution. Third, drug and target features are fused through bi-directional Intention network, which combines Intention and multi-head attention. Finally, unknown drug-target (DT) pairs are classified through multilayer perceptron based on the fused DT features. The results demonstrate that BINDTI greatly outperformed four baseline methods (i.e., CPI-GNN, TransfomerCPI, MolTrans, and IIFDTI) on the BindingDB, BioSNAP, DrugBank, and Human datasets. More importantly, it was more appropriate to predict new DTIs than the four baseline methods on imbalanced datasets. Ablation experimental results elucidated that both bi-directional Intention and ACmix could greatly advance DTI prediction. The fused feature visualization and case studies manifested that the predicted results by BINDTI were basically consistent with the true ones. We anticipate that the proposed BINDTI framework can find new low-cost drug candidates, improve drugs' virtual screening, and further facilitate drug repositioning as well as drug discovery. BINDTI is publicly available at https://github.com/plhhnu/BINDTI.

Automated Parking Slot Identification Framework

Automated Parking Slot Identification Framework

Identification of Late Pleistocene and Holocene fossil lizards from Hall's Cave (Kerr County, Texas) and a primer on morphological variation in North American lizard skulls.

Fossil identification practices have a profound effect on our interpretation of the past because these identifications form the basis for downstream analyses. Therefore, well-supported fossil identifications are necessary for examining the impact of past environmental changes on populations and communities. Here we apply an apomorphic identification framework in a case study identifying fossil lizard remains from Hall's Cave, a late Quaternary fossil site located in Central Texas, USA. We present images and descriptions of a broad comparative sample of North American lizard cranial elements and compile new and previously reported apomorphic characters for identifying fossil lizards. Our fossil identifications from Hall's Cave resulted in a minimum of 11 lizard taxa, including five lizard taxa previously unknown from the site. Most of the identified fossil lizard taxa inhabit the area around Hall's Cave today, but we reinforce the presence of an extirpated species complex of horned lizard. A main goal of this work is to establish a procedure for making well-supported fossil lizard identifications across North America. The data from this study will assist researchers endeavoring to identify fossil lizards, increasing the potential for novel discoveries related to North American lizards and facilitating more holistic views of ancient faunal assemblages.

Research on e-commerce customer value mining based on K-means clustering algorithm

Abstract In the era of e-commerce economy, how to mine and study the different values of customers is an essential factor affecting the development of e-commerce enterprises. Based on this, this paper uses a clustering algorithm to mine and study the value of e-commerce customers. The research firstly constructs RFM e-commerce customer value identification framework, designs e-commerce customer value evaluation indexes and calculates the weights of the value indexes, and then uses K-means clustering algorithm and classical artificial bee colony algorithm to improve the Calculation, and completes e-commerce customer refinement based on the value of the user. The results show that the type of e-commerce customer value based on the RFMC model can be divided into eight types, based on which the e-commerce customer value is further subdivided into four types by using the clustering algorithm, namely, core customers (13.86%), supportive customers (45.38%), habitual customers (21.08%) and risky customers (19.68%). Based on the clustering algorithm, the customer value was classified into type 0 customers (low value customers), type 1 customers (high value customers), and type 2 customers (medium value customers).

Data and knowledge collaborative-driven fault identification and self-healing control action inference framework for blast furnace

The blast furnace reactor has a large volume, and smelting occurs at high temperatures and high-pressure environments. The blast furnace reactor has a large volume, and smelting occurs at high temperatures and high-pressure environments. Considering the small samples of fault data and non-stationarity of the production process with a considerable time lag, it is difficult to diagnose and eliminate the faults timely. This paper proposes for the first time a data and knowledge collaborative-driven framework to identify fault and perform self-healing control. Following the adaptive two-scale sequence division method, the prior knowledge matrix refined K2 algorithm is used to construct Bayesian networks to model the control process. When a new abnormal condition arises, the most similar historical sequence will be found, and inference on the corresponding Bayesian network can lead to fault identification results and self-healing control action. The proposed framework has achieved satisfactory results in simulation experiments and real data experiments. In the simulation data, the Bayesian network (BN) modeling achieved an accuracy of 98.75%, and the time required for structure learning of the BN was reduced by over 75.69%. In real data, the accuracy of identifying blast furnace faults reached 97.1%, and the results of self-healing control reasoning surpassed those of traditional BN reasoning methods in terms of correctness, order, completeness, and necessity.

Quantifying the Impact of the Peptide Identification Framework on the Results of Fast Photochemical Oxidation of Protein Analysis.

Fast Photochemical Oxidation of Proteins (FPOP) is a promising technique for studying protein structure and dynamics. The quality of insight provided by FPOP depends on the reliability of the determination of the modification site. This study investigates the performance of two search engines, Mascot and PEAKS, for the data processing of FPOP analyses. Comparison of Mascot and PEAKS of the hemoglobin--haptoglobin Bruker timsTOF data set (PXD021621) revealed greater consistency in the Mascot identification of modified peptides, with around 26% of the IDs being mutual for all three replicates, compared to approximately 22% for PEAKS. The intersection between Mascot and PEAKS results revealed a limited number (31%) of shared modified peptides. Principal Component Analysis (PCA) using the peptide-spectrum match (PSM) score, site probability, and peptide intensity was applied to evaluate the results, and the analyses revealed distinct clusters of modified peptides. Mascot showed the ability to assess confident site determination, even with lower PSM scores. However, high PSM scores from PEAKS did not guarantee a reliable determination of the modification site. Fragmentation coverage of the modification position played a crucial role in Mascot assignments, while the AScore localizations from PEAKS often become ambiguous because the software employs MS/MS merging.

ResnetAge: A Resnet-Based DNA Methylation Age Prediction Method.

Aging is a significant contributing factor to degenerative diseases such as cancer. The extent of DNA methylation in human cells indicates the aging process and screening for age-related methylation sites can be used to construct epigenetic clocks. Thereby, it can be a new aging-detecting marker for clinical diagnosis and treatments. Predicting the biological age of human individuals is conducive to the study of physical aging problems. Although many researchers have developed epigenetic clock prediction methods based on traditional machine learning and even deep learning, higher prediction accuracy is still required to match the clinical applications. Here, we proposed an epigenetic clock prediction method based on a Resnet neuro networks model named ResnetAge. The model accepts 22,278 CpG sites as a sample input, supporting both the Illumina 27K and 450K identification frameworks. It was trained using 32 public datasets containing multiple tissues such as whole blood, saliva, and mouth. The Mean Absolute Error (MAE) of the training set is 1.29 years, and the Median Absolute Deviation (MAD) is 0.98 years. The Mean Absolute Error (MAE) of the validation set is 3.24 years, and the Median Absolute Deviation (MAD) is 2.3 years. Our method has higher accuracy in age prediction in comparison with other methylation-based age prediction methods.