Search results for: multimodal fusion classifier

Authors: Kemka Ihemelandu, Chukwuemeka Ihemelandu

Abstract:

Melanoma remains a public health crisis, with incidence rates increasing rapidly in the past decades. Improving diagnostic accuracy to decrease misdiagnosis using Artificial intelligence (AI) continues to be documented. Unfortunately, unintended racially biased outcomes, a product of lack of diversity in the dataset used, with a noted class imbalance favoring lighter vs. darker skin tone, have increasingly been recognized as a problem.Resulting in noted limitations of the accuracy of the Convolutional neural network (CNN)models. CNN models are prone to biased output due to biases in the dataset used to train them. Our aim in this study was the optimization of convolutional neural network algorithms to mitigate bias in the automated diagnosis of melanoma. We hypothesized that our proposed training algorithms based on a data augmentation method to optimize the diagnostic accuracy of a CNN classifier by generating new training samples from the original ones will reduce bias in the automated diagnosis of melanoma. We applied geometric transformation, including; rotations, translations, scale change, flipping, and shearing. Resulting in a CNN model that provided a modifiedinput data making for a model that could learn subtle racial features. Optimal selection of the momentum and batch hyperparameter increased our model accuracy. We show that our augmented model reduces bias while maintaining accuracy in the automated diagnosis of melanoma.

Keywords: bias, augmentation, melanoma, convolutional neural network

Procedia PDF Downloads 213

Authors: Rui Liu, Pengyu Cui, Nan Jiang

Abstract:

At present, there is much research on the application of centralized management and cross-integration application of basic geographic information. However, the idea of information integration and sharing between land, sea, and air navigation targets is not deeply applied into the research of navigation information service, especially in the information expression. Targeting at this problem, the paper carries out works about the expression pattern of navigation electronic map for ground vehicles under air and land united navigation mechanism. At first, with the support from multi-source information fusion of GIS vector data, RS data, GPS data, etc., an air and land united information expression pattern is designed aiming at specific navigation task of emergency rescue in the earthquake. And then, the characteristics and specifications of the united expression of air and land navigation information under the constraints of map load are summarized and transferred into expression rules in the rule bank. At last, the related navigation experiment is implemented to evaluate the effect of the expression pattern. The experiment selects evaluation factors of the navigation task accomplishment time and the navigation error rate as the main index, and make comparisons with the traditional single information expression pattern. To sum up, the research improved the theory of navigation electronic map and laid a certain foundation for the design and realization of united navigation system in the aspect of real-time navigation information delivery.

Keywords: navigation electronic map, united navigation, multi-element expression pattern, multi-source information fusion

Procedia PDF Downloads 201

Authors: Simone Leonardi, Luca Ardito

Abstract:

Micro-influencers are effective elements in the marketing strategies of companies and institutions because of their capability to create an hyper-engaged audience around a specific topic of interest. In recent years, many scientific approaches and commercial tools have handled the task of detecting this type of social media users. These strategies adopt solutions ranging from rule based machine learning models to deep neural networks and graph analysis on text, images, and account information. This work compares the existing solutions and proposes an ensemble method to generalize them with different input data and social media platforms. The deployed solution combines deep learning models on unstructured data with statistical machine learning models on structured data. We retrieve both social media accounts information and multimedia posts on Twitter and Instagram. These data are mapped into feature vectors for an eXtreme Gradient Boosting (XGBoost) classifier. Sixty different topics have been analyzed to build a rule based gold standard dataset and to compare the performances of our approach against baseline classifiers. We prove the effectiveness of our work by comparing the accuracy, precision, recall, and f1 score of our model with different configurations and architectures. We obtained an accuracy of 0.91 with our best performing model.

Keywords: deep learning, gradient boosting, image processing, micro-influencers, NLP, social media

Procedia PDF Downloads 184

Authors: Chung-Ming Lo, Chung-Chien Lee

Abstract:

In many countries, the lifetime prevalence of shoulder pain is up to 70%. In America, the health care system spends 7 billion per year about the healthy issues of shoulder pain. With respect to the origin, up to 70% of shoulder pain is attributed to rotator cuff lesions This study proposed a computer-aided diagnosis (CAD) system to assist radiologists classifying rotator cuff lesions with less operator dependence. Quantitative features were extracted from the shoulder ultrasound images acquired using an ALOKA alpha-6 US scanner (Hitachi-Aloka Medical, Tokyo, Japan) with linear array probe (scan width: 36mm) ranging from 5 to 13 MHz. During examination, the postures of the examined patients are standard sitting position and are followed by the regular routine. After acquisition, the shoulder US images were drawn out from the scanner and stored as 8-bit images with pixel value ranging from 0 to 255. Upon the sonographic appearance, the boundary of each lesion was delineated by a physician to indicate the specific pattern for analysis. The three lesion categories for classification were composed of 20 cases of tendon inflammation, 18 cases of calcific tendonitis, and 18 cases of supraspinatus tear. For each lesion, second-order statistics were quantified in the feature extraction. The second-order statistics were the texture features describing the correlations between adjacent pixels in a lesion. Because echogenicity patterns were expressed via grey-scale. The grey-scale co-occurrence matrixes with four angles of adjacent pixels were used. The texture metrics included the mean and standard deviation of energy, entropy, correlation, inverse different moment, inertia, cluster shade, cluster prominence, and Haralick correlation. Then, the quantitative features were combined in a multinomial logistic regression classifier to generate a prediction model of rotator cuff lesions. Multinomial logistic regression classifier is widely used in the classification of more than two categories such as the three lesion types used in this study. In the classifier, backward elimination was used to select a feature subset which is the most relevant. They were selected from the trained classifier with the lowest error rate. Leave-one-out cross-validation was used to evaluate the performance of the classifier. Each case was left out of the total cases and used to test the trained result by the remaining cases. According to the physician’s assessment, the performance of the proposed CAD system was shown by the accuracy. As a result, the proposed system achieved an accuracy of 86%. A CAD system based on the statistical texture features to interpret echogenicity values in shoulder musculoskeletal ultrasound was established to generate a prediction model for rotator cuff lesions. Clinically, it is difficult to distinguish some kinds of rotator cuff lesions, especially partial-thickness tear of rotator cuff. The shoulder orthopaedic surgeon and musculoskeletal radiologist reported greater diagnostic test accuracy than general radiologist or ultrasonographers based on the available literature. Consequently, the proposed CAD system which was developed according to the experiment of the shoulder orthopaedic surgeon can provide reliable suggestions to general radiologists or ultrasonographers. More quantitative features related to the specific patterns of different lesion types would be investigated in the further study to improve the prediction.

Keywords: shoulder ultrasound, rotator cuff lesions, texture, computer-aided diagnosis

Procedia PDF Downloads 286

Authors: Hantian Wu, Bo Huang, Yuan Zeng

Abstract:

Divisions between wealthy and poor, private and public landscapes are propagated by the increasing economic inequality of cities. While these are the spatial reflections of larger social issues and problems, urban design can at least employ spatial techniques that promote more inclusive rather than exclusive, overlapping rather than segregated, interlinked rather than disconnected landscapes. Indeed, the type of edge or border between urban landscapes plays a critical role in the way the environment is perceived. China experiences rapid urbanization, which poses unpredictable environmental challenges. The urban green cover and water body are under changes, which highly relevant to resident wealth and happiness. However, very limited knowledge and data on their rapid changes are available. In this regard, enhancing the monitoring of urban landscape with high-frequency method, evaluating and estimating the impacts of the urban landscape changes, and understating the driving forces of urban landscape changes can be a significant contribution for urban planning and studying. High-resolution remote sensing data has been widely applied to urban management in China. The map of urban land use map for the entire China of 2018 with 10 meters resolution has been published. However, this research focuses on the large-scale and high-resolution remote sensing land use but does not precisely focus on the seasonal change of urban covers. High-resolution remote sensing data has a long-operation cycle (e.g., Landsat 8 required 16 days for the same location), which is unable to satisfy the requirement of monitoring urban-landscape changes. On the other hand, aerial-remote or unmanned aerial vehicle (UAV) sensing are limited by the aviation-regulation and cost was hardly widely applied in the mega-cities. Moreover, those data are limited by the climate and weather conditions (e.g., cloud, fog), and those problems make capturing spatial and temporal dynamics is always a challenge for the remote sensing community. Particularly, during the rainy season, no data are available even for Sentinel Satellite data with 5 days interval. Many natural events and/or human activities drive the changes of urban covers. In this case, enhancing the monitoring of urban landscape with high-frequency method, evaluating and estimating the impacts of the urban landscape changes, and understanding the mechanism of urban landscape changes can be a significant contribution for urban planning and studying. This project aims to use the high spatiotemporal fusion of remote sensing data to create short-cycle, high-resolution remote sensing data sets for exploring the high-frequently urban cover changes. This research will enhance the long-term monitoring applicability of high spatiotemporal fusion of remote sensing data for the urban landscape for optimizing the urban management of landscape border to promoting the inclusive of the urban landscape to all communities.

Keywords: urban land cover changes, remote sensing, high spatiotemporal fusion, urban management

Procedia PDF Downloads 126

Authors: Arth J. Shah, Madhu R. Kamble

Abstract:

Voice biometric liveness detection is customized to certify an authentication process of the voice data presented is genuine and not a recording or synthetic voice. With the rise of deepfakes and other equivalently sophisticated spoofing generation techniques, it’s becoming challenging to ensure that the person on the other end is a live speaker or not. Voice Liveness Detection (VLD) system is a group of security measures which detect and prevent voice spoofing attacks. Motivated by the recent development of the Kolmogorov-Arnold Network (KAN) based on the Kolmogorov-Arnold theorem, we proposed KAN for the VLD task. To date, multilayer perceptron (MLP) based classifiers have been used for the classification tasks. We aim to capture not only the compositional structure of the model but also to optimize the values of univariate functions. This study explains the mathematical as well as experimental analysis of KAN for VLD tasks, thereby opening a new perspective for scientists to work on speech and signal processing-based tasks. This study emerges as a combination of traditional signal processing tasks and new deep learning models, which further proved to be a better combination for VLD tasks. The experiments are performed on the POCO and ASVSpoof 2017 V2 database. We used Constant Q-transform, Mel, and short-time Fourier transform (STFT) based front-end features and used CNN, BiLSTM, and KAN as back-end classifiers. The best accuracy is 91.26 % on the POCO database using STFT features with the KAN classifier. In the ASVSpoof 2017 V2 database, the lowest EER we obtained was 26.42 %, using CQT features and KAN as a classifier.

Keywords: Kolmogorov Arnold networks, multilayer perceptron, pop noise, voice liveness detection

Procedia PDF Downloads 44

Authors: Matthew Yeager, Christopher Willy, John Bischoff

Abstract:

The conceptualization and design phases of a system lifecycle consume a significant amount of the lifecycle budget in the form of direct tasking and capital, as well as the implicit costs associated with unforeseeable design errors that are only realized during downstream phases. Ad hoc or iterative approaches to generating system requirements oftentimes fail to consider the full array of feasible systems or product designs for a variety of reasons, including, but not limited to: initial conceptualization that oftentimes incorporates a priori or legacy features; the inability to capture, communicate and accommodate stakeholder preferences; inadequate technical designs and/or feasibility studies; and locally-, but not globally-, optimized subsystems and components. These design pitfalls can beget unanticipated developmental or system alterations with added costs, risks and support activities, heightening the risk for suboptimal system performance, premature obsolescence or forgone development. Supported by rapid advances in learning algorithms and hardware technology, sensors and sensor systems have become commonplace in both commercial and industrial products. The evolving array of hardware components (i.e. sensors, CPUs, modular / auxiliary access, etc…) as well as recognition, data fusion and communication protocols have all become increasingly complex and critical for design engineers during both concpetualization and implementation. This work seeks to develop and utilize a non-deterministic approach for sensor system design within the multi-attribute tradespace exploration (MATE) paradigm, a technique that incorporates decision theory into model-based techniques in order to explore complex design environments and discover better system designs. Developed to address the inherent design constraints in complex aerospace systems, MATE techniques enable project engineers to examine all viable system designs, assess attribute utility and system performance, and better align with stakeholder requirements. Whereas such previous work has been focused on aerospace systems and conducted in a deterministic fashion, this study addresses a wider array of system design elements by incorporating both traditional tradespace elements (e.g. hardware components) as well as popular multi-sensor data fusion models and techniques. Furthermore, statistical performance features to this model-based MATE approach will enable non-deterministic techniques for various commercial systems that range in application, complexity and system behavior, demonstrating a significant utility within the realm of formal systems decision-making.

Keywords: multi-attribute tradespace exploration, data fusion, sensors, systems engineering, system design

Procedia PDF Downloads 189

Authors: Efstratios Karavasilis, Foteini Christidi, Georgios Velonakis, Agapi Plousi, Kalliopi Platoni, Nikolaos Kelekis, Ioannis Evdokimidis, Efstathios Efstathopoulos

Abstract:

Introduction: Advanced structural and functional neuroimaging techniques contribute to the study of anatomical and functional brain connectivity and its role in the pathophysiology and symptoms’ heterogeneity in several neurodegenerative disorders, including multiple sclerosis (MS). Aim: In the present study, we applied multiparametric neuroimaging techniques to investigate the structural and functional cortico-cerebellar changes in MS patients. Material: We included 51 MS patients (28 with clinically isolated syndrome [CIS], 31 with relapsing-remitting MS [RRMS]) and 51 age- and gender-matched healthy controls (HC) who underwent MRI in a 3.0T MRI scanner. Methodology: The acquisition protocol included high-resolution 3D T1 weighted, diffusion-weighted imaging and echo planar imaging sequences for the analysis of volumetric, tractography and functional resting state data, respectively. We performed between-group comparisons (CIS, RRMS, HC) using CAT12 and CONN16 MATLAB toolboxes for the analysis of volumetric (cerebellar gray matter density) and functional (cortico-cerebellar resting-state functional connectivity) data, respectively. Brainance suite was used for the analysis of tractography data (cortico-cerebellar white matter integrity; fractional anisotropy [FA]; axial and radial diffusivity [AD; RD]) to reconstruct the cerebellum tracts. Results: Patients with CIS did not show significant gray matter (GM) density differences compared with HC. However, they showed decreased FA and increased diffusivity measures in cortico-cerebellar tracts, and increased cortico-cerebellar functional connectivity. Patients with RRMS showed decreased GM density in cerebellar regions, decreased FA and increased diffusivity measures in cortico-cerebellar WM tracts, as well as a pattern of increased and mostly decreased functional cortico-cerebellar connectivity compared to HC. The comparison between CIS and RRMS patients revealed significant GM density difference, reduced FA and increased diffusivity measures in WM cortico-cerebellar tracts and increased/decreased functional connectivity. The identification of decreased WM integrity and increased functional cortico-cerebellar connectivity without GM changes in CIS and the pattern of decreased GM density decreased WM integrity and mostly decreased functional connectivity in RRMS patients emphasizes the role of compensatory mechanisms in early disease stages and the disintegration of structural and functional networks with disease progression. Conclusions: In conclusion, our study highlights the added value of multimodal neuroimaging techniques for the in vivo investigation of cortico-cerebellar brain changes in neurodegenerative disorders. An extension and future opportunity to leverage multimodal neuroimaging data inevitably remain the integration of such data in the recently-applied mathematical approaches of machine learning algorithms to more accurately classify and predict patients’ disease course.

Keywords: advanced neuroimaging techniques, cerebellum, MRI, multiple sclerosis

Procedia PDF Downloads 141

Authors: Lae-Jeong Park

Abstract:

The paper presents a method that utilizes figure-ground color segmentation to extract effective global feature in terms of false positive reduction in the head-shoulder detection. Conventional detectors that rely on local features such as HOG due to real-time operation suffer from false positives. Color cue in an input image provides salient information on a global characteristic which is necessary to alleviate the false positives of the local feature based detectors. An effective approach that uses figure-ground color segmentation has been presented in an effort to reduce the false positives in object detection. In this paper, an extended version of the approach is presented that adopts separate multipart foregrounds instead of a single prior foreground and performs the figure-ground color segmentation with each of the foregrounds. The multipart foregrounds include the parts of the head-shoulder shape and additional auxiliary foregrounds being optimized by a search algorithm. A classifier is constructed with the feature that consists of a set of the multiple resulting segmentations. Experimental results show that the presented method can discriminate more false positive than the single prior shape-based classifier as well as detectors with the local features. The improvement is possible because the presented approach can reduce the false positives that have the same colors in the head and shoulder foregrounds.

Keywords: pedestrian detection, color segmentation, false positive, feature extraction

Procedia PDF Downloads 281

Authors: Evgeniya Y. Yuzbasheva, Tigran V. Yuzbashev, Natalia I. Perkovskaya, Elizaveta B. Mostova

Abstract:

Cell-surface display of lipase is of great interest as it has many applications in the field of biotechnology owing to its unique advantages: simplified product purification, and cost-effective downstream processing. One promising area of application for whole-cell biocatalysts with surface displayed lipase is biodiesel synthesis. Biodiesel is biodegradable, renewable, and nontoxic alternative fuel for diesel engines. Although the alkaline catalysis method has been widely used for biodiesel production, it has a number of limitations, such as rigorous feedstock specifications, complicated downstream processes, including removal of inorganic salts from the product, recovery of the salt-containing by-product glycerol, and treatment of alkaline wastewater. Enzymatic synthesis of biodiesel can overcome these drawbacks. In this study, Lip2p lipase was displayed on Yarrowia lipolytica cells via C- and N-terminal fusion variant. The active site of lipase is located near the C-terminus, therefore to prevent the activity loosing the insertion of glycine-serine linker between Lip2p and C-domains was performed. The hydrolytic activity of the displayed lipase reached 12,000–18,000 U/g of dry weight. However, leakage of enzyme from the cell wall was observed. In case of C-terminal fusion variant, the leakage was occurred due to the proteolytic cleavage within the linker peptide. In case of N-terminal fusion variant, the leaking enzyme was presented as three proteins, one of which corresponded to the whole hybrid protein. The calculated number of recombinant enzyme displayed on the cell surface is approximately 6–9 × 105 molecules per cell, which is close to the theoretical maximum (2 × 106 molecules/cell). Thus, we attribute the enzyme leakage to the limited space available on the cell surface. Nevertheless, cell-bound lipase exhibited greater stability to short-term and long-term temperature treatment than the native enzyme. It retained 74% of original activity at 60°C for 5 min of incubation, and 83% of original activity after incubation at 50°C during 5 h. Cell-bound lipase had also higher stability in organic solvents and detergents. The developed whole-cell biocatalyst was used for recycling biodiesel synthesis. Two repeated cycles of methanolysis yielded 84.1–% and 71.0–% methyl esters after 33–h and 45–h reactions, respectively.

Keywords: biodiesel, cell-surface display, lipase, whole-cell biocatalyst

Procedia PDF Downloads 483

Authors: Jared Cheves, Amanda DeChent, Joyce Pan

Abstract:

Total knee replacements (TKAs) are one of the most common but painful surgical procedures performed in the United States. Currently, the gold standard for postoperative pain management is the utilization of opioids. However, in the wake of the opioid epidemic, the healthcare system is attempting to reduce opioid consumption by trialing innovative opioid sparing analgesic techniques such as continuous peripheral nerve blocks (CPNB) and continuous periarticular infiltration (CPAI). The alleviation of pain, particularly during the first 72 hours postoperatively, is of utmost importance due to its association with delayed recovery, impaired rehabilitation, immunosuppression, the development of chronic pain, the development of rebound pain, and decreased patient satisfaction. While both CPNB and CPAI are being used today, there is limited evidence comparing the two to the current standard of care or to each other. An extensive literature review was performed to explore the safety profiles and effectiveness of CPNB and CPAI in reducing reported pain scores and decreasing opioid consumption. The literature revealed the usage of CPNB contributed to lower pain scores and decreased opioid use when compared to opioid-only control groups. Additionally, CPAI did not improve pain scores or decrease opioid consumption when combined with a multimodal analgesic (MMA) regimen. When comparing CPNB and CPAI to each other, neither unanimously lowered pain scores to a greater degree, but the literature indicates that CPNB decreased opioid consumption more than CPAI. More research is needed to further cement the efficacy of CPNB and CPAI as standard components of MMA in TKA procedures. In addition, future research can also focus on novel catheter-free applications to reduce the complications of continuous catheter analgesics.

Keywords: total knee arthroplasty, continuous peripheral nerve blocks, continuous periarticular infiltration, opioid, multimodal analgesia

Procedia PDF Downloads 98

Authors: Kumar Shashvat, Amol P. Bhondekar

Abstract:

In the midst of the five senses, odor is the most reminiscent and least understood. Odor testing has been mysterious and odor data fabled to most practitioners. The delinquent of recognition and classification of odor is important to achieve. The facility to smell and predict whether the artifact is of further use or it has become undesirable for consumption; the imitation of this problem hooked on a model is of consideration. The general industrial standard for this classification is color based anyhow; odor can be improved classifier than color based classification and if incorporated in machine will be awfully constructive. For cataloging of odor for peas, trees and cashews various discriminative approaches have been used Discriminative approaches offer good prognostic performance and have been widely used in many applications but are incapable to make effectual use of the unlabeled information. In such scenarios, generative approaches have better applicability, as they are able to knob glitches, such as in set-ups where variability in the series of possible input vectors is enormous. Generative models are integrated in machine learning for either modeling data directly or as a transitional step to form an indeterminate probability density function. The algorithms or models Linear Discriminant Analysis and Naive Bayes Classifier have been used for classification of the odor of cashews. Linear Discriminant Analysis is a method used in data classification, pattern recognition, and machine learning to discover a linear combination of features that typifies or divides two or more classes of objects or procedures. The Naive Bayes algorithm is a classification approach base on Bayes rule and a set of qualified independence theory. Naive Bayes classifiers are highly scalable, requiring a number of restraints linear in the number of variables (features/predictors) in a learning predicament. The main recompenses of using the generative models are generally a Generative Models make stronger assumptions about the data, specifically, about the distribution of predictors given the response variables. The Electronic instrument which is used for artificial odor sensing and classification is an electronic nose. This device is designed to imitate the anthropological sense of odor by providing an analysis of individual chemicals or chemical mixtures. The experimental results have been evaluated in the form of the performance measures i.e. are accuracy, precision and recall. The investigational results have proven that the overall performance of the Linear Discriminant Analysis was better in assessment to the Naive Bayes Classifier on cashew dataset.

Keywords: odor classification, generative models, naive bayes, linear discriminant analysis

Procedia PDF Downloads 390

Authors: P. Weerkamp Bartholomeus

Abstract:

Autism treatment evaluation is crucial for monitoring the development of an intervention at an early stage. ‘ReAttach’ is a new intervention based on the principles of attachment and social cognitive training. Practical research suggests promising results on a variety of developmental areas. Five years after the first ReAttach sessions these findings can be extended with qualitative research by means of follow-up interviews. The potential impact of this treatment on daily life functioning and well-being of autistic persons becomes clear.

Keywords: autism, innovation, treatment, social cognitive training

Procedia PDF Downloads 292

Authors: Rohit Gupta, Ravinder Agarwal

Abstract:

Surface electromyographic (sEMG) signal has the potential to identify the human activities and intention. This potential is further exploited to control the artificial limbs using the sEMG signal from residual limbs of amputees. The paper deals with the development of multichannel cost efficient sEMG signal interface for research application, along with evaluation of proposed class dependent statistical approach of the feature selection method. The sEMG signal acquisition interface was developed using ADS1298 of Texas Instruments, which is a front-end interface integrated circuit for ECG application. Further, the sEMG signal is recorded from two lower limb muscles for three locomotions namely: Plane Walk (PW), Stair Ascending (SA), Stair Descending (SD). A class dependent statistical approach is proposed for feature selection and also its performance is compared with 12 preexisting feature vectors. To make the study more extensive, performance of five different types of classifiers are compared. The outcome of the current piece of work proves the suitability of the proposed feature selection algorithm for locomotion recognition, as compared to other existing feature vectors. The SVM Classifier is found as the outperformed classifier among compared classifiers with an average recognition accuracy of 97.40%. Feature vector selection emerges as the most dominant factor affecting the classification performance as it holds 51.51% of the total variance in classification accuracy. The results demonstrate the potentials of the developed sEMG signal acquisition interface along with the proposed feature selection algorithm.

Keywords: classifiers, feature selection, locomotion, sEMG

Procedia PDF Downloads 293

Authors: Azita Ramezani, Ghazal Mashhadiagha, Bahareh Sanabakhsh

Abstract:

This study researches the combination of Random. Forest classifiers with large language models (LLMs) and natural language processing (NLP) to improve diagnostic accuracy in chest X-ray analysis using the Indiana University dataset. Utilizing advanced NLP techniques, the research preprocesses textual data from radiological reports to extract key features, which are then merged with image-derived data. This improved dataset is analyzed with Random Forest classifiers to predict specific clinical results, focusing on the identification of health issues and the estimation of case urgency. The findings reveal that the combination of NLP, LLMs, and machine learning not only increases diagnostic precision but also reliability, especially in quickly identifying critical conditions. Achieving an accuracy of 99.35%, the model shows significant advancements over conventional diagnostic techniques. The results emphasize the large potential of machine learning in medical imaging, suggesting that these technologies could greatly enhance clinician judgment and patient outcomes by offering quicker and more precise diagnostic approximations.

Keywords: natural language processing (NLP), large language models (LLMs), random forest classifier, chest x-ray analysis, medical imaging, diagnostic accuracy, indiana university dataset, machine learning in healthcare, predictive modeling, clinical decision support systems

Procedia PDF Downloads 47

Authors: Harshit Agrawal, Salman Muhammad

Abstract:

Degradation to reinforced concrete (RC), primarily due to corrosion of embedded reinforcement, has been a major cause of concern worldwide. Among several ways to control corrosion, the use of coated reinforcement has gained significant interest in field applications. However, the choice of proper coating material and the effect of damage over coating are yet to be addressed for effective application of coated reinforcements. The present study aims to investigate and compare the performance of three different types of coated reinforcements —Fusion-Bonded Epoxy Coating (FBEC), Cement Polymer Composite Coating (CPCC), and Dual Zinc-Epoxy Coating (DZEC) —in concrete structures. The aim is to assess their corrosion resistance, durability, and overall effectiveness as coated reinforcement materials both in undamaged and simulated damaged conditions. Through accelerated corrosion tests, electrochemical analysis, and exposure to aggressive marine environments, the study evaluates the long-term performance of each coating system. This research serves as a crucial guide for engineers and construction professionals in selecting the most suitable corrosion protection for reinforced concrete, thereby enhancing the durability and sustainability of infrastructure.

Keywords: corrosion, reinforced concrete, coated reinforcement, seawater exposure, electrochemical analysis, service life, corrosion prevention

Procedia PDF Downloads 84

Authors: Gayathri Devi V, Aravamudan Kannan, Amit Sircar

Abstract:

In the inner fuel cycle system of a nuclear fusion reactor, the Hydrogen Isotopes Removal System (HIRS) plays a pivoted role. It enables the effective extraction of the hydrogen isotopes from the breeder purge gas which helps to maintain the tritium breeding ratio and sustain the fusion reaction. One of the components of HIRS, Cryogenic Molecular Sieve Bed (CMSB) columns with zeolites adsorbents are considered for the physisorption of hydrogen isotopes at 1 bar and 77 K. Even though zeolites have good thermal stability and reduced activation properties making them ideal for use in nuclear reactor applications, their modest capacity for hydrogen isotopes adsorption is a cause of concern. In order to enhance the adsorbent capacity in an informed manner, it is helpful to understand the adsorption phenomena at the quantum electronic structure level. Physicochemical modifications of the adsorbent material enhances the adsorption capacity through the incorporation of active sites. This may be accomplished through the incorporation of suitable metal ions in the zeolite framework. In this work, molecular hydrogen isotopes adsorption on the active sites of functionalized zeolites are investigated in detail using Density Functional Theory (DFT) study. This involves the utilization of hybrid Generalized Gradient Approximation (GGA) with dispersion correction to account for the exchange and correlation functional of DFT. The electronic energies, adsorption enthalpy, adsorption free energy, Highest Occupied Molecular Orbital (HOMO), Lowest Unoccupied Molecular Orbital (LUMO) energies are computed on the stable 8T zeolite clusters as well as the periodic structure functionalized with different active sites. The characteristics of the dihydrogen bond with the active metal sites and the isotopic effects are also studied in detail. Validation studies with DFT will also be presented for adsorption of hydrogen on metal ion functionalized zeolites. The ab-inito screening analysis gave insights regarding the mechanism of hydrogen interaction with the zeolites under study and also the effect of the metal ion on adsorption. This detailed study provides guidelines for selection of the appropriate metal ions that may be incorporated in the zeolites framework for effective adsorption of hydrogen isotopes in the HIRS.

Keywords: adsorption enthalpy, functionalized zeolites, hydrogen isotopes, nuclear fusion, physisorption

Procedia PDF Downloads 181

Authors: Sahila Chopra, Hemdeep, Arshdeep Kaur, Raj K. Gupta

Abstract:

In recent times, we noticed an interesting and important role of non-coplanar degree-of-freedom (Φ = 00) in heavy ion reactions. Using the dynamical cluster-decay model (DCM) with Φ degree-of-freedom included, we have studied three compound systems 246Bk∗, 164Yb∗ and 105Ag∗. Here, within the DCM with pocket formula for nuclear proximity potential, we look for the effects of including compact, non-coplanar configurations (Φc = 00) on the non-compound nucleus (nCN) contribution in total fusion cross section σfus. For 246Bk∗, formed in 11B+235U and 14N+232Th reaction channels, the DCM with coplanar nuclei (Φc = 00) shows an nCN contribution for 11B+235U channel, but none for 14N+232Th channel, which on including Φ gives both reaction channels as pure compound nucleus decays. In the case of 164Yb∗, formed in 64Ni+100Mo, the small nCN effects for Φ=00 are reduced to almost zero for Φ = 00. Interestingly, however, 105Ag∗ for Φ = 00 shows a small nCN contribution, which gets strongly enhanced for Φ = 00, such that the characteristic property of PCN presents a change of behaviour, like that of a strongly fissioning superheavy element to a weakly fissioning nucleus; note that 105Ag∗ is a weakly fissioning nucleus and Psurv behaves like one for a weakly fissioning nucleus for both Φ = 00 and Φ = 00. Apparently, Φ is presenting itself like a good degree-of-freedom in the DCM.

Keywords: dynamical cluster-decay model, fusion cross sections, non-compound nucleus effects, non-coplanarity

Procedia PDF Downloads 303

Authors: Hiba Naccache, Rima Hleiss

Abstract:

Additive manufacturing AM or 3D printing is one of the pillars of Industry 4.0. Compared to traditional manufacturing, AM provides a prototype before production in order to optimize the design and avoid the stock market and uses strictly necessary material which can be recyclable, for the benefit of leaning towards local production, saving money, time and resources. Different types of AM exist and it has a broad range of applications across several industries like aerospace, automotive, medicine, education and else. The Laser Powder Bed Fusion (LPBF) is a metal AM technique that uses a laser to liquefy metal powder, layer by layer, to build a three-dimensional (3D) object. In industry 4.0 and aligned with the numbers 9 (Industry, Innovation and Infrastructure) and 12 (Responsible Production and Consumption) of the Sustainable Development Goals of the UNESCO 2030 Agenda, the AM’s manufacturers committed to minimizing the environmental impact by being sustainable in every production. The LPBF has several environmental advantages, like reduced waste production, lower energy consumption, and greater flexibility in creating components with lightweight and complex geometries. However, LPBF also have environmental drawbacks, like energy consumption, gas consumption and emissions. It is critical to recognize the environmental impacts of LPBF in order to mitigate them. To increase awareness and promote sustainable practices regarding LPBF, the researchers use the Elaboration Likelihood Model (ELM) theory where people from multiple universities in France and Qatar process information in two ways: peripherally and centrally. The peripheral campaigns use superficial cues to get attention, and the central campaigns provide clear and concise information. The authors created a seminar including a video showing LPBF production and a website with educational resources. The data is collected using questionnaire to test attitude about the public awareness before and after the seminar. The results reflected a great shift on the awareness toward LPBF and its impact on the environment. With no presence of similar research, to our best knowledge, this study will add to the literature on the sustainability of the LPBF production technique.

Keywords: additive manufacturing, laser powder bed fusion, elaboration likelihood model theory, sustainable development goals, education-awareness, France, Qatar, specific energy consumption, environmental impact, lightweight components

Procedia PDF Downloads 90

Authors: Karim Kheloufi, El Hachemi Amara

Abstract:

In the present study, a three-dimensional transient numerical model was developed to study the temperature field and cutting kerf shape during laser fusion cutting. The finite volume model has been constructed, based on the Navier–Stokes equations and energy conservation equation for the description of momentum and heat transport phenomena, and the Volume of Fluid (VOF) method for free surface tracking. The Fresnel absorption model is used to handle the absorption of the incident wave by the surface of the liquid metal and the enthalpy-porosity technique is employed to account for the latent heat during melting and solidification of the material. To model the physical phenomena occurring at the liquid film/gas interface, including momentum/heat transfer, a new approach is proposed which consists of treating friction force, pressure force applied by the gas jet and the heat absorbed by the cutting front surface as source terms incorporated into the governing equations. All these physics are coupled and solved simultaneously in Fluent CFD®. The main objective of using a transient phase change model in the current case is to simulate the dynamics and geometry of a growing laser-cutting generated kerf until it becomes fully developed. The model is used to investigate the effect of some process parameters on temperature fields and the formed kerf geometry.

Keywords: laser cutting, numerical simulation, heat transfer, fluid flow

Procedia PDF Downloads 340

Authors: Huawei Bai, Jianguo Yao, Fellow, IEEE

Abstract:

Atrial fibrillation (AF) is the most common form of heart arrhythmia and is closely associated with mortality and morbidity in heart failure, stroke, and coronary artery disease. The development of single spot optical sensors enables widespread photoplethysmography (PPG) screening, especially for AF, since it represents a more convenient and noninvasive approach. To our knowledge, most existing studies based on public and unbalanced datasets can barely handle the multiple noises sources in the real world and, also, lack interpretability. In this paper, we construct a large- scale PPG dataset using measurements collected from PPG wrist- watch devices worn by volunteers and propose an attention-based two-stream heterogeneous neural network (TSHNN). The first stream is a hybrid neural network consisting of a three-layer one-dimensional convolutional neural network (1D-CNN) and two-layer attention- based bidirectional long short-term memory (Bi-LSTM) network to learn representations from temporally sampled signals. The second stream extracts latent representations from the PPG time-frequency spectrogram using a five-layer CNN. The outputs from both streams are fed into a fusion layer for the outcome. Visualization of the attention weights learned demonstrates the effectiveness of the attention mechanism against noise. The experimental results show that the TSHNN outperforms all the competitive baseline approaches and with 98.09% accuracy, achieves state-of-the-art performance.

Keywords: PPG wearables, atrial fibrillation, feature fusion, attention mechanism, hyber network

Procedia PDF Downloads 122

Authors: Saliha Gachi, Mouloud Aissani, Fouad Boubenider

Abstract:

Friction Stir Welding (FSW) is a solid-state welding technique that can join material without melting the plates to be welded. In this work, we are interested to demonstrate the potentiality of FSW for joining the heat-treatable aluminum alloy 2024-T3 which is reputed as difficult to be welded by fusion techniques. Thereafter, the FSW joint is compared with another one obtained from a conventional fusion process Tungsten Inert Gas (TIG). FSW welds are made up using an FSW tool mounted on a milling machine. Single pass welding was applied to fabricated TIG joint. The comparison between the two processes has been made on the temperature evolution, mechanical and microstructure behavior. The microstructural examination revealed that FSW weld is composed of four zones: Base metal (BM), Heat affected zone (HAZ), Thermo-mechanical affected zone (THAZ) and the nugget zone (NZ). The NZ exhibits a recrystallized equiaxed refined grains that induce better mechanical properties and good ductility compared to TIG joint where the grains have a larger size in the welded region compared with the BM due to the elevated heat input. The microhardness results show that, in FSW weld, the THAZ contains the lowest microhardness values and increase in the NZ; however, in TIG process, the lowest values are localized on the NZ.

Keywords: friction stir welding, tungsten inert gaz, aluminum, microstructure

Procedia PDF Downloads 277

Authors: M. Kharrat, G. Moreau, Z. Aboura

Abstract:

The latest advances in the weaving industry, combined with increasingly sophisticated means of materials processing, have made it possible to produce complex 3D composite structures. Mainly used in aeronautics, composite materials with 3D architecture offer better mechanical properties than 2D reinforced composites. Nevertheless, these materials require a good understanding of their behavior. Because of the complexity of such materials, the damage mechanisms are multiple, and the scenario of their appearance and evolution depends on the nature of the exerted solicitations. The AE technique is a well-established tool for discriminating between the damage mechanisms. Suitable sensors are used during the mechanical test to monitor the structural health of the material. Relevant AE-features are then extracted from the recorded signals, followed by a data analysis using pattern recognition techniques. In order to better understand the damage scenarios of interlock composite materials, a multi-instrumentation was set-up in this work for tracking damage initiation and development, especially in the vicinity of the first significant damage, called macro-damage. The deployed instrumentation includes video-microscopy, Digital Image Correlation, Acoustic Emission (AE) and micro-tomography. In this study, a multi-variable AE data analysis approach was developed for the discrimination between the different signal classes representing the different emission sources during testing. An unsupervised classification technique was adopted to perform AE data clustering without a priori knowledge. The multi-instrumentation and the clustered data served to label the different signal families and to build a learning database. This latter is useful to construct a supervised classifier that can be used for automatic recognition of the AE signals. Several materials with different ingredients were tested under various solicitations in order to feed and enrich the learning database. The methodology presented in this work was useful to refine the damage threshold for the new generation materials. The damage mechanisms around this threshold were highlighted. The obtained signal classes were assigned to the different mechanisms. The isolation of a 'noise' class makes it possible to discriminate between the signals emitted by damages without resorting to spatial filtering or increasing the AE detection threshold. The approach was validated on different material configurations. For the same material and the same type of solicitation, the identified classes are reproducible and little disturbed. The supervised classifier constructed based on the learning database was able to predict the labels of the classified signals.

Keywords: acoustic emission, classifier, damage mechanisms, first damage threshold, interlock composite materials, pattern recognition

Procedia PDF Downloads 156

Authors: S. D. Zalepugin, A. E. Murzich, D. G. Satskevich, A. B. Palivanov

Abstract:

Introduction. The incidence of spinal injuries in patients under 18 years of age has increased significantly in recent years, which represents a significant economic, social and medical problem. The most common method of surgical stabilization of spinal fractures in pediatric patients is transpedicular posterior spinal fusion, which is widely used by spinal neurosurgeons in adult patients. Purpose of the study: This study evaluates the results of treatment of thoracolumbar spine lesions in children using the transpedicular screw fixation method. Materials and methods. From 2019 to 2024, 35 children with injuries to the thoracic and lumbar spine underwent surgical treatment using the transpedicular screw fixation method. Among the injured, girls prevailed (21 cases, 60%). The age of the victims ranged from 9 to 17 years. The main causes of damage were: catatrauma (19 cases), road accident (5 cases), sports injury (6 cases), and other reasons - 5 cases. In 5 cases, suicidal attempts occurred. Co-injury was observed in most cases (20 patients, or 57%), which is natural for high-energy injury. Vertebral-spinal injury with neurological disorders was observed in 13 patients, the disorders ranged from mild inferior (4 children) to moderate/severe paraparesis (5 patients) and inferior paraplegia (4 children). 6 children had pelvic organ dysfunction in the form of urinary and fecal retention or incontinence. All thirty-five patients, within a period of 1 to 57 days after the injury, underwent several surgical interventions from the posterior surgical access using a screw fixation method (posterior decompression + spinal fusion). In 12 cases, it was necessary to perform the second stage of surgical treatment - anterior decompression of the spinal cord or its roots. Verticalization of patients was carried out within 1 to 5 days after surgery. Results. In all patients, the nearest, up to 1 year, results were evaluated. In children operated in 2019-2021, the results were studied in terms of 3 to 5 years. The procedures used, clinical results and the quality of the fixative installation were assessed. All patients managed to achieve positive results. The use of internal fixation made it possible to carry out early verticalization of children, eliminate pain syndrome and achieve a regression of neurological disorders in most patients (especially in cases when the operation was performed early after injury - from 1 to 3 days). Within the first month, the ability to self-care was fully restored. Bone fusion was observed within 6-12 months after surgery. There were no complications after surgery. The analysis of postoperative radiographs, CT and MRI images revealed the correct standing of the screws in all cases. Conclusion. The posterior spinal fusion using the new method of screw fixation in pediatric patients allows to achieve durable stabilization of damage, begins early rehabilitation of patients and reduces the duration of hospital treatment by 2-3 times. Thus, we recommend the use of a transpedicular fixator in children as a reliable, technically feasible method for restoring spinal stability with a low risk of intra- and postoperative complications.

Keywords: pediatric patients, spinal injuries, transpedicular stabilization, operative treatment

Procedia PDF Downloads 12

Authors: Areej Salaymeh, Loren Schwiebert, Stephen Remias, Jonathan Waddell

Abstract:

Extracting information from new data sources has emerged as a crucial task in many traffic planning processes, such as identifying traffic patterns, route planning, traffic forecasting, and locating infrastructure improvements. Given the advanced technologies used to collect Global Positioning System (GPS) data from dedicated GPS devices, GPS equipped phones, and navigation tools, intelligent data analysis methodologies are necessary to mine this raw data. In this research, an automatic detection framework is proposed to help identify and classify the locations of stopped GPS waypoints into two main categories: signalized intersections or highway congestion. The Delaunay triangulation is used to perform this assessment in the clustering phase. While most of the existing clustering algorithms need assumptions about the data distribution, the effectiveness of the Delaunay triangulation relies on triangulating geographical data points without such assumptions. Our proposed method starts by cleaning noise from the data and normalizing it. Next, the framework will identify stoppage points by calculating the traveled distance. The last step is to use clustering to form groups of waypoints for signalized traffic and highway congestion. Next, a binary classifier was applied to find distinguish highway congestion from signalized stop points. The binary classifier uses the length of the cluster to find congestion. The proposed framework shows high accuracy for identifying the stop positions and congestion points in around 99.2% of trials. We show that it is possible, using limited GPS data, to distinguish with high accuracy.

Keywords: Delaunay triangulation, clustering, intelligent transportation systems, GPS data

Procedia PDF Downloads 276

Authors: Gustavo Menezes De Souza Melo, Arnaud Heitz, Johannes Henrich Schleifenbaum

Abstract:

Additive manufacturing is a growing market that is taking over in many industries as it offers numerous advantages like new design possibilities, weight-saving solutions, ease of manufacture, and simplification of assemblies. These are all unquestionable technical or financial assets. As to the environmental aspect, additive manufacturing is often discussed whether it is the best solution to decarbonize our industries or if conventional manufacturing remains cleaner. This work presents a life cycle assessment (LCA) comparison based on the technological case of a motorbike swing-arm. We compare the original equipment manufacturer part made with conventional manufacturing (CM) methods to an additive manufacturing (AM) version printed using the laser powder bed fusion process. The AM version has been modified and optimized to achieve better dynamic performance without any regard to weight saving. Lightweight not being a priority in the creation of the 3D printed part brings us a unique perspective in this study. To achieve the LCA, we are using the open-source life cycle, and sustainability software OpenLCA combined with the ReCiPe 2016 at midpoint and endpoint level method. This allows the calculation and the presentation of the results through indicators such as global warming, water use, resource scarcity, etc. The results are then showing the relative impact of the AM version compared to the CM one and give us a key to understand and answer questions about the environmental sustainability of additive manufacturing.

Keywords: additive manufacturing, environmental impact, life cycle assessment, laser powder bed fusion

Procedia PDF Downloads 263

Authors: A: Annis Fathima, V. Vaidehi, S. Ajitha

Abstract:

Face recognition system finds many applications in surveillance and human computer interaction systems. As the applications using face recognition systems are of much importance and demand more accuracy, more robustness in the face recognition system is expected with less computation time. In this paper, a hybrid approach for face recognition combining Gabor Wavelet and Linear Discriminant Analysis (HGWLDA) is proposed. The normalized input grayscale image is approximated and reduced in dimension to lower the processing overhead for Gabor filters. This image is convolved with bank of Gabor filters with varying scales and orientations. LDA, a subspace analysis techniques are used to reduce the intra-class space and maximize the inter-class space. The techniques used are 2-dimensional Linear Discriminant Analysis (2D-LDA), 2-dimensional bidirectional LDA ((2D)2LDA), Weighted 2-dimensional bidirectional Linear Discriminant Analysis (Wt (2D)2 LDA). LDA reduces the feature dimension by extracting the features with greater variance. k-Nearest Neighbour (k-NN) classifier is used to classify and recognize the test image by comparing its feature with each of the training set features. The HGWLDA approach is robust against illumination conditions as the Gabor features are illumination invariant. This approach also aims at a better recognition rate using less number of features for varying expressions. The performance of the proposed HGWLDA approaches is evaluated using AT&T database, MIT-India face database and faces94 database. It is found that the proposed HGWLDA approach provides better results than the existing Gabor approach.

Keywords: face recognition, Gabor wavelet, LDA, k-NN classifier

Procedia PDF Downloads 467

Authors: Shalini Rankawat, Mansi Rankawat, Rahul Dubey, Mazad Zaveri

Abstract:

Physiological signals such as electrocardiogram (ECG) and arterial blood pressure (ABP) in the intensive care unit (ICU) are often seriously corrupted by noise, artifacts, and missing data, which lead to errors in the estimation of heart rate (HR) and incidences of false alarm from ICU monitors. Clinical support in ICU requires most reliable heart rate estimation. Cardiac activity, because of its relatively high electrical energy, may introduce artifacts in Electroencephalogram (EEG), Electrooculogram (EOG), and Electromyogram (EMG) recordings. This paper presents a robust heart rate estimation method by detection of R-peaks of ECG artifacts in EEG, EMG & EOG signals, using energy-based function and a novel Signal Quality Index (SQI) assessment technique. SQIs of physiological signals (EEG, EMG, & EOG) were obtained by correlation of nonlinear energy operator (teager energy) of these signals with either ECG or ABP signal. HR is estimated from ECG, ABP, EEG, EMG, and EOG signals from separate Kalman filter based upon individual SQIs. Data fusion of each HR estimate was then performed by weighing each estimate by the Kalman filters’ SQI modified innovations. The fused signal HR estimate is more accurate and robust than any of the individual HR estimate. This method was evaluated on MIMIC II data base of PhysioNet from bedside monitors of ICU patients. The method provides an accurate HR estimate even in the presence of noise and artifacts.

Keywords: ECG, ABP, EEG, EMG, EOG, ECG artifacts, Teager-Kaiser energy, heart rate, signal quality index, Kalman filter, data fusion

Procedia PDF Downloads 696

Authors: B. Elshafei, X. Mao

Abstract:

The demand for renewable energy is significantly increasing, major investments are being supplied to the wind power generation industry as a leading source of clean energy. The wind energy sector is entirely dependable and driven by the prediction of wind speed, which by the nature of wind is very stochastic and widely random. This s0tudy employs deep multi-fidelity Gaussian process regression, used to predict wind speeds for medium term time horizons. Data of the RUNE experiment in the west coast of Denmark were provided by the Technical University of Denmark, which represent the wind speed across the study area from the period between December 2015 and March 2016. The study aims to investigate the effect of pre-processing the data by denoising the signal using empirical wavelet transform (EWT) and engaging the vector components of wind speed to increase the number of input data layers for data fusion using deep multi-fidelity Gaussian process regression (GPR). The outcomes were compared using root mean square error (RMSE) and the results demonstrated a significant increase in the accuracy of predictions which demonstrated that using vector components of the wind speed as additional predictors exhibits more accurate predictions than strategies that ignore them, reflecting the importance of the inclusion of all sub data and pre-processing signals for wind speed forecasting models.

Keywords: data fusion, Gaussian process regression, signal denoise, temporal extrapolation

Procedia PDF Downloads 136

Authors: Bliss Singhal

Abstract:

Machine learning (ML) is a branch of Artificial Intelligence (AI) where computers analyze data and find patterns in the data. The study focuses on the detection of metastatic cancer using ML. Metastatic cancer is the stage where cancer has spread to other parts of the body and is the cause of approximately 90% of cancer-related deaths. Normally, pathologists spend hours each day to manually classifying whether tumors are benign or malignant. This tedious task contributes to mislabeling metastasis being over 60% of the time and emphasizes the importance of being aware of human error and other inefficiencies. ML is a good candidate to improve the correct identification of metastatic cancer, saving thousands of lives and can also improve the speed and efficiency of the process, thereby taking fewer resources and time. So far, the deep learning methodology of AI has been used in research to detect cancer. This study is a novel approach to determining the potential of using preprocessing algorithms combined with classification algorithms in detecting metastatic cancer. The study used two preprocessing algorithms: principal component analysis (PCA) and the genetic algorithm, to reduce the dimensionality of the dataset and then used three classification algorithms: logistic regression, decision tree classifier, and k-nearest neighbors to detect metastatic cancer in the pathology scans. The highest accuracy of 71.14% was produced by the ML pipeline comprising of PCA, the genetic algorithm, and the k-nearest neighbor algorithm, suggesting that preprocessing and classification algorithms have great potential for detecting metastatic cancer.

Keywords: breast cancer, principal component analysis, genetic algorithm, k-nearest neighbors, decision tree classifier, logistic regression

Procedia PDF Downloads 83