Search results for: genetic algorithms

Authors: Hervice Roméo Fogno Fotsoa, Germaine Djuidje Kenmoe, Claude Vidal Aloyem Kazé

Abstract:

One of the main applications of machine learning is the prediction of time series. But a more accurate prediction requires a more optimal model of machine learning. Several optimization techniques have been developed, but without considering the input variables disposition of the system. Thus, this work aims to present a new machine learning architecture optimization technique based on their optimal input variables disposition. The validations are done on the prediction of wind time series, using data collected in Cameroon. The number of possible dispositions with four input variables is determined, i.e., twenty-four. Each of the dispositions is used to perform the prediction, with the main criteria being the training and prediction performances. The results obtained from a static architecture and a dynamic architecture of neural networks have shown that these performances are a function of the input variable's disposition, and this is in a different way from the architectures. This analysis revealed that it is necessary to take into account the input variable's disposition for the development of a more optimal neural network model. Thus, a new neural network training algorithm is proposed by introducing the search for the optimal input variables disposition in the traditional back-propagation algorithm. The results of the application of this new optimization approach on the two single neural network architectures are compared with the previously obtained results step by step. Moreover, this proposed approach is validated in a collaborative optimization method with a single objective optimization technique, i.e., genetic algorithm back-propagation neural networks. From these comparisons, it is concluded that each proposed model outperforms its traditional model in terms of training and prediction performance of time series. Thus the proposed optimization approach can be useful in improving the accuracy of time series forecasts. This proves that the proposed optimization approach can be useful in improving the accuracy of time series prediction based on machine learning.

Keywords: input variable disposition, machine learning, optimization, performance, time series prediction

Procedia PDF Downloads 99

Authors: Hamidreza Hoshyarmanesh, Hosein Madieh, Sanju Lama, Yaser Maddahi, Garnette R. Sutherland, Kourosh Zareinia

Abstract:

This paper illustrates the concept of an algorithm to register specified markers on the neuroArm surgical manipulators, an image-guided MR-compatible tele-operated robot for microsurgery and stereotaxy. Two range-finding algorithms, namely time-of-flight and phase-shift, are evaluated for registration and supervisory control. The time-of-flight approach is implemented in a semi-field experiment to determine the precise position of a tiny retro-reflective moving object. The moving object simulates a surgical tool tip. The tool is a target that would be connected to the neuroArm end-effector during surgery inside the magnet bore of the MR imaging system. In order to apply flight approach, a 905-nm pulsed laser diode and an avalanche photodiode are utilized as the transmitter and receiver, respectively. For the experiment, a high frequency time to digital converter was designed using a field-programmable gate arrays. In the phase-shift approach, a continuous green laser beam with a wavelength of 530 nm was used as the transmitter. Results showed that a positioning error of 0.1 mm occurred when the scanner-target point distance was set in the range of 2.5 to 3 meters. The effectiveness of this non-contact approach exhibited that the method could be employed as an alternative for conventional mechanical registration arm. Furthermore, the approach is not limited by physical contact and extension of joint angles.

Keywords: 3D laser scanner, intraoperative MR imaging, neuroArm, real time registration, robot-assisted surgery, supervisory control

Procedia PDF Downloads 279

Authors: Abdolghani Ebrahimi, Diego Klabjan, Chenxi Ge, Daniela Ladner, Parker Stride

Abstract:

In this work, we use machine learning and novel data analysis techniques to predict the one-year mortality of cirrhotic patients. Data from 2,322 patients with liver cirrhosis are collected at a single medical center. Different machine learning models are applied to predict one-year mortality. A comprehensive feature space including demographic information, comorbidity, clinical procedure and laboratory tests is being analyzed. A temporal pattern mining technic called Frequent Subgraph Mining (FSM) is being used. Model for End-stage liver disease (MELD) prediction of mortality is used as a comparator. All of our models statistically significantly outperform the MELD-score model and show an average 10% improvement of the area under the curve (AUC). The FSM technic itself does not improve the model significantly, but FSM, together with a machine learning technique called an ensemble, further improves the model performance. With the abundance of data available in healthcare through electronic health records (EHR), existing predictive models can be refined to identify and treat patients at risk for higher mortality. However, due to the sparsity of the temporal information needed by FSM, the FSM model does not yield significant improvements. To the best of our knowledge, this is the first work to apply modern machine learning algorithms and data analysis methods on predicting one-year mortality of cirrhotic patients and builds a model that predicts one-year mortality significantly more accurate than the MELD score. We have also tested the potential of FSM and provided a new perspective of the importance of clinical features.

Keywords: machine learning, liver cirrhosis, subgraph mining, supervised learning

Procedia PDF Downloads 132

Authors: Blessing Ojeme, Frederick Quinn, Russell Karls, Shannon Quinn

Abstract:

The detection and segmentation of mitochondria from fluorescence microscopy are crucial for understanding the complex structure of the nervous system. However, the constant fission and fusion of mitochondria and image distortion in the background make the task of detection and segmentation challenging. In the literature, a number of open-source software tools and artificial intelligence (AI) methods have been described for analyzing mitochondrial images, achieving remarkable classification and quantitation results. However, the availability of combined expertise in the medical field and AI required to utilize these tools poses a challenge to its full adoption and use in clinical settings. Motivated by the advantages of automated methods in terms of good performance, minimum detection time, ease of implementation, and cross-platform compatibility, this study proposes a fully automated framework for the detection and segmentation of mitochondria using both image shape information and descriptive statistics. Using the low-cost, open-source python and openCV library, the algorithms are implemented in three stages: pre-processing, image binarization, and coarse-to-fine segmentation. The proposed model is validated using the mitochondrial fluorescence dataset. Ground truth labels generated using a Lab kit were also used to evaluate the performance of our detection and segmentation model. The study produces good detection and segmentation results and reports the challenges encountered during the image analysis of mitochondrial morphology from the fluorescence mitochondrial dataset. A discussion on the methods and future perspectives of fully automated frameworks conclude the paper.

Keywords: 2D, binarization, CLAHE, detection, fluorescence microscopy, mitochondria, segmentation

Procedia PDF Downloads 354

Authors: Saqib Ali

Abstract:

Sources are classified into two depending upon the factor of reviving. These sources, which cannot be revived into their original shape once they are consumed, are considered as nonrenewable energy resources, i.e., (coal, fuel) Moreover, those energy resources which are revivable to the original condition even after being consumed are known as renewable energy resources, i.e., (wind, solar, hydel) Renewable energy is a cost-effective way to generate clean and green electrical energy Now a day’s majority of the countries are paying heed to energy generation from RES Pakistan is mostly relying on conventional energy resources which are mostly nonrenewable in nature coal, fuel is one of the major resources, and with the advent of time their prices are increasing on the other hand RES have great potential in the country with the deployment of RES greater reliability and an effective power system can be obtained In this thesis, a similar concept is being used and a hybrid power system is proposed which is composed of intermixing of renewable and nonrenewable sources The Source side is composed of solar, wind, fuel cells which will be used in an optimal manner to serve load The goal is to provide an economical, reliable, uninterruptable power supply. This is achieved by optimal controller (PI, PD, PID, FOPID) Optimization techniques are applied to the controllers to achieve the desired results. Advanced algorithms (Particle swarm optimization, Flower Pollination Algorithm) will be used to extract the desired output from the controller Detailed comparison in the form of tables and results will be provided, which will highlight the efficiency of the proposed system.

Keywords: distributed generation, demand-side management, hybrid power system, micro grid, renewable energy resources, supply-side management

Procedia PDF Downloads 94

Authors: Haifeng Zhou, Tsungyang Liow, Xiaoguang Tu, Eujin Lim, Chao Li, Junfeng Song, Xianshu Luo, Ying Huang, Lianxi Jia, Lianwee Luo, Qing Fang, Mingbin Yu, Guoqiang Lo

Abstract:

With the development of technology, countries gradually allocated more and more frequency spectrums for civilization and commercial usage, especially those high radio frequency bands indicating high information capacity. The field effect becomes more and more prominent in microwave components as frequency increases, which invalidates the transmission line theory and complicate the design of microwave components. Here a modeling approach based on numerical search algorithm is proposed to design various building blocks for microwave circuits to avoid complicated impedance matching and equivalent electrical circuit approximation. Concretely, a microwave component is discretized to a set of segments along the microwave propagation path. Each of the segment is initialized with random dimensions, which constructs a multiple-dimension parameter space. Then numerical searching algorithms (e.g. Pattern search algorithm) are used to find out the ideal geometrical parameters. The optimal parameter set is achieved by evaluating the fitness of S parameters after a number of iterations. We had adopted this approach in our current projects and designed many microwave components including sharp bends, T-branches, Y-branches, microstrip-to-stripline converters and etc. For example, a stripline 90° bend was designed in 2.54 mm x 2.54 mm space for dual-band operation (Ka band and Ku band) with < 0.18 dB insertion loss and < -55 dB reflection. We expect that this approach can enrich the tool kits for microwave designers.

Keywords: microwave component, microstrip and stripline, bend, power division, the numerical search algorithm.

Procedia PDF Downloads 377

Authors: Andrea Treviño Gavito, Diego Klabjan, Sanjiv J. Shah

Abstract:

Echocardiograms serve as pivotal resources for clinicians in diagnosing cardiac conditions, offering non-invasive insights into a heart’s structure and function. When echocardiographic studies are conducted, no standardized labeling of the acquired views is performed. Employing machine learning algorithms for automated echocardiogram view detection has emerged as a promising solution to enhance efficiency in echocardiogram use for diagnosis. However, existing approaches predominantly rely on supervised learning, necessitating labor-intensive expert labeling. In this paper, we introduce a fully unsupervised echocardiographic view detection framework that leverages convolutional autoencoders to obtain lower dimensional representations and the K-means algorithm for clustering them into view-related groups. Our approach focuses on discriminative patches from echocardiographic frames. Additionally, we propose a trainable inverse average layer to optimize decoding of average operations. By integrating both public and proprietary datasets, we obtain a marked improvement in model performance when compared to utilizing a proprietary dataset alone. Our experiments show boosts of 15.5% in accuracy and 9.0% in the F-1 score for frame-based clustering, and 25.9% in accuracy and 19.8% in the F-1 score for view-based clustering. Our research highlights the potential of unsupervised learning methodologies and the utilization of open-sourced data in addressing the complexities of echocardiogram interpretation, paving the way for more accurate and efficient cardiac diagnoses.

Keywords: artificial intelligence, echocardiographic view detection, echocardiography, machine learning, self-supervised representation learning, unsupervised learning

Procedia PDF Downloads 21

Authors: Karen L. Middlemiss, Denham G. Cook, Peter Jaksons, Alistair Jerrett, William Davison

Abstract:

Lateralisation of cognitive function is a common phenomenon found throughout the animal kingdom. Strong biases in functional behaviours have evolved from asymmetrical brain hemispheres which differ in structure and/or cognitive function. In fish, lateralisation is involved in visually mediated behaviours such as schooling, predator avoidance, and foraging, and is considered to have a direct impact on species fitness. Currently, there is very little literature on the role of lateralisation in fish schools. The yellow-eyed mullet (Aldrichetta forsteri), is an estuarine and coastal species found commonly throughout temperate regions of Australia and New Zealand. This study sought to quantify visually mediated behaviours in yellow-eyed mullet to identify the significance of lateralisation, and the factors which influence functional behaviours in schooling fish. Our approach to study design was to conduct a series of tank based experiments investigating; a) individual and population level lateralisation, b) schooling behaviour, and d) optic lobe anatomy. Yellow-eyed mullet showed individual variation in direction and strength of lateralisation in juveniles, and trait specific spatial positioning within the school was evidenced in strongly lateralised fish. In combination with observed differences in schooling behaviour, the possibility of ontogenetic plasticity in both behavioural lateralisation and optic lobe morphology in adults is suggested. These findings highlight the need for research into the genetic and environmental factors (epigenetics) which drive functional behaviours such as schooling, feeding and aggression. Improved knowledge on collective behaviour could have significant benefits to captive rearing programmes through improved culture techniques and will add to the limited body of knowledge on the complex ecophysiological interactions present in our inshore fisheries.

Keywords: cerebral asymmetry, fisheries, schooling, visual bias

Procedia PDF Downloads 209

Authors: Sheng Yu Chen, Shi-Heng Wang

Abstract:

Aim: Based on human, animal experiments, and genetic studies, cysteinyl leukotrienes, LTC4, LTD4, and LTE4, are inflammatory substances that are metabolized by 5-lipooxygenase from arachidonic acid, and these substances trigger asthma. In addition, the synthetic pathway of cysteinyl leukotriene is relevant to the increase in cardiovascular diseases such as myocardial ischemia and stroke. Given the situation, we aim to investigate whether cysteinyl leukotrienes receptor antagonist (LTRA), montelukast which cures those who have asthma has potential protective effects on cardiovascular diseases. Method: We conducted a cohort study, and enrolled participants which are newly diagnosed with asthma (ICD-9 CM code 493. X) between 2002 to 2011. The data source is from Taiwan National Health Insurance Research Database Patients with a previous history of myocardial infarction or ischemic stroke were excluded. Among the remaining participants, every montelukast user was matched with two randomly non-users by sex, and age. The incident cardiovascular diseases, including myocardial infarction and ischemic stroke, were regarded as outcomes. We followed the participants until outcomes come first or the end of the following period. To explore the protective effect of montelukast on the risk of cardiovascular disease, we use multivariable Cox regression to estimate the hazard ratio with adjustment for potential confounding factors. Result: There are 55876 newly diagnosed asthma patients who had at least one claim of inpatient admission or at least three claims of outpatient records. We enrolled 5350 montelukast users and 10700 non-users in this cohort study. The following mean (±SD) time of the Montelukast group is 5 (±2.19 )years, and the non-users group is 6.2 5.47 (± 2.641) years. By using multivariable Cox regression, our analysis indicated that the risk of incident cardiovascular diseases between montelukast users (n=43, 0.8%) and non-users (n=111, 1.04%) is approximately equal. [adjusted hazard ratio 0.992; P-value:0.9643] Conclusion: In this population-based study, we found that the use of montelukast is not associated with a decrease in incident MI or IS.

Keywords: asthma, inflammation, montelukast, insurance research database, cardiovascular diseases

Procedia PDF Downloads 78

Authors: Xiaowei Zhang, Min Xu, Saeid Habibi, Fengjun Yan, Ryan Ahmed

Abstract:

Recently, Electric Vehicles (EVs) have received extensive consideration since they offer a more sustainable and greener transportation alternative compared to fossil-fuel propelled vehicles. Lithium-Ion (Li-ion) batteries are increasingly being deployed in EVs because of their high energy density, high cell-level voltage, and low rate of self-discharge. Since Li-ion batteries represent the most expensive component in the EV powertrain, accurate monitoring and control strategies must be executed to ensure their prolonged lifespan. The Battery Management System (BMS) has to accurately estimate parameters such as the battery State-of-Charge (SOC), State-of-Health (SOH), and Remaining Useful Life (RUL). In order for the BMS to estimate these parameters, an accurate and control-oriented battery model has to work collaboratively with a robust state and parameter estimation strategy. Since battery physical parameters, such as the internal resistance and diffusion coefficient change depending on the battery state-of-life (SOL), the BMS has to be adaptive to accommodate for this change. In this paper, an extensive battery aging study has been conducted over 12-months period on 5.4 Ah, 3.7 V Lithium polymer cells. Instead of using fixed charging/discharging aging cycles at fixed C-rate, a set of real-world driving scenarios have been used to age the cells. The test has been interrupted every 5% capacity degradation by a set of reference performance tests to assess the battery degradation and track model parameters. As battery ages, the combined model parameters are optimized and tracked in an offline mode over the entire batteries lifespan. Based on the optimized model, a state and parameter estimation strategy based on the Extended Kalman Filter (EKF) and the relatively new Smooth Variable Structure Filter (SVSF) have been applied to estimate the SOC at various states of life.

Keywords: lithium-ion batteries, genetic algorithm optimization, battery aging test, parameter identification

Procedia PDF Downloads 262

Authors: Clara Franch de la Cal, Christopher J Morris, Michael McArthur

Abstract:

Cystic fibrosis (CF) is an autosomal recessive genetic disorder characterized by abnormal transport of chloride and sodium across the lung epithelium, leading to thick and viscous secretions. Within which CF patients suffer from repeated bacterial pulmonary infections, with Pseudomonas aeru-ginosa (PA) eliciting the greatest inflammatory response, causing an irreversible loss of lung func-tion that determines morbidity and mortality. The cell wall of PA is a permeability barrier to many antibacterials and the rise of Mutli-Drug Resistant strains (MDR) is eroding the efficacy of the few remaining clinical options. In addition when PA infection becomes established it forms an antibi-otic-resistant biofilm, embedded in which are slow growing cells that are refractive to drug treat-ment. Making the development of new antibacterials a major challenge. This work describes the development of new type of nanoparticulate oligonucleotide antibacterial capable of tackling PA infections, including MDR strains. It is being developed to both block growth and prevent biofilm formation. These oligonucleotide therapeutics, Transcription Factor Decoys (TFD), act on novel genomic targets by capturing key regulatory proteins to block essential bacterial genes and defeat infection. They have been successfully transfected into a wide range of pathogenic bacteria, both in vitro and in vivo, using a proprietary delivery technology. The surfactant used self-assembles with TFD to form a nanoparticle stable in biological fluids, which protects the TFD from degradation and preferentially transfects prokaryotic membranes. Key challenges are to adapt the nanoparticle so it is active against PA in the context of biofilms and to formulate it for administration by inhalation. This would allow the drug to be delivered to the respiratory tract, thereby achieving drug concentrations sufficient to eradicate the pathogenic organisms at the site of infection.

Keywords: antibacterials, transcriptional factor decoys (TFDs), pseudomonas aeruginosa

Procedia PDF Downloads 281

Authors: S. S. Adamu, H. S. Muhammad, D. S. Shuaibu

Abstract:

Poor power quality in electrical power systems can lead to medical equipment at healthcare centres to malfunction and present wrong medical diagnosis. Equipment such as X-rays, computerized axial tomography, etc. can pollute the system due to their high level of harmonics production, which may cause a number of undesirable effects like heating, equipment damages and electromagnetic interferences. The conventional approach of mitigation uses passive inductor/capacitor (LC) filters, which has some drawbacks such as, large sizes, resonance problems and fixed compensation behaviours. The current trends of solutions generally employ active power filters using suitable control algorithms. This work focuses on assessing the level of Total Harmonic Distortion (THD) on medical facilities and various ways of mitigation, using radiology unit of an existing hospital as a case study. The measurement of the harmonics is conducted with a power quality analyzer at the point of common coupling (PCC). The levels of measured THD are found to be higher than the IEEE 519-1992 standard limits. The system is then modelled as a harmonic current source using MATLAB/SIMULINK. To mitigate the unwanted harmonic currents a shunt active filter is developed using synchronous detection algorithm to extract the fundamental component of the source currents. Fuzzy logic controller is then developed to control the filter. The THD without the active power filter are validated using the measured values. The THD with the developed filter show that the harmonics are now within the recommended limits.

Keywords: power quality, total harmonics distortion, shunt active filters, fuzzy logic

Procedia PDF Downloads 474

Authors: Ali Al Orf, Khawaja Bilal Waheed

Abstract:

Background and objective: Joubert syndrome (JS) is a rare, autosomal-recessive condition. Early recognition is important for management and counseling. Magnetic resonance imaging (MRI) can help in diagnosis. Therefore, we sought to evaluate clinical presentation and MRI findings in Joubert syndrome and related disorders. Method: A retrospective review of genetically proven cases of Joubert syndromes and related disorders was reviewed for their clinical presentation, demographic information, and magnetic resonance imaging findings in a period of the last 10 years. Two radiologists documented magnetic resonance imaging (MRI) findings. The presence of hypoplasia of the cerebellar vermis with hypoplasia of the superior cerebellar peduncle resembling the “Molar Tooth Sign” in the mid-brain was documented. Genetic testing results were collected to label genes linked to the diagnoses. Results: Out of 12 genetically proven JS cases, most were females (9/12), and nearly all presented with hypotonia, ataxia, developmental delay, intellectual impairment, and speech disorders. 5/12 children presented at age of 1 or below. The molar tooth sign was seen in 10/12 cases. Two cases were associated with other brain findings. Most of the cases were found associated with consanguineous marriage Conclusion and discussion: The molar tooth sign is a frequent and reliable sign of JS and related disorders. Genes related to defective cilia result in malfunctioning in the retina, renal tubule, and neural cell migration, thus producing heterogeneous syndrome complexes known as “ciliopathies.” Other ciliopathies like Senior-Loken syndrome, Bardet Biedl syndrome, and isolated nephronophthisis must be considered as the differential diagnosis of JS. The main imaging findings are the partial or complete absence of the cerebellar vermis, hypoplastic cerebellar peduncles (giving MTS), and (bat-wing appearance) fourth ventricular deformity. LimitationsSingle-center, small sample size, and retrospective nature of the study were a few of the study limitations.

Keywords: Joubart syndrome, magnetic resonance imaging, molar tooth sign, hypotonia

Procedia PDF Downloads 89

Authors: Fei Sun, Meilan Xu, Jianghui Zhu, Maria Stefanie Dwiyanti, Cheolwoo Park, Fanjiang Kong, Baohui Liu, Tetsuya Yamada, Jun Abe

Abstract:

Reduced or lack of sensitivity to long daylengths is a key character for soybean, a short-day crop, to adapt to higher latitudinal environments. However, the photoperiod-insensitivity often results in a reduction of the duration of vegetative growth and final yield. To overcome this limitation, a photoperiod insensitive line (RIL16) was developed in this study that delayed flowering from the recombinant inbred population derived from a cross between a photoperiod-insensitive cultivar AGS292 and a late-flowering Thai cultivar K3. Expression analyses under SD and LD conditions revealed that the expression levels of FLOWERING LOCUS T (FT) orthologues, FT2a and FT5a, were lowered in RIL16 relative to AGS292, although the expression of E1, a soybean-specific suppressor for FTs, was inhibited in both conditions. A soybean orthologue of TARGET OF EAT1 (TOE1), another suppressor of FT, showed an upregulated expression in RIL16, which appeared to reflect a lower expression of miR172a. Our data suggest that the delayed flowering of RIL16 most likely is controlled by genes involved in an age-dependent pathway in flowering. The QTL analysis based on 1,125 SNPs obtained from Restriction Site Associated DNA Sequencing revealed two major QTLs for flowering dates in Chromosome 16 and two minor QTLs in Chromosome 4, all of which accounted for 55% and 48% of the whole variations observed in natural day length and artificially-induced long day length conditions, respectively. The intervals of the major QTLs harbored FT2a and FT5a, respectively, on the basis of annotated genes in the Williams 82 reference genome. Sequencing analysis further revealed a nonsynonymous mutation in FT2a and an SNP in the 3′ UTR region of FT5a. A further study may elucidate a detailed mechanism underlying the QTL for late flowering. The alleles from K3 at the two QTLs can be used singly or in combination to retain an appropriate duration of vegetative growth to maximize the final yield of photoperiod-insensitive soybeans.

Keywords: FT genes, miR72a, photoperiod-insensitive, soybean flowering

Procedia PDF Downloads 212

Authors: Yanhua Zhao, Chenli Rao, Dongdong Li, Chuanmin Tao

Abstract:

The Chinese Centers for Disease Control and Prevention (CCDC) issued a new laboratory-based algorithm for HIV diagnosis on April 2016, which initially screens with a combination HIV-1/HIV-2 antigen/antibody fourth-generation immunoassay (IA) followed, when reactive, an HIV-1/HIV-2 undifferentiated antibody IA in duplicate. Reactive specimens with concordant results undergo supplemental tests with western blots, or HIV-1 nucleic acid tests (NATs) and non-reactive specimens with discordant results receive HIV-1 NATs or p24 antigen tests or 2-4 weeks follow-up tests. However, little data evaluating the application of the new algorithm have been reported to date. The study was to evaluate the performance of new laboratory-based HIV diagnostic algorithm in an inpatient population of Southwest China over the initial 6 months by compared with the old algorithm. Plasma specimens collected from inpatients from May 1, 2016, to October 31, 2016, are submitted to the laboratory for screening HIV infection performed by both the new HIV testing algorithm and the old version. The sensitivity and specificity of the algorithms and the difference of the categorized numbers of plasmas were calculated. Under the new algorithm for HIV diagnosis, 170 of the total 52 749 plasma specimens were confirmed as positively HIV-infected (0.32%). The sensitivity and specificity of the new algorithm were 100% (170/170) and 100% (52 579/52 579), respectively; while 167 HIV-1 positive specimens were identified by the old algorithm with sensitivity 98.24% (167/170) and 100% (52 579/52 579), respectively. Three acute HIV-1 infections (AHIs) and two early HIV-1 infections (EHIs) were identified by the new algorithm; the former was missed by old procedure. Compared with the old version, the new algorithm produced fewer WB-indeterminate results (2 vs. 16, p = 0.001), which led to fewer follow-up tests. Therefore, the new HIV testing algorithm is more sensitive for detecting acute HIV-1 infections with maintaining the ability to verify the established HIV-1 infections and can dramatically decrease the greater number of WB-indeterminate specimens.

Keywords: algorithm, diagnosis, HIV, laboratory

Procedia PDF Downloads 393

Authors: Ali Moradiamani, Samaneh Sadat Sajjadi, Mahdi Jalili

Abstract:

Power system analysis has been a major research topic in the generation and distribution sections, in both industry and academia, for a long time. Several load flow and fault analysis scenarios have been normally performed to study the performance of different parts of the grid in the context of, for example, voltage and frequency control. Software tools, such as PSCAD, PSSE, and PowerFactory DIgSILENT, have been developed to perform these analyses accurately. Distribution grid had been the passive part of the grid and had been known as the grid of consumers. However, a significant paradigm shift has happened with the emergence of Distributed Energy Resources (DERs) in the distribution level. It means that the concept of power system analysis needs to be extended to the distribution grid, especially considering self sufficient technologies such as microgrids. Compared to the generation and transmission levels, the distribution level includes significantly more generation/consumption nodes thanks to PV rooftop solar generation and battery energy storage systems. In addition, different consumption profile is expected from household residents resulting in a diverse set of scenarios. Emergence of electric vehicles will absolutely make the environment more complicated considering their charging (and possibly discharging) requirements. These complexities, as well as the large size of distribution grids, create challenges for the available power system analysis software. In this paper, we study the requirements of simulation tools in the distribution grid and how data-driven algorithms are required to increase the accuracy of the simulation results.

Keywords: smart grids, distributed energy resources, electric vehicles, battery storage systsms, simulation tools

Procedia PDF Downloads 98

Authors: Shahid Hussain Abro, Siamak Zohari, Lena H. M. Renström, Désirée S. Jansson, Faruk Otman, Karin Ullman, Claudia Baule

Abstract:

Infectious bronchitis is an acute, highly contagious respiratory, nephropathogenic and reproductive disease of poultry that is caused by infectious bronchitis virus (IBV). The present study used a large data set of structural gene sequences, including newly generated ones and sequences available in the GenBank database to further analyze the diversity and to identify selective pressures and recombination spots. There were some deletions or insertions in the analyzed regions in isolates of the Italy-02 and D274 genotypes. Whereas, there were no insertions or deletions observed in the isolates of the Massachusetts and 4/91 genotype. The hypervariable nucleotide sequence regions spanned positions 152–239, 554–582, 686–737 and 802–912 in the S1 sub-unit of the all analyzed genotypes. The nucleotide sequence data of the E gene showed that this gene was comparatively unstable and subjected to a high frequency of mutations. The M gene showed substitutions consistently distributed except for a region between nucleotide positions 250–680 that remained conserved. The lowest variation in the nucleotide sequences of ORF5a was observed in the isolates of the D274 genotype. While, ORF5b and N gene sequences showed highly conserved regions and were less subjected to variation. Genes ORF3a, ORF3b, M, ORF5a, ORF5b and N presented negative selective pressure among the analyzed isolates. However, some regions of the ORFs showed favorable selective pressure(s). The S1 and E proteins were subjected to a high rate of mutational substitutions and non-synonymous amino acids. Strong signals of recombination breakpoints and ending break point were observed in the S and N genes. Overall, the results of this study revealed that very likely the strong selective pressures in E, M and the high frequency of substitutions in the S gene can probably be considered the main determinants in the evolution of IBV.

Keywords: IBV, avian infectious bronchitis, structural genes, genotypes, genetic diversity

Procedia PDF Downloads 428

Authors: Radmila Maksimovic, Sonja Ketin, Rade Biocanin, Jelena Maksimovic

Abstract:

The abnormal conditions of life and work genetic factors often play a major role in incidence of diabetes-diabetes, heart disease and vascular disease, jaundice, and post traumatic stress. Trauma and post traumatic stress are most common in the displaced persons,and the focus of this paper is to shed light on this issue in former Yugoslavia, Yugoslavia and now in our country. This is caused by increased beta-cell sensitivity to viruses, the development of autoimmune antibodies against its own pancreascells, degenerative changes in cells that r esult in change of structure and insulin. In this paper, we dealt with traumatic events and long-term psycho social consequences for internally displaced persons, several years after displacement, and found a high level of PTSD symptoms. This stress is present in almost 1/3 of internally displaced persons, and every sixth person is suffering from PTSD in the past. Respondents generally suffer from symptoms of intrusion, but there was a large number of symptoms, avoidance and increased arousal. We also found that gender, age andeducation related to the symptoms. Females, and older respondents and internally displaced persons with lower levels of education how a higher level of PTSD symptoms, especially symptoms of intrusion and increase darousal. It is a highly traumatized sample in which more than 1/2 of respondents experienced more than three traumatic events in life,although the number of traumas experienced before, during and after the conflict varies.We found that during the war, internally displaced persons haveexperienced more traumatic events compared with the periodbefore and after the conflict. Trauma are different in type. No significant correlation between the number of experienced trauma and PTSD, suggesting that it is necessary to further study the structure of past traumas and the intermediary effects of certain risk factors and protective factors.

Keywords: living environment, displaced persons, jaundice, diabetes, trauma, diabetic hypertension, post-traumatic stress (PTSD), treatment

Procedia PDF Downloads 390

Authors: Annika Stechemesser, Rachel Pounds, Emma Lucas, Chris Dawson, Julia Lipecki, Pavle Vrljicak, Jan Brosens, Sean Kehoe, Jason Yap, Lawrence Young, Sascha Ott

Abstract:

Advances in technology make it now possible to retrieve the genetic information of thousands of single cancerous cells. One of the key challenges in single cell analysis of cancerous tissue is to determine the number of different cell types and their characteristic genes within the sample to better understand the tumors and their reaction to different treatments. For this analysis to be possible, it is crucial to filter out background noise as it can severely blur the downstream analysis and give misleading results. In-depth analysis of the state-of-the-art filtering methods for single cell data showed that they do, in some cases, not separate noisy and normal cells sufficiently. We introduced an algorithm that filters and clusters single cell data simultaneously without relying on certain genes or thresholds chosen by eye. It detects communities in a Shared Nearest Neighbor similarity network, which captures the similarities and dissimilarities of the cells by optimizing the modularity and then identifies and removes vertices with a weak clustering belonging. This strategy is based on the fact that noisy data instances are very likely to be similar to true cell types but do not match any of these wells. Once the clustering is complete, we apply a set of evaluation metrics on the cluster level and accept or reject clusters based on the outcome. The performance of our algorithm was tested on three datasets and led to convincing results. We were able to replicate the results on a Peripheral Blood Mononuclear Cells dataset. Furthermore, we applied the algorithm to two samples of ovarian cancer from the same patient before and after chemotherapy. Comparing the standard approach to our algorithm, we found a hidden cell type in the ovarian postchemotherapy data with interesting marker genes that are potentially relevant for medical research.

Keywords: cancer research, graph theory, machine learning, single cell analysis

Procedia PDF Downloads 107

Authors: Saikiran Subbagari, Avinash Malladhi

Abstract:

Anti Money Laundering (AML) regulations are designed to prevent money laundering and terrorist financing activities worldwide. Financial institutions around the world are legally obligated to identify, assess and mitigate the risks associated with money laundering and report any suspicious transactions to governing authorities. With increasing volumes of data to analyze, financial institutions seek to automate their AML processes. In the rise of financial crimes, optical character recognition (OCR), in combination with machine learning (ML) algorithms, serves as a crucial tool for automating AML processes by extracting the data from documents and identifying suspicious transactions. In this paper, we examine the utilization of OCR for AML and delve into various OCR techniques employed in AML processes. These techniques encompass template-based, feature-based, neural network-based, natural language processing (NLP), hidden markov models (HMMs), conditional random fields (CRFs), binarizations, pattern matching and stroke width transform (SWT). We evaluate each technique, discussing their strengths and constraints. Also, we emphasize on how OCR can improve the accuracy of customer identity verification by comparing the extracted text with the office of foreign assets control (OFAC) watchlist. We will also discuss how OCR helps to overcome language barriers in AML compliance. We also address the implementation challenges that OCR-based AML systems may face and offer recommendations for financial institutions based on the data from previous research studies, which illustrate the effectiveness of OCR-based AML.

Keywords: anti-money laundering, compliance, financial crimes, fraud detection, machine learning, optical character recognition

Procedia PDF Downloads 139

Authors: Sylvain Amailland, Jean-Hugh Thomas, Charles Pézerat, Romuald Boucheron, Jean-Claude Pascal

Abstract:

The noise requirements for naval and research vessels have seen an increasing demand for quieter ships in order to fulfil current regulations and to reduce the effects on marine life. Hence, new methods dedicated to the characterization of propeller noise, which is the main source of noise in the far-field, are needed. The study of cavitating propellers in closed-section is interesting for analyzing hydrodynamic performance but could involve significant difficulties for hydroacoustic study, especially due to reverberation and boundary layer noise in the tunnel. The aim of this paper is to present a numerical methodology for the identification of hydroacoustic sources on marine propellers using hydrophone arrays in a large hydrodynamic tunnel. The main difficulties are linked to the reverberation of the tunnel and the boundary layer noise that strongly reduce the signal-to-noise ratio. In this paper it is proposed to estimate the reflection coefficients using an inverse method and some reference transfer functions measured in the tunnel. This approach allows to reduce the uncertainties of the propagation model used in the inverse problem. In order to reduce the boundary layer noise, a cleaning algorithm taking advantage of the low rank and sparse structure of the cross-spectrum matrices of the acoustic and the boundary layer noise is presented. This approach allows to recover the acoustic signal even well under the boundary layer noise. The improvement brought by this method is visible on acoustic maps resulting from beamforming and DAMAS algorithms.

Keywords: acoustic imaging, boundary layer noise denoising, inverse problems, model adaptation

Procedia PDF Downloads 327

Authors: Babatunde Olumide Olawale, Oyebode Olumide Oyediran

Abstract:

The security safe is a place or building where classified document and precious items are kept. To prevent unauthorised persons from gaining access to this safe a lot of technologies had been used. But frequent reports of an unauthorised person gaining access into security safes with the aim of removing document and items from the safes are pointers to the fact that there is still security gap in the recent technologies used as access control for the security safe. In this paper we try to solve this problem by developing a multimodal biometric system for physical access control into a security safe using face and voice recognition. The safe is accessed by the combination of face and speech pattern recognition and also in that sequential order. User authentication is achieved through the use of camera/sensor unit and a microphone unit both attached to the door of the safe. The user face was captured by the camera/sensor while the speech was captured by the use of the microphone unit. The Scale Invariance Feature Transform (SIFT) algorithm was used to train images to form templates for the face recognition system while the Mel-Frequency Cepitral Coefficients (MFCC) algorithm was used to train the speech recognition system to recognise authorise user’s speech. Both algorithms were hosted in two separate web based servers and for automatic analysis of our work; our developed system was simulated in a MATLAB environment. The results obtained shows that the developed system was able to give access to authorise users while declining unauthorised person access to the security safe.

Keywords: access control, multimodal biometrics, pattern recognition, security safe

Procedia PDF Downloads 324

Authors: Min Chen, Rubi Gupta

Abstract:

Understanding and predicting stock market movements is a challenging problem. It is believed stock markets are partially driven by public sentiments, which leads to numerous research efforts to predict stock market trend using public sentiments expressed on social media such as Twitter but with limited success. Recently a microblogging website StockTwits is becoming increasingly popular for users to share their discussions and sentiments about stocks and financial market. In this project, we analyze the text content of StockTwits tweets and extract financial sentiment using text featurization and machine learning algorithms. StockTwits tweets are first pre-processed using techniques including stopword removal, special character removal, and case normalization to remove noise. Features are extracted from these preprocessed tweets through text featurization process using bags of words, N-gram models, TF-IDF (term frequency-inverse document frequency), and latent semantic analysis. Machine learning models are then trained to classify the tweets' sentiment as positive (bullish) or negative (bearish). The correlation between the aggregated daily sentiment and daily stock price movement is then investigated using Pearson’s correlation coefficient. Finally, the sentiment information is applied together with time series stock data to predict stock price movement. The experiments on five companies (Apple, Amazon, General Electric, Microsoft, and Target) in a duration of nine months demonstrate the effectiveness of our study in improving the prediction accuracy.

Keywords: machine learning, sentiment analysis, stock price prediction, tweet processing

Procedia PDF Downloads 147

Authors: H. Kalboussi, A. Aloui, W. Boughattas, M. Maoua, A. Brahem, S. Chatti, O. El Maalel, F. Debbabi, N. Mrizak, Y. Ben Youssef, A. Khlif, I. Bougmiza

Abstract:

Background: In recent decades, the incidence of children's hematological malignancies has been increasing worldwide including Tunisia. Their severity is reflected in the importance of the medical, social and economic impact. This increase remains fully unexplained, and the involvement of genetic, environmental and occupational factors is strongly suspected. Materials and Methods: Our study is a cross-sectional survey of the type case-control conducted in the University Hospital of Farhat Hached of Sousse during the period ranging between 1 July 2011 and 30 June 2012,and which included children with acute leukemia compared to children unharmed by neoplastic disease . Cases and controls were matched by age and gender. Our objective was to: - Describe the socio-occupational characteristics of the parents of children with acute leukemia. - Identify potential occupational factors implicated in the genesis of acute leukemia. Result: The number of acute leukemia cases in the Hematology Service and day hospital of the University Hospital of Farhat Hached during the study period was 66 cases divided into in 40 boys and 26 girls with a sex ratio of 1.53. Our cases and controls were matched by age and gender. The risk of incidence of leukemia in children from smoking fathers was higher (p = 0.02, OR = 2.24, IC = [1.11 - 4.52]). The risk of incidence of leukemia in children from alcoholic fathers was higher with p = 0,009, OR = 3.9; CI = [1.33 - 11.39]. After adjusting different variables, the difference persisted significantly with pa = 0.03 and ORa = 3.5; ICa = [1.09 -11.6]. 25.7 % of cases had a family history of blood disease and neoplasia, whereas no control presented that. The difference was statistically significant (p = 0.006), OR = 1.46, IC = [1.38 - 1.56]. The parental occupational exposures associated to the occurrence of acute leukemia in children were: - Pesticides with a statistically significant difference (p = 0.03), OR = 2.94, IC = [1.06 - 8.13]. This difference persisted after adjustment with different variables pa = 0.01, ORa 3.75; ICa = [1.27 - 11.03]. - Cement without a statistically non-significant difference (p = 0.2). This difference has become significant after adjustment with the different variables pa = 0.03; ORa = 2.67; ICa = [1.06 - 6.7]. Conclusion: Parental exposure to occupational risk factors may play a role in the pathogenesis of acute leukemia in children.

Keywords: hematological malignancies, children, parents, occupational exposure

Procedia PDF Downloads 313

Authors: Hamza Ikhlaq, Stephen Franks

Abstract:

Background: Polycystic ovarian syndrome (PCOS) is one of the most common endocrine disorders affecting women of reproductive age. The aetiology behind PCOS is poorly understood but influencing ethnic, environmental, and genetic factors have been recognised. However, literature examining the impact of ethnicity is scarce. We hypothesised Body Mass Index (BMI) and ethnicity influence the clinical, metabolic, and biochemical presentations of PCOS, with an interaction between these factors. Methods: A database of 1081 women with PCOS and a control group of 72 women were analysed. BMIs were grouped using the World Health Organisation classification into normal weight, overweight and obese groups. Ethnicities were classified into European, South Asian, and Afro-Caribbean groups. Biochemical and clinical presentations were compared amongst these groups, and statistical analyses were performed to assess significance. Results: This study revealed ethnicity significantly influences biochemical and clinical presentations of PCOS. A greater proportion of South Asian women are impacted by menstrual cycle disturbances and hirsutism than European and Afro-Caribbean women. South Asian and Afro-Caribbean women show greater measures of insulin resistance and weight gain when compared to their European peers. Women with increased BMI are shown to have an increased prevalence of PCOS phenotypes alongside increased levels of insulin resistance and testosterone. Furthermore, significantly different relationships between the waist-hip ratio and measures of insulin and glucose control for Afro-Caribbean women were identified compared to other ethnic groups. Conclusions: The findings of this study show ethnicity significantly influence the phenotypic and biochemical presentations of PCOS, with an interaction between body habitus and ethnicity found. Furthermore, we provide further data on the influences of BMI on the manifestations of PCOS. Therefore, we highlight the need to consider these factors when reviewing diagnostic criteria and delivering clinical care for these groups.

Keywords: PCOS, ethnicity, BMI, clinical

Procedia PDF Downloads 105

Authors: Silvia Ximena Barrios, Diego Armando Villamizar Mantilla, Raquel Elvira Ocazionez, , Elena E. Stashenko, María Pilar Vinardell, Jorge Luis Fuentes

Abstract:

Introduction: Skin overexposure to solar radiation has been a serious public health concern, because of its potential carcinogenicity. Therefore, preventive protection strategies using photoprotective agents are critical to counteract the harmful effect of solar radiation. Plants may be a source of photoprotective compounds that inhibit cellular mutations involved in skin cancer initiation. This work evaluated the photoprotective and antigenotoxic effects against ultraviolet B (UVB) radiation of a mixture of Posoqueria latifolia flower extract and Kaempferol (MixPoKa). Methods: The photoprotective efficacy of MixPoka (Posoqueria latifolia flower extract 250 μg/ml and Kaempferol 349.5 μM) was evaluated using in vitro indices such as sun protection factor SPFᵢₙ ᵥᵢₜᵣₒ and critical wavelength (λc). The MixPoKa photostability (Eff) at human minimal erythema doses (MED), according to the Fitzpatrick skin scale, was also estimated. Cytotoxicity and genotoxicity/antigenotoxicity were studied in MRC5 human fibroblasts using the trypan blue exclusion and Comet assays, respectively. Kinetics of the genetic damage repair post irradiation in the presence and absence of the MixPoka, was also evaluated. Results: The MixPoka -UV absorbance spectrum was high across the spectral bands between 200 and 400 nm. The UVB photoprotection efficacy of MixPoka was high (SPFᵢₙ ᵥᵢₜᵣₒ = 25.70 ± 0.06), showed wide photoprotection spectrum (λc = 380 ± 0), and resulted photostable (Eff = 92.3–100.0%). The MixPoka was neither cytotoxic nor genotoxic in MRC5 human fibroblasts; but presented significant antigenotoxic effect against UVB radiation. Additionally, MixPoka stimulate DNA repair post-irradiation. The potential of this phytochemical mixture as sunscreen ingredients was discussed. Conclusion: MixPoka showed a significant antigenotoxic effect against UVB radiation and stimulated DNA repair after irradiation. MixPoka could be used as an ingredient in a sunscreen cream.

Keywords: flower extract, photoprotection, antigenotoxicity, cytotoxicity, genotoxicit

Procedia PDF Downloads 76

Authors: Rita Alfattal, Maryam Alfarhan, Adeeb M. Algaith, Buthaina Albash, Reem M. Elshafie, Asma Alshammari, Ahmad Alahmad, Fatima Dashti, Rasha Alsafi, Hind Alsharhan

Abstract:

Defects of respiratory chain complex III (CIII) result in characteristic but rare mitochondrial disorders associated with distinct neuroradiological findings. The underlying molecular defects affecting mitochondrial CIII assembly factors are few and yet to be identified. LYRM7 assembly factor is required for proper CIII assembly where it acts as a chaperone for the Rieske iron‐sulfur (UQCRFS1) protein in the mitochondrial matrix and stabilizing it. We present here the seventeenth individual with LYRM7-associated mitochondrial leukoencephalopathy harboring a previously reported rare pathogenic homozygous LYRM 7 variant, c.2T>C, (p.Met1?). Like previously reported individuals, our 4-year-old male proband presented with recurrent metabolic and lactic acidosis, encephalopathy, and myopathy. Further, he has additional, previously unreported features, including an acute stroke like episode with bilateral central blindness and optic neuropathy, recurrent hyperglycemia and hypertension associated with metabolic crisis. However, he has no signs of psychomotor regression. He has been stable clinically with residual left-sided reduced visual acuity and amblyopia, and no more metabolic crises for 2-year-period while on the mitochondrial cocktail. Although the reported brain MRI findings in other affected individuals are homogenous, it is slightly different in our index, revealing evidence of bilateral almost symmetric multifocal periventricular T2 hyperintensities with hyperintensities of the optic nerves, optic chiasm, and corona radiata but with no cavitation or cystic changes. This report describes new clinical and radiological findings of LYRM7-associated disease. The report also summarizes the clinical and molecular data of previously reported individuals describing the full phenotypic spectrum.

Keywords: LYRM7 gene defect, mitochondrial disease, , lactic acidosis, , genetic disorder

Procedia PDF Downloads 67

Authors: Leixuri Aguirre, Iñaki Milton-Laskibar, Elizabeth Hijona, Luis Bujanda, Agnes M. Rimando, Maria P. Portillo

Abstract:

Introduction: In recent years great attention has been paid by scientific community to phenolic compounds as active biomolecules naturally present in foodstuffs due to their beneficial effects on health. Pterostilbene is a resveratrol dimethylether derivative which shows higher biodisponibility. Objective. To analyze the effects of two doses of pterostilbene on several markers of thermogenic capacity in a model of genetic obesity, which shows reduced thermogenesis. Methods: The experiment was conducted with thirty Zucker (fa/fa) rats that were distributed in 3 experimental groups, the control group and two groups orally administered with pterostilbene at 15 and 30 mg/kg body weight/day for 6 weeks. Gene expression of Ucp1, Pgc-1α, Cpt1b, Pparα, Nfr1, Tfam and Cox-2 were assessed by RT-PCR, protein expression of UCP1 and GLUT4 by western blot and enzyme activity of carnitine palmitoyl transferase 1b and citrate synthase by spectrophotometry in interscapular brown adipose tissue (iBAT). Statistical analysis was performed by using one way ANOVA and Newman-Keuls as post-hoc test. Results: Pterostilbene did not change gene expression of Pgc-1α. However, significant increases were found in the expression of Ucp1, Pparα, Nfr-1 and Cox-2. Protein expression of UCP1 and GLUT4 was increased in animals treated with pterostilbene, as well as the activities of CPT-1b and CS. These effects were observed with both doses of pterostilbene, without differences between them. Conclusions: These results show that pterostilbene increases thermogenic and oxidative capacity of brown adipose tissue in obese rats. Whether these effects effectively contribute to the anti-obesity properties of these compound needs further research. Acknowledgments: MINECO-FEDER (AGL2015-65719-R), Basque Government (IT-572-13), University of the Basque Country (ELDUNANOTEK UFI11/32), Institut of Health Carlos III (CIBERobn). Iñaki Milton is a fellowship from the Basque Government.

Keywords: brown adipose tissue, pterostilbene, thermogenesis, uncoupling protein 1

Procedia PDF Downloads 290

Authors: Tarana Siddika, Ilka U. Heinemann, Patrick O’Donoghue

Abstract:

Protein kinase B (AKT1) is a serine/threonine kinase and central transducer of cell survival pathways. Typical approaches to study AKT1 biology in cells rely on growth factor or insulin stimulation that activates AKT1 via phosphorylation at two key regulatory sites (Threonine308, Serine473), yet cell stimulation also activates many other kinases and fails to differentiate the effect of the two main activating sites of AKT1 on downstream substrate phosphorylation and cell growth. While both AKT1 activating sites are associated with disease and used as clinical markers, in some cancers, high levels of Threonine308 phosphorylation are associated with poor prognosis while in others poor survival correlates with high Serine473 levels. To produce cells with specific AKT1 activity, a system was developed to deliver active AKT1 to human cells. AKT1 phospho-variants were produced from Escherichia coli with programmed phosphorylation by genetic code expansion. Tagging of AKT1 with an N-terminal cell penetrating peptide tag derived from the human immunodeficiency virus trans-activator of transcription (TAT) helped to enter AKT1 proteins in mammalian cells. The TAT-tag did not alter AKT1 kinase activity and was necessary and sufficient to rapidly deliver AKT1 protein variants that persisted in human cells for 24 h without the need to use transfection reagents. TAT-pAKT1T308, TAT-pAKT1S473 and TAT-pAKT1T308S473 proteins induced selective phosphorylation of the known AKT1 substrate GSK-3αβ, and downstream stimulation of the AKT1 pathway as evidenced by phosphorylation of ribosomal protein S6 at Serine240/244 in transfected cells. Increase in cell growth and proliferation was observed due to the transfection of different phosphorylated AKT1 protein variants compared to cells with TAT-AKT1 protein. The data demonstrate efficient delivery of AKT1 with programmed phosphorylation to human cells, thus establishing a cell-based model system to investigate signaling that is dependent on specific AKT1 activity and phosphorylation.

Keywords: cell penetrating peptide, cell signaling, protein kinase b (AKT1), phosphorylation

Procedia PDF Downloads 112

Authors: Leonardo C. Pacheco-Londoño, Nataly J Galan-Freyle, Lisandro Pacheco-Lugo, Antonio Acosta-Hoyos, Elkin Navarro, Gustavo Aroca-Martinez, Karin Rondón-Payares, Alberto C. Espinosa-Garavito, Samuel P. Hernández-Rivera

Abstract:

At the Life Science Research Center at Simon Bolivar University, a primary focus is the diagnosis of various diseases, and the use of gold nanoparticles (Au-NPs) in diverse biomedical applications is continually expanding. In the present study, Au-NPs were employed as substrates for Surface-Enhanced Raman Spectroscopy (SERS) aimed at diagnosing kidney diseases arising from Lupus Nephritis (LN), preeclampsia (PC), and Hypertension (H). Discrimination models were developed for distinguishing patients with and without kidney diseases based on the SERS signals from urine samples by partial least squares-discriminant analysis (PLS-DA). A comparative study of the Raman signals across the three conditions was conducted, leading to the identification of potential metabolite signals. Model performance was assessed through cross-validation and external validation, determining parameters like sensitivity and specificity. Additionally, a secondary analysis was performed using machine learning (ML) models, wherein different ML algorithms were evaluated for their efficiency. Models’ validation was carried out using cross-validation and external validation, and other parameters were determined, such as sensitivity and specificity; the models showed average values of 0.9 for both parameters. Additionally, it is not possible to highlight this collaborative effort involved two university research centers and two healthcare institutions, ensuring ethical treatment and informed consent of patient samples.

Keywords: SERS, Raman, PLS-DA, kidney diseases

Procedia PDF Downloads 39