Search results for: neural smith predictor

Authors: Inna Kornienko, Svetlana Guryeva, Anatoly Shekhter, Elena Petersen

Abstract:

Transplantation is an effective treatment option for patients suffering from different end-stage diseases. However, it is plagued by a constant shortage of donor organs and the subsequent need of a lifelong immunosuppressive therapy for the patient. Currently some researchers look towards using of pig organs to replace human organs for transplantation since the matrix derived from porcine organs is a convenient substitute for the human matrix. As an initial step to create a new ex vivo tissue engineered model, optimized protocols have been created to obtain organ-specific acellular matrices and evaluated their potential as tissue engineered scaffolds for culture of normal cells and tumor cell lines. These protocols include decellularization by perfusion in a bioreactor system and immersion-agitation on an orbital shaker with use of various detergents (SDS, Triton X-100) and freezing. Complete decellularization – in terms of residual DNA amount – is an important predictor of probability of immune rejection of materials of natural origin. However, the signs of cellular material may still remain within the matrix even after harsh decellularization protocols. In this regard, the matrices obtained from tissues of low-immunogenic pigs with α3Galactosyl-tranferase gene knock out (GalT-KO) may be a promising alternative to native animal sources. The research included a study of induced effect of frozen and fresh fragments of GalT-KO skin on healing of full-thickness plane wounds in 80 rats. Commercially available wound dressings (Ksenoderm, Hyamatrix and Alloderm) as well as allogenic skin were used as a positive control and untreated wounds were analyzed as a negative control. The results were evaluated on the 4th day after grafting, which corresponds to the time of start of normal wound epithelization. It has been shown that a non-specific immune response in models treated with GalT-Ko pig skin was milder than in all the control groups. Research has been performed to measure technical skin characteristics: stiffness and elasticity properties, corneometry, tevametry, and cutometry. These metrics enabled the evaluation of hydratation level, corneous layer husking level, as well as skin elasticity and micro- and macro-landscape. These preliminary data may contribute to development of personalized transplantable organs from GalT-Ko pigs with significantly limited potential of immune rejection. By applying growth factors to a decellularized skin sample it is possible to achieve various regenerative effects based on the particular situation. In this particular research BMP2 and Heparin-binding EGF-like growth factor have been used. Ideally, a bioengineered organ must be biocompatible, non-immunogenic and support cell growth. Porcine organs are attractive for xenotransplantation if severe immunologic concerns can be bypassed. The results indicate that genetically modified pig tissues with knock-outed α3Galactosyl-tranferase gene may be used for production of low-immunogenic matrix suitable for transplantation.

Keywords: decellularization, low-immunogenic, matrix, scaffolds, transplants

Procedia PDF Downloads 255

Authors: Lucilla Crosta, Anthony Edwards

Abstract:

Companies and the market place nowadays struggle to find employees with adequate skills in relation to anticipated growth of their businesses. At least half of workers will need to undertake some form of up-skilling process in the next five years in order to remain aligned with the requests of the market . In order to meet these challenges, there is a clear need to explore the potential uses of AI (artificial Intelligence) based tools in assessing transversal skills (critical thinking, communication and soft skills of different types in general) of workers and adult students while empowering them to develop those same skills in a reliable trustworthy way. Companies seek workers with key transversal skills that can make a difference between workers now and in the future. However, critical thinking seems to be the one of the most imprtant skill, bringing unexplored ideas and company growth in business contexts. What employers have been reporting since years now, is that this skill is lacking in the majority of workers and adult students, and this is particularly visible trough their writing. This paper investigates how critical thinking and communication skills are currently developed in Higher Education environments through use of AI tools at postgraduate levels. It analyses the use of a branch of AI namely Machine Learning and Big Data and of Neural Network Analysis. It also examines the potential effect the acquisition of these skills through AI tools and what kind of effects this has on employability This paper will draw information from researchers and studies both at national (Italy & UK) and international level in Higher Education. The issues associated with the development and use of one specific AI tool Edulai, will be examined in details. Finally comparisons will be also made between these tools and the more recent phenomenon of Chat GPT and forthcomings and drawbacks will be analysed.

Keywords: critical thinking, artificial intelligence, higher education, soft skills, chat GPT

Procedia PDF Downloads 77

Authors: Lanchi Xie, Zhihui Li, Zhigang Li, Guiqiang Wang, Lei Xu, Yuwen Yan

Abstract:

Image-based facial features can be classified into category recognition features and individual recognition features. Current automated face recognition systems extract a specific feature vector of different dimensions from a facial image according to their pre-trained neural network. However, to improve the efficiency of parameter calculation, an algorithm generally reduces the image details by pooling. The operation will overlook the details concerned much by forensic experts. In our experiment, we adopted a variety of face recognition algorithms based on deep learning, compared a large number of naturally collected face images with the known data of the same person's frontal ID photos. Downscaling and manual handling were performed on the testing images. The results supported that the facial recognition algorithms based on deep learning detected structural and morphological information and rarely focused on specific markers such as stains and moles. Overall performance, distribution of genuine scores and impostor scores, and likelihood ratios were tested to evaluate the accuracy of biometric systems and forensic experts. Experiments showed that the biometric systems were skilled in distinguishing category features, and forensic experts were better at discovering the individual features of human faces. In the proposed approach, a fusion was performed at the score level. At the specified false accept rate, the framework achieved a lower false reject rate. This paper contributes to improving the interpretability of the objective method of facial comparison and provides a novel method for human-machine collaboration in this field.

Keywords: likelihood ratio, automated facial recognition, facial comparison, biometrics

Procedia PDF Downloads 103

Authors: Sevelina Ndlovu

Abstract:

Financial Technology (fintech) advancement is recognised as one of the most transformational innovations in the financial industry. Fintech has given rise to internet-only digital banking, a novel financial technology advancement, and innovation that allows banking services through internet applications with no need for physical branches. This technology is becoming a new banking normal among consumers for its ubiquitous and real-time access advantages. There is evident switching and migration from traditional banking towards these fintech facilities, which could possibly pose a systemic risk if not properly understood and monitored. Fintech advancement has also brought about the emergence and escalation of financial technology consumption themes such as trust, security, perceived risk, and sustainability within the banking industry, themes scarcely covered in existing theoretic literature. To that end, the objective of this research is to investigate factors that determine fintech adoption and propose an integrated adoption model. This study aims to establish what the significant drivers of adoption are and develop a conceptual model that integrates technological, behavioral, and environmental constructs by extending the Unified Theory of Acceptance and Use of Technology 2 (UTAUT2). It proposes integrating constructs that influence financial consumption themes such as trust, perceived risk, security, financial incentives, micro-investing opportunities, and environmental consciousness to determine the impact of these factors on the adoption and intention to use digital banking apps. The main advantage of this conceptual model is the consolidation of a greater number of predictor variables that can provide a fuller explanation of the consumer's adoption of digital banking Apps. Moderating variables of age, gender, and income are incorporated. To the best of author’s knowledge, this study is the first that extends the UTAUT2 model with this combination of constructs to investigate user’s intention to adopt internet-only digital banking apps in the UK context. By investigating factors that are not included in the existing theories but are highly pertinent to the adoption of internet-only banking services, this research adds to existing knowledge and extends the generalisability of the UTAUT2 in a financial services adoption context. This is something that fills a gap in knowledge, as highlighted to needing further research on UTAUT2 after reviewing the theory in 2016 from its original version of 2003. To achieve the objectives of this study, this research assumes a quantitative research approach to empirically test the hypotheses derived from existing literature and pilot studies to give statistical support to generalise the research findings for further possible applications in theory and practice. This research is explanatory or casual in nature and uses cross-section primary data collected through a survey method. Convenient and purposive sampling using structured self-administered online questionnaires is used for data collection. The proposed model is tested using Structural Equation Modelling (SEM), and the analysis of primary data collected through an online survey is processed using Smart PLS software with a sample size of 386 digital bank users. The results are expected to establish if there are significant relationships between the dependent and independent variables and establish what the most influencing factors are.

Keywords: banking applications, digital banking, financial technology, technology adoption, UTAUT2

Procedia PDF Downloads 36

Authors: Annalakshmi G., Sakthivel Murugan S.

Abstract:

This paper presents a local directional encoded derivative binary pattern (LDEDBP) feature extraction method that can be applied for the classification of submarine coral reef images. The classification of coral reef images using texture features is difficult due to the dissimilarities in class samples. In coral reef image classification, texture features are extracted using the proposed method called local directional encoded derivative binary pattern (LDEDBP). The proposed approach extracts the complete structural arrangement of the local region using local binary batten (LBP) and also extracts the edge information using local directional pattern (LDP) from the edge response available in a particular region, thereby achieving extra discriminative feature value. Typically the LDP extracts the edge details in all eight directions. The process of integrating edge responses along with the local binary pattern achieves a more robust texture descriptor than the other descriptors used in texture feature extraction methods. Finally, the proposed technique is applied to an extreme learning machine (ELM) method with a meta-heuristic algorithm known as weighted distance grey wolf optimizer (GWO) to optimize the input weight and biases of single-hidden-layer feed-forward neural networks (SLFN). In the empirical results, ELM-WDGWO demonstrated their better performance in terms of accuracy on all coral datasets, namely RSMAS, EILAT, EILAT2, and MLC, compared with other state-of-the-art algorithms. The proposed method achieves the highest overall classification accuracy of 94% compared to the other state of art methods.

Keywords: feature extraction, local directional pattern, ELM classifier, GWO optimization

Procedia PDF Downloads 140

Authors: Amin Naboureh, Ainong Li, Jinhu Bian, Guangbin Lei, Hamid Ebrahimy

Abstract:

Large-scale land cover mapping has become a new challenge in land change and remote sensing field because of involving a big volume of data. Moreover, selecting the right classification method, especially when there are different types of landscapes in the study area is quite difficult. This paper is an attempt to compare the performance of different machine learning (ML) algorithms for generating a land cover map of the China-Central Asia–West Asia Corridor that is considered as one of the main parts of the Belt and Road Initiative project (BRI). The cloud-based Google Earth Engine (GEE) platform was used for generating a land cover map for the study area from Landsat-8 images (2017) by applying three frequently used ML algorithms including random forest (RF), support vector machine (SVM), and artificial neural network (ANN). The selected ML algorithms (RF, SVM, and ANN) were trained and tested using reference data obtained from MODIS yearly land cover product and very high-resolution satellite images. The finding of the study illustrated that among three frequently used ML algorithms, RF with 91% overall accuracy had the best result in producing a land cover map for the China-Central Asia–West Asia Corridor whereas ANN showed the worst result with 85% overall accuracy. The great performance of the GEE in applying different ML algorithms and handling huge volume of remotely sensed data in the present study showed that it could also help the researchers to generate reliable long-term land cover change maps. The finding of this research has great importance for decision-makers and BRI’s authorities in strategic land use planning.

Keywords: land cover, google earth engine, machine learning, remote sensing

Procedia PDF Downloads 96

Authors: Ruphi Naz, Altaf Ahmad, Mohammad Anis

Abstract:

Sialic acid (5-Acetylneuraminic acid, Neu5Ac) is a common sugar found as a terminal residue on glycoconjugates in many animals. Humans brain and the central nervous system contain the highest concentration of sialic acid (as N-acetylneuraminic acid) where these acids play an important role in neural transmission and ganglioside structure in synaptogenesis. Due to its important biological function, sialic acid is attracting increasing attention. To understand metabolic networks, fluxes and regulation, it is essential to be able to determine the cellular and subcellular levels of metabolites. Genetically-encoded fluorescence resonance energy transfer (FRET) sensors represent a promising technology for measuring metabolite levels and corresponding rate changes in live cells. Taking this, we developed a genetically encoded FRET (fluorescence resonance energy transfer) based nanosensor to analyse the sialic acid level in living cells. Sialic acid periplasmic binding protein (sia P) from Haemophilus influenzae was taken and ligated between the FRET pair, the cyan fluorescent protein (eCFP) and Venus. The chimeric sensor protein was expressed in E. coli BL21 (DE3) and purified by affinity chromatography. Conformational changes in the binding protein clearly confirmed the changes in FRET efficiency. So any change in the concentration of sialic acid is associated with the change in FRET ratio. This sensor is very specific to sialic acid and found stable with the different range of pH. This nanosensor successfully reported the intracellular level of sialic acid in bacterial cell. The data suggest that the nanosensors may be a versatile tool for studying the in vivo dynamics of sialic acid level non-invasively in living cells

Keywords: nanosensor, FRET, Haemophilus influenzae, metabolic networks

Procedia PDF Downloads 106

Authors: Yehjune Heo

Abstract:

As biometric systems become widely deployed, the security of identification systems can be easily attacked by various spoof materials. This paper contributes to finding a reliable and practical anti-spoofing method using Convolutional Neural Networks (CNNs) based on the types of loss functions and optimizers. The types of CNNs used in this paper include AlexNet, VGGNet, and ResNet. By using various loss functions including Cross-Entropy, Center Loss, Cosine Proximity, and Hinge Loss, and various loss optimizers which include Adam, SGD, RMSProp, Adadelta, Adagrad, and Nadam, we obtained significant performance changes. We realize that choosing the correct loss function for each model is crucial since different loss functions lead to different errors on the same evaluation. By using a subset of the Livdet 2017 database, we validate our approach to compare the generalization power. It is important to note that we use a subset of LiveDet and the database is the same across all training and testing for each model. This way, we can compare the performance, in terms of generalization, for the unseen data across all different models. The best CNN (AlexNet) with the appropriate loss function and optimizers result in more than 3% of performance gain over the other CNN models with the default loss function and optimizer. In addition to the highest generalization performance, this paper also contains the models with high accuracy associated with parameters and mean average error rates to find the model that consumes the least memory and computation time for training and testing. Although AlexNet has less complexity over other CNN models, it is proven to be very efficient. For practical anti-spoofing systems, the deployed version should use a small amount of memory and should run very fast with high anti-spoofing performance. For our deployed version on smartphones, additional processing steps, such as quantization and pruning algorithms, have been applied in our final model.

Keywords: anti-spoofing, CNN, fingerprint recognition, loss function, optimizer

Procedia PDF Downloads 109

Authors: Isaac Kayode Ogunlade

Abstract:

Data acquisition (DAQ) is the process by which physical phenomena from the real world are transformed into an electrical signal(s) that are measured and converted into a digital format for processing, analysis, and storage by a computer. The DAQ is designed using PIC18F4550 microcontroller, communicating with Personal Computer (PC) through USB (Universal Serial Bus). The research deployed initial knowledge of data acquisition system and embedded system to develop a weather data acquisition device using LM35 sensor to measure weather parameters and the use of Artificial Intelligence(Artificial Neural Network - ANN)and statistical approach(Autoregressive Integrated Moving Average – ARIMA) to predict precipitation (rainfall). The device is placed by a standard device in the Department of Meteorology, Federal University of Technology, Akure (FUTA) to know the performance evaluation of the device. Both devices (standard and designed) were subjected to 180 days with the same atmospheric condition for data mining (temperature, relative humidity, and pressure). The acquired data is trained in MATLAB R2012b environment using ANN, and ARIMAto predict precipitation (rainfall). Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Correction Square (R2), and Mean Percentage Error (MPE) was deplored as standardize evaluation to know the performance of the models in the prediction of precipitation. The results from the working of the developed device show that the device has an efficiency of 96% and is also compatible with Personal Computer (PC) and laptops. The simulation result for acquired data shows that ANN models precipitation (rainfall) prediction for two months (May and June 2017) revealed a disparity error of 1.59%; while ARIMA is 2.63%, respectively. The device will be useful in research, practical laboratories, and industrial environments.

Keywords: data acquisition system, design device, weather development, predict precipitation and (FUTA) standard device

Procedia PDF Downloads 66

Authors: Carol Anne Hargreaves

Abstract:

A key issue in stock investment is how to select representative features for stock selection. The objective of this paper is to firstly determine whether an automated stock investment system, using machine learning techniques, may be used to identify a portfolio of growth stocks that are highly likely to provide returns better than the stock market index. The second objective is to identify the technical features that best characterize whether a stock’s price is likely to go up and to identify the most important factors and their contribution to predicting the likelihood of the stock price going up. Unsupervised machine learning techniques, such as cluster analysis, were applied to the stock data to identify a cluster of stocks that was likely to go up in price – portfolio 1. Next, the principal component analysis technique was used to select stocks that were rated high on component one and component two – portfolio 2. Thirdly, a supervised machine learning technique, the logistic regression method, was used to select stocks with a high probability of their price going up – portfolio 3. The predictive models were validated with metrics such as, sensitivity (recall), specificity and overall accuracy for all models. All accuracy measures were above 70%. All portfolios outperformed the market by more than eight times. The top three stocks were selected for each of the three stock portfolios and traded in the market for one month. After one month the return for each stock portfolio was computed and compared with the stock market index returns. The returns for all three stock portfolios was 23.87% for the principal component analysis stock portfolio, 11.65% for the logistic regression portfolio and 8.88% for the K-means cluster portfolio while the stock market performance was 0.38%. This study confirms that an automated stock investment system using machine learning techniques can identify top performing stock portfolios that outperform the stock market.

Keywords: machine learning, stock market trading, logistic regression, cluster analysis, factor analysis, decision trees, neural networks, automated stock investment system

Procedia PDF Downloads 131

Authors: Catherine S. Fichten, Tali Heiman, Mary Jorgensen, Mai Nhu Nguyen, Rhonda Amsel, Dorit Olenik-Shemesh

Abstract:

The study examined Canadian and Israeli students' perceptions related to their intention to graduate from their program of studies. Canada and Israel are dissimilar in many ways that affect education, including language and alphabet. In addition, the postsecondary education systems differ. For example, in some parts of Canada (e.g., in Quebec, Canada’s 2nd largest province), students matriculate after 11 years of high school; in Israel, this typically occurs after 12 years. In addition, Quebec students attend two compulsory years of junior college before enrolling in a three-year university Bachelor program; in Israel students enroll in a three-year Bachelor program directly after matriculation. In addition, Israeli students typically enroll in the army shortly after high school graduation; in Canada, this is not the case. What the two countries do have in common is concern about the success of postsecondary students with disabilities. The present study was based on Ajzen’s Theory of Planned Behavior (TPB); the model suggests that behavior is influenced by Intention to carry it out. This, in turn, is predicted by the following correlated variables: Perceived Behavioral Control (i.e., ease or difficulty enacting the behavior - in this case graduation), Subjective Norms (i.e., perceived social/peer pressure from individuals important in the student’s life), and Attitude (i.e., positive or negative evaluation of graduation). A questionnaire was developed to test the TPB in previous Canadian studies and administered to 845 Canadian college students (755 nondisabled, 90 with LD/ADHD) who had completed at least one semester of studies) and to 660 Israeli university students enrolled in a Bachelor’s program (537 nondisabled, 123 with LD/ADHD). Because Israeli students were older than Canadian students we covaried age in SPSS-based ANOVA comparisons and included it in regression equations. Because females typically have better academic outcomes than males, gender was included in all analyses. ANOVA results indicate only a significant gender effect for Intention to graduate, with females having higher scores. Four stepwise regressions were conducted, with Intention to graduate as the predicted variable, and Gender and the three TPB predictors as independent variables (separate analyses for Israeli and Canadian samples with and without LD/ADHD). Results show that for samples with LD/ADHD, although Gender and Age were not significant predictors, the TPB predictors were, with all three TPB predictors being significant for the Canadian sample (i.e., Perceived Behavioral Control, Subjective Norms, Attitude, R2=.595), and two of the three (i.e., Perceived Behavioral Control, Subjective Norms) for the Israeli sample (R2=.528). For nondisabled students, the results for both countries show that all three TPB predictors were significant along with Gender: R2=.443 for Canada and R2=.332 for Israel; age was not significant. Our findings show that despite vast differences between our Canadian and Israeli samples, Intention to graduate was related to the three TPB predictors. This suggests that our TPB measure is valid for diverse samples and countries that it can be used as a quick, inexpensive way to predict graduation rates, and that strengthening the three predictor variables may result in higher graduation rates.

Keywords: disability, higher education, students, theory of planned behavior

Procedia PDF Downloads 352

Authors: Ho-Won Jung, Donghun Lee, Hyung-Jin Kim

Abstract:

Predictive analytics (data analysis) uses a subset of measurements (the features, predictor, or independent variable) to predict another measurement (the outcome, target, or dependent variable) on a single person or unit. It applies empirical methods in statistics, operations research, and machine learning to predict the future, or otherwise unknown events or outcome on a single or person or unit, based on patterns in data. Most analyses of metabolic syndrome are not predictive analytics but statistical explanatory studies that build a proposed model (theory building) and then validate metabolic syndrome predictors hypothesized (theory testing). A proposed theoretical model forms with causal hypotheses that specify how and why certain empirical phenomena occur. Predictive analytics and explanatory modeling have their own territories in analysis. However, predictive analytics can perform vital roles in explanatory studies, i.e., scientific activities such as theory building, theory testing, and relevance assessment. In the context, this study is to demonstrate how to use our predictive analytics to support theory building (i.e., hypothesis generation). For the purpose, this study utilized a big data predictive analytics platform TM based on a co-occurrence graph. The co-occurrence graph is depicted with nodes (e.g., items in a basket) and arcs (direct connections between two nodes), where items in a basket are fully connected. A cluster is a collection of fully connected items, where the specific group of items has co-occurred in several rows in a data set. Clusters can be ranked using importance metrics, such as node size (number of items), frequency, surprise (observed frequency vs. expected), among others. The size of a graph can be represented by the numbers of nodes and arcs. Since the size of a co-occurrence graph does not depend directly on the number of observations (transactions), huge amounts of transactions can be represented and processed efficiently. For a demonstration, a total of 13,254 metabolic syndrome training data is plugged into the analytics platform to generate rules (potential hypotheses). Each observation includes 31 predictors, for example, associated with sociodemographic, habits, and activities. Some are intentionally included to get predictive analytics insights on variable selection such as cancer examination, house type, and vaccination. The platform automatically generates plausible hypotheses (rules) without statistical modeling. Then the rules are validated with an external testing dataset including 4,090 observations. Results as a kind of inductive reasoning show potential hypotheses extracted as a set of association rules. Most statistical models generate just one estimated equation. On the other hand, a set of rules (many estimated equations from a statistical perspective) in this study may imply heterogeneity in a population (i.e., different subpopulations with unique features are aggregated). Next step of theory development, i.e., theory testing, statistically tests whether a proposed theoretical model is a plausible explanation of a phenomenon interested in. If hypotheses generated are tested statistically with several thousand observations, most of the variables will become significant as the p-values approach zero. Thus, theory validation needs statistical methods utilizing a part of observations such as bootstrap resampling with an appropriate sample size.

Keywords: explanatory modeling, metabolic syndrome, predictive analytics, theory building

Procedia PDF Downloads 247

Authors: David A. Harness

Abstract:

Natural evolution of ATP cognitive systems is to meet AI peer review standards. ATP process of axiom selection from Mizar to prove a conjecture would be further refined, as in all human and machine learning, by solving the real world problem of the proposed AI peer review challenge: Determine which conjecture forms the higher confidence level constructive proof between Standard Model of Physics SU(n) lattice gauge group operation vs. present non-standard 4D GEM EOS SU(n) lattice gauge group spatially extended operation in which the photon and electron are the first two trace angular momentum invariants of a gravitoelectromagnetic (GEM) energy momentum density tensor wavetrain integration spin-stress pressure-volume equation of state (EOS), initiated via 32 lines of Mathematica code. Resulting gravitoelectromagnetic spectrum ranges from compressive through rarefactive of the central cosmological constant vacuum energy density in units of pascals. Said self-adjoint group operation exclusively operates on the stress energy momentum tensor of the Einstein field equations, introducing quantization directly on the 4D spacetime level, essentially reformulating the Yang-Mills virtual superpositioned particle compounded lattice gauge groups quantization of the vacuum—into a single hyper-complex multi-valued GEM U(1) × SU(1,3) lattice gauge group Planck spacetime mesh quantization of the vacuum. Thus the Mizar corpus already contains all of the axioms required for relevant DeepMath premise selection and unambiguous formal natural language parsing in context deep learning.

Keywords: automated theorem proving, constructive quantum field theory, information theory, neural networks

Procedia PDF Downloads 153

Authors: J. DeBoard, R. Dietrich, J. Hughes, K. Yurko, G. Harms

Abstract:

Alzheimer’s disease (AD) is a predominant type of dementia and is likely a major cause of neural network impairment. The pathogenesis of this neurodegenerative disorder has yet to be fully elucidated. There are currently no known cures for the disease, and the best hope is to be able to detect it early enough to impede its progress. Beyond age and genetics, another prevalent risk factor for AD might be traumatic brain injury (TBI), which has similar neurodegenerative hallmarks. Our research focuses on obtaining information and methods to be able to predict when neurodegenerative effects might occur at a clinical level by observation of events at a cellular and molecular level in model mice. First, we wish to introduce our evidence that brain damage can be observed via brain imaging prior to the noticeable loss of neuromuscular control in model mice of AD. We then show our evidence that some blood biomarkers might be able to be early predictors of AD in the same model mice. Thus, we were interested to see if we might be able to predict which mice might show long-term neurodegenerative effects due to differing degrees of TBI and what level of TBI causes further damage and earlier death to the AD model mice. Upon application of TBIs via an apparatus to effectively induce extremely mild to mild TBIs, wild-type (WT) mice and AD mouse models were tested for cognition, neuromuscular control, olfactory ability, blood biomarkers, and brain imaging. Experiments are currently still in process, and more results are therefore forthcoming. Preliminary data suggest that neuromotor control diminishes as well as olfactory function for both AD and WT mice after the administration of five consecutive mild TBIs. Also, seizure activity increases significantly for both AD and WT after the administration of the five TBI treatment. If future data supports these findings, important implications about the effect of TBI on those at risk for AD might be possible.

Keywords: Alzheimer's disease, blood biomarker, neurodegeneration, neuromuscular control, olfaction, traumatic brain injury

Procedia PDF Downloads 114

Authors: M. Bilal Ishfaq, Adnan N. Qureshi

Abstract:

COVID-19 is the most infectious disease these days, it was first reported in Wuhan, the capital city of Hubei in China then it spread rapidly throughout the whole world. Later on 11 March 2020, the World Health Organisation (WHO) declared it a pandemic. Since COVID-19 is highly contagious, it has affected approximately 219M people worldwide and caused 4.55M deaths. It has brought the importance of accurate diagnosis of respiratory diseases such as pneumonia and COVID-19 to the forefront. In this paper, we propose a hybrid approach for the automated detection of COVID-19 using medical imaging. We have presented the hybridization of manually extracted and convolutional features. Our approach combines Haralick texture features and convolutional features extracted from chest X-rays and CT scans. We also employ a minimum redundancy maximum relevance (MRMR) feature selection algorithm to reduce computational complexity and enhance classification performance. The proposed model is evaluated on four publicly available datasets, including Chest X-ray Pneumonia, COVID-19 Pneumonia, COVID-19 CTMaster, and VinBig data. The results demonstrate high accuracy and effectiveness, with 0.9925 on the Chest X-ray pneumonia dataset, 0.9895 on the COVID-19, Pneumonia and Normal Chest X-ray dataset, 0.9806 on the Covid CTMaster dataset, and 0.9398 on the VinBig dataset. We further evaluate the effectiveness of the proposed model using ROC curves, where the AUC for the best-performing model reaches 0.96. Our proposed model provides a promising tool for the early detection and accurate diagnosis of COVID-19, which can assist healthcare professionals in making informed treatment decisions and improving patient outcomes. The results of the proposed model are quite plausible and the system can be deployed in a clinical or research setting to assist in the diagnosis of COVID-19.

Keywords: COVID-19, feature engineering, artificial neural networks, radiology images

Procedia PDF Downloads 46

Authors: Animish Jain

Abstract:

This study deals with using Multiplicative Weight Update within artificial intelligence and machine learning to create models that can diagnose skin cancer using microscopic images of cancer samples. In this study, the multiplicative weight update method is used to take the predictions of multiple models to try and acquire more accurate results. Logistic Regression, Convolutional Neural Network (CNN), and Support Vector Machine Classifier (SVMC) models are employed within the Multiplicative Weight Update system. These models are trained on pictures of skin cancer from the ISIC-Archive, to look for patterns to label unseen scans as either benign or malignant. These models are utilized in a multiplicative weight update algorithm which takes into account the precision and accuracy of each model through each successive guess to apply weights to their guess. These guesses and weights are then analyzed together to try and obtain the correct predictions. The research hypothesis for this study stated that there would be a significant difference in the accuracy of the three models and the Multiplicative Weight Update system. The SVMC model had an accuracy of 77.88%. The CNN model had an accuracy of 85.30%. The Logistic Regression model had an accuracy of 79.09%. Using Multiplicative Weight Update, the algorithm received an accuracy of 72.27%. The final conclusion that was drawn was that there was a significant difference in the accuracy of the three models and the Multiplicative Weight Update system. The conclusion was made that using a CNN model would be the best option for this problem rather than a Multiplicative Weight Update system. This is due to the possibility that Multiplicative Weight Update is not effective in a binary setting where there are only two possible classifications. In a categorical setting with multiple classes and groupings, a Multiplicative Weight Update system might become more proficient as it takes into account the strengths of multiple different models to classify images into multiple categories rather than only two categories, as shown in this study. This experimentation and computer science project can help to create better algorithms and models for the future of artificial intelligence in the medical imaging field.

Keywords: artificial intelligence, machine learning, multiplicative weight update, skin cancer

Procedia PDF Downloads 51

Authors: Susan Diamond

Abstract:

Machine Learning workloads have traditionally been run in high-performance computing (HPC) environments, where users log in to dedicated machines and utilize the attached GPUs to run training jobs on huge datasets. Training of large neural network models is very resource intensive, and even after exploiting parallelism and accelerators such as GPUs, a single training job can still take days. Consequently, the cost of hardware is a barrier to entry. Even when upfront cost is not a concern, the lead time to set up such an HPC environment takes months from acquiring hardware to set up the hardware with the right set of firmware, software installed and configured. Furthermore, scalability is hard to achieve in a rigid traditional lab environment. Therefore, it is slow to react to the dynamic change in the artificial intelligent industry. Watson Deep Learning as a service, a cloud-based deep learning platform that mitigates the long lead time and high upfront investment in hardware. It enables robust and scalable sharing of resources among the teams in an organization. It is designed for on-demand cloud environments. Providing a similar user experience in a multi-tenant cloud environment comes with its own unique challenges regarding fault tolerance, performance, and security. Watson Deep Learning as a service tackles these challenges and present a deep learning stack for the cloud environments in a secure, scalable and fault-tolerant manner. It supports a wide range of deep-learning frameworks such as Tensorflow, PyTorch, Caffe, Torch, Theano, and MXNet etc. These frameworks reduce the effort and skillset required to design, train, and use deep learning models. Deep Learning as a service is used at IBM by AI researchers in areas including machine translation, computer vision, and healthcare. 

Keywords: deep learning, machine learning, cognitive computing, model training

Procedia PDF Downloads 185

Authors: A. Casale, J. Alessi, C. N. Bianchi, G. Bozzini, M. Brunoldi, V. Cappanera, P. Corvisiero, G. Fanciulli, D. Grosso, N. Magnoli, A. Mandich, C. Melchiorre, C. Morri, P. Povero, N. Stasi, M. Taiuti, G. Viano, M. Wurtz

Abstract:

This work describes a real-time algorithm for detecting, tracking and classifying single motorboats, developed using the acoustic data recorded by a hydrophone array within the framework of EU LIFE + project ARION (LIFE09NAT/IT/000190). The project aims to improve the conservation status of bottlenose dolphins through a real-time simultaneous monitoring of their population and surface ship traffic. A Passive Acoustic Monitoring (PAM) system is installed on two autonomous permanent marine buoys, located close to the boundaries of the Marine Protected Area (MPA) of Portofino (Ligurian Sea- Italy). Detecting surface ships is also a necessity in many other sensible areas, such as wind farms, oil platforms, and harbours. A PAM system could be an effective alternative to the usual monitoring systems, as radar or active sonar, for localizing unauthorized ship presence or illegal activities, with the advantage of not revealing its presence. Each ARION buoy consists of a particular type of structure, named meda elastica (elastic beacon) composed of a main pole, about 30-meter length, emerging for 7 meters, anchored to a mooring of 30 tons at 90 m depth by an anti-twist steel wire. Each buoy is equipped with a floating element and a hydrophone tetrahedron array, whose raw data are send via a Wi-Fi bridge to a ground station where real-time analysis is performed. Bottlenose dolphin detection algorithm and ship monitoring algorithm are operating in parallel and in real time. Three modules were developed and commissioned for ship monitoring. The first is the detection algorithm, based on Time Difference Of Arrival (TDOA) measurements, i.e., the evaluation of angular direction of the target respect to each buoy and the triangulation for obtaining the target position. The second is the tracking algorithm, based on a Kalman filter, i.e., the estimate of the real course and speed of the target through a predictor filter. At last, the classification algorithm is based on the DEMON method, i.e., the extraction of the acoustic signature of single vessels. The following results were obtained; the detection algorithm succeeded in evaluating the bearing angle with respect to each buoy and the position of the target, with an uncertainty of 2 degrees and a maximum range of 2.5 km. The tracking algorithm succeeded in reconstructing the real vessel courses and estimating the speed with an accuracy of 20% respect to the Automatic Identification System (AIS) signals. The classification algorithm succeeded in isolating the acoustic signature of single vessels, demonstrating its temporal stability and the consistency of both buoys results. As reference, the results were compared with the Hilbert transform of single channel signals. The algorithm for tracking multiple targets is ready to be developed, thanks to the modularity of the single ship algorithm: the classification module will enumerate and identify all targets present in the study area; for each of them, the detection module and the tracking module will be applied to monitor their course.

Keywords: acoustic-noise, bottlenose-dolphin, hydrophone, motorboat

Procedia PDF Downloads 142

Authors: Olga Smilevska Spasova, Katerina Boshkovska, Gorica Popova, Mirjana Popovska

Abstract:

Introduction: Pneumonia is an infection of the pulmonary parenchyma. HPIV 3 is one of four viruses that is a member of the Paramyxoviridae family designated types 1-4 that have a nonsegmented, single-stranded RNA genome with a lipid-containing envelope. They are spread from the respiratory tract by aerosolized secretions or by direct contact with secretions. Type 3 is endemic and can cause serious illness in immunocompromised patients. Illness caused by parainfluenza occurs shortly after inoculation with the virus. The level of immunoglobulin A antibody in serum is the best predictor of susceptibility to infection. Streptococcus pneumonia or pneumococcus is a Gram-positive, spherical bacteria, usually found in pairs and it is a member of the genus Streptococcus. Streptococcus pneumonia resides asymptomatically in healthy carriers typically colonizing the respiratory tract, sinuses, and nasal cavity. In individuals with weaker immune systems like young infants, pneumococcal bacterium is the most common cause of community-acquired pneumonia in the world. Case Report: The aim is to present a case of lower respiratory tract infection in an infant caused by parainfluenza virus 3, S. pneumonia and undifferentiated gram-negative bacteria that was successfully treated. The infant is with a history of recurrent episodes of wheezing in the past 3mounts.Infant of 10months presents 2weeks before admittance with high fever, runny nose, and cough. The primary pediatrician prescribed oral cefpodoxime for 10days and inhaled salbutamol. Two days before admittance in hospital the infant with high fever, cough, and difficulty breathing. At admittance, infant is pale, anxious with rapid respirations, cough, wheezing and tachycardia. On auscultation: vesicular breathing sounds with high pitched wheezing and on the right coarse crackles. Investigations: Blood analysis: RBC: 4, 7 x1012L, WBC: 8,3x109L: Neut: 42.73% Lym: 41.57%, Hgb: 9.38 g/dl MCV: 62.7fl, MCH: 20.0pg MCHC: 31.8 g/dl RDW: 18.7% Plt-307.9 x109LCRP: 2,5mg/l, serum iron-7.92umol/l, O2sat-97% on blood gas analysis, puls-125/min.X-ray of chest with hyperinflationand right pericardial consolidation. Microbiological analysis of sputum sample is positive for undifferentiated gram-negative bacteria (colonizer)–resistant to cefotaxime, ampicillin, cefoxitin, sulfamet.+trimetoprim and sensitive to amikacin, gentamicin, and ciprofloxacin. Molecular multiplex RT-PCR for 19 viruses and multiplex PCR for 7 bacteria test for respiratory pathogens positive for Parainfluenza virus 3(Ct=22.73), Streptococcus pneumonia (Ct=26.75).IED: IgG-9.31g/l, IgA-0.351g/l, IgM-0.86g/l. Therapy: Treatment was started with inhaled salbutamol, intravenous antibiotic cefotaxime as well as systemic corticosteroids. On day 7 because of slow clinical resolution of chest auscultation findings and an etiologic clue with a positive sputum sample for resistant undifferentiated gram negative bacteria, a second intravenous antibiotic was administered amikacin. The infant is discharged on day 14 with resolution of clinical findings. Conclusion: Mixed co-infections with respiratory viruses and bacteria in immunocompromised infants are likely to lead to a more severe form of community acquired pneumonia that will need hospitalization.

Keywords: HPIV- 3, infant, pneumonia, S. pneumonia, x-ray chest

Procedia PDF Downloads 53

Authors: Kiran Datta, Daniella Holland-Hart, Anthony Byrne

Abstract:

Introduction: Oesophago-gastric (OG) cancers are the fifth commonest in the UK, accounting for over 12,000 deaths each year. Most patients will present at later stages of the disease, with only 21% of patients with stage 4 disease surviving longer than a year. As a result, many patients are unsuitable for curative surgery and instead receive palliative treatment to improve prognosis and symptom burden. However, palliative chemotherapy can result in significant toxicity: almost half of the patients are unable to complete their chemotherapy regimen, with this proportion rising significantly in older and frailer patients. In addition, clinical trials often exclude older and frailer patients due to strict inclusion criteria, meaning there is limited evidence to guide which patients are most likely to benefit from palliative chemotherapy. Inappropriate chemotherapy administration is at odds with the goals of palliative treatment and care, which are to improve quality of life, and this also represents a significant resource expenditure. This literature review aimed to examine and appraise evidence regarding treatment resilience in order to guide clinicians in identifying the most suitable candidates for palliative chemotherapy. Factors influencing treatment resilience were assessed, as measured by completion rates, dose reductions, and toxicities. Methods: This literature review was conducted using rapid review methodology, utilising modified systematic methods. A literature search was performed across the MEDLINE, EMBASE, and Cochrane Library databases, with results limited to papers within the last 15 years and available in English. Key inclusion criteria included: 1) participants with either oesophageal, gastro-oesophageal junction, or gastric cancers; 2) patients treated with palliative chemotherapy; 3) available data evaluating the association between baseline participant characteristics and treatment resilience. Results: Of the 2326 papers returned, 11 reports of 10 studies were included in this review after excluding duplicates and irrelevant papers. Treatment resilience factors that were assessed included: age, performance status, frailty, inflammatory markers, and sarcopenia. Age was generally a poor predictor for how well patients would tolerate chemotherapy, while poor performance status was a better indicator of the need for dose reduction and treatment non-completion. Frailty was assessed across one cohort using multiple screening tools and was an effective marker of the risk of toxicity and the requirement for dose reduction. Inflammatory markers included lymphopenia and the Glasgow Prognostic Score, which assessed inflammation and hypoalbuminaemia. Although quick to obtain and interpret, these findings appeared less reliable due to the inclusion of patients treated with palliative radiotherapy. Sarcopenia and body composition were often associated with chemotherapy toxicity but not the rate of regimen completion. Conclusion: This review demonstrates that there are numerous measures that can estimate the ability of patients with oesophago-gastric cancer to tolerate palliative chemotherapy, and these should be incorporated into clinical assessments to promote personalised decision-making around treatment. Age should not be a barrier to receiving chemotherapy and older and frailer patients should be included in future clinical trials to better represent typical patients with oesophago-gastric cancers. Decisions regarding palliative treatment should be guided by these factors identified as well as patient preference.

Keywords: frailty, oesophago-gastric cancer, palliative chemotherapy, treatment resilience

Procedia PDF Downloads 49

Authors: Naoum Mylonas, Eugenia Petridou

Abstract:

Objectives: The objectives of this research are firstly, to develop an integrated model of predicting factors to new ventures performance, taking into account certain issues and specificities related to creative industry and female entrepreneurship based on the prior research; secondly, to determine the appropriate measures of venture performance in a creative industry context, drawing upon previous surveys; thirdly, to illustrate the importance of entrepreneurial orientation, networking ties, environment dynamism and access to financial capital on new ventures performance. Prior Work: An extant review of the creative industry literature highlights the special nature of entrepreneurship in this field. Entrepreneurs in creative industry share certain specific characteristics and intensions, such as to produce something aesthetic, to enrich their talents and their creativity, and to combine their entrepreneurial with their artistic orientation. Thus, assessing venture performance and success in creative industry entails an examination of how creative people or artists conceptualize success. Moreover, female entrepreneurs manifest more positive attitudes towards sectors primarily based on creativity, rather than innovation in which males outbalance. As creative industry entrepreneurship based mainly on the creative personality of the creator / artist, a high interest is accrued to examine female entrepreneurship in the creative industry. Hypotheses development: H1a: Female entrepreneurs who are more entrepreneurially-oriented show a higher financial performance. H1b: Female entrepreneurs who are more artistically-oriented show a higher creative performance. H2: Female entrepreneurs who have personality that is more creative perform better. H3: Female entrepreneurs who participate in or belong to networks perform better. H4: Female entrepreneurs who have been consulted by a mentor perform better. Η5a: Female entrepreneurs who are motivated more by pull-factors perform better. H5b: Female entrepreneurs who are motivated more by push-factors perform worse. Approach: A mixed method triangulation design has been adopted for the collection and analysis of data. The data are collected through a structured questionnaire for the quantitative part and through semi-structured interviews for the qualitative part as well. The sample is 293 Greek female entrepreneurs in the creative industry. Main findings: All research hypotheses are accepted. The majority of creative industry entrepreneurs evaluate themselves in creative performance terms rather than financial ones. The individuals who are closely related to traditional arts sectors have no EO but also evaluate themselves highly in terms of venture performance. Creative personality of creators is appeared as the most important predictor of venture performance. Pull factors in accordance with our hypothesis lead to higher levels of performance compared to push factors. Networking and mentoring are viewed as very important, particularly now during the turbulent economic environment in Greece. Implications-Value: Our research provides an integrated model with several moderating variables to predict ventures performance in the creative industry, taking also into account the complicated nature of arts and the way artists and creators define success. At the end, the findings may be used for the appropriate design of educational programs in creative industry entrepreneurship. This research has been co-financed by the European Union (European Social Fund – ESF) and Greek national funds through the Operational Program "Education and Lifelong Learning" of the National Strategic Reference Framework (NSRF) - Research Funding Program: Heracleitus II. Investing in knowledge society through the European Social Fund.

Keywords: venture performance, female entrepreneurship, creative industry, networks

Procedia PDF Downloads 241

Authors: Yongjiang Zhang, Kallol Barai, Umesh R. Hodeghatta, Trang Tran, Vikas Dhiman

Abstract:

Detecting water stress on crops early and accurately is crucial to minimize its impact. This study aims to measure water stress in wild blueberry crops non-destructively by analyzing proximal hyperspectral data. The data collection took place in the summer growing season of 2022. A drought experiment was conducted on wild blueberries in the randomized block design in the greenhouse, incorporating various genotypes and irrigation treatments. Hyperspectral data ( spectral range: 400-1000 nm) using a handheld spectroradiometer and leaf water potential data using a pressure chamber were collected from wild blueberry plants. Machine learning techniques, including multiple regression analysis and random forest models, were employed to predict leaf water potential (MPa). We explored the optimal wavelength bands for simple differences (RY1-R Y2), simple ratios (RY1/RY2), and normalized differences (|RY1-R Y2|/ (RY1-R Y2)). NDWI ((R857 - R1241)/(R857 + R1241)), SD (R2188 – R2245), and SR (R1752 / R1756) emerged as top predictors for predicting leaf water potential, significantly contributing to the highest model performance. The base learner models achieved an R-squared value of approximately 0.81, indicating their capacity to explain 81% of the variance. Research is underway to develop a neural vegetation index (NVI) that automates the process of index development by searching for specific wavelengths in the space ratio of linear functions of reflectance. The NVI framework could work across species and predict different physiological parameters.

Keywords: hyperspectral reflectance, water potential, spectral indices, machine learning, wild blueberries, optimal bands

Procedia PDF Downloads 46

Authors: Nicola Colaninno, Eugenio Morello

Abstract:

The urban environment affects local-to-global climate and, in turn, suffers global warming phenomena, with worrying impacts on human well-being, health, social and economic activities. Physic-morphological features of the built-up space affect urban air temperature, locally, causing the urban environment to be warmer compared to surrounding rural. This occurrence, typically known as the Urban Heat Island (UHI), is normally assessed by means of air temperature from fixed weather stations and/or traverse observations or based on remotely sensed Land Surface Temperatures (LST). The information provided by ground weather stations is key for assessing local air temperature. However, the spatial coverage is normally limited due to low density and uneven distribution of the stations. Although different interpolation techniques such as Inverse Distance Weighting (IDW), Ordinary Kriging (OK), or Multiple Linear Regression (MLR) are used to estimate air temperature from observed points, such an approach may not effectively reflect the real climatic conditions of an interpolated point. Quantifying local UHI for extensive areas based on weather stations’ observations only is not practicable. Alternatively, the use of thermal remote sensing has been widely investigated based on LST. Data from Landsat, ASTER, or MODIS have been extensively used. Indeed, LST has an indirect but significant influence on air temperatures. However, high-resolution near-surface air temperature (NSAT) is currently difficult to retrieve. Here we have experimented Geographically Weighted Regression (GWR) as an effective approach to enable NSAT estimation by accounting for spatial non-stationarity of the phenomenon. The model combines on-site measurements of air temperature, from fixed weather stations and satellite-derived LST. The approach is structured upon two main steps. First, a GWR model has been set to estimate NSAT at low resolution, by combining air temperature from discrete observations retrieved by weather stations (dependent variable) and the LST from satellite observations (predictor). At this step, MODIS data, from Terra satellite, at 1 kilometer of spatial resolution have been employed. Two time periods are considered according to satellite revisit period, i.e. 10:30 am and 9:30 pm. Afterward, the results have been downscaled at 30 meters of spatial resolution by setting a GWR model between the previously retrieved near-surface air temperature (dependent variable), the multispectral information as provided by the Landsat mission, in particular the albedo, and Digital Elevation Model (DEM) from the Shuttle Radar Topography Mission (SRTM), both at 30 meters. Albedo and DEM are now the predictors. The area under investigation is the Metropolitan City of Milan, which covers an area of approximately 1,575 km2 and encompasses a population of over 3 million inhabitants. Both models, low- (1 km) and high-resolution (30 meters), have been validated according to a cross-validation that relies on indicators such as R2, Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). All the employed indicators give evidence of highly efficient models. In addition, an alternative network of weather stations, available for the City of Milano only, has been employed for testing the accuracy of the predicted temperatures, giving and RMSE of 0.6 and 0.7 for daytime and night-time, respectively.

Keywords: urban climate, urban heat island, geographically weighted regression, remote sensing

Procedia PDF Downloads 171

Authors: Souvik Phadikar, Nidul Sinha, Rajdeep Ghosh

Abstract:

In brainwaves research using electroencephalogram (EEG) signals, finding the most relevant and effective feature set for identification of activities in the human brain is a big challenge till today because of the random nature of the signals. The feature extraction method is a key issue to solve this problem. Finding those features that prove to give distinctive pictures for different activities and similar for the same activities is very difficult, especially for the number of activities. The performance of a classifier accuracy depends on this quality of feature set. Further, more number of features result in high computational complexity and less number of features compromise with the lower performance. In this paper, a novel idea of the selection of optimal feature set using a heuristically optimized deep autoencoder is presented. Using various feature extraction methods, a vast number of features are extracted from the EEG signals and fed to the autoencoder deep neural network. The autoencoder encodes the input features into a small set of codes. To avoid the gradient vanish problem and normalization of the dataset, a meta-heuristic search algorithm is used to minimize the mean square error (MSE) between encoder input and decoder output. To reduce the feature set into a smaller one, 4 hidden layers are considered in the autoencoder network; hence it is called Heuristically Optimized Deep Autoencoder (HO-DAE). In this method, no features are rejected; all the features are combined into the response of responses of the hidden layer. The results reveal that higher accuracy can be achieved using optimal reduced features. The proposed HO-DAE is also compared with the regular autoencoder to test the performance of both. The performance of the proposed method is validated and compared with the other two methods recently reported in the literature, which reveals that the proposed method is far better than the other two methods in terms of classification accuracy.

Keywords: autoencoder, brainwave signal analysis, electroencephalogram, feature extraction, feature selection, optimization

Procedia PDF Downloads 95

Authors: Malik Muhammad Arslan, Muneeb Ullah, Dai Shihan, Daniyal Haider, Xiaodong Yang

Abstract:

Chest X-rays are instrumental in the detection and monitoring of a wide array of diseases, including viral infections such as COVID-19, tuberculosis, pneumonia, lung cancer, and various cardiac and pulmonary conditions. To enhance the accuracy of diagnosis, artificial intelligence (AI) algorithms, particularly deep learning models like Convolutional Neural Networks (CNNs), are employed. However, these deep learning models demand a substantial and varied dataset to attain optimal precision. Generative Adversarial Networks (GANs) can be employed to create new data, thereby supplementing the existing dataset and enhancing the accuracy of deep learning models. Nevertheless, GANs have their limitations, such as issues related to stability, convergence, and the ability to distinguish between authentic and fabricated data. In order to overcome these challenges and advance the detection and classification of CXR normal and abnormal images, this study introduces a distinctive technique known as DCWGAN (Diverse Conditional Wasserstein GAN) for generating synthetic chest X-ray (CXR) images. The study evaluates the effectiveness of this Idiosyncratic DCWGAN technique using the ResNet50 model and compares its results with those obtained using the traditional GAN approach. The findings reveal that the ResNet50 model trained on the DCWGAN-generated dataset outperformed the model trained on the classic GAN-generated dataset. Specifically, the ResNet50 model utilizing DCWGAN synthetic images achieved impressive performance metrics with an accuracy of 0.961, precision of 0.955, recall of 0.970, and F1-Measure of 0.963. These results indicate the promising potential for the early detection of diseases in CXR images using this Inimitable approach.

Keywords: CNN, classification, deep learning, GAN, Resnet50

Procedia PDF Downloads 54

Authors: Bikis Muhammed, Sehra Sedigh Sarvestani, Ali R. Hurson, Lasanthi Gamage

Abstract:

Vehicular traffic events have overly complex spatial correlations and temporal interdependencies and are also influenced by environmental events such as weather conditions. To capture these spatial and temporal interdependencies and make more realistic vehicular traffic predictions, graph neural networks (GNN) based traffic prediction models have been extensively utilized due to their capability of capturing non-Euclidean spatial correlation very effectively. However, most of the already existing GNN-based traffic prediction models have some limitations during learning complex and dynamic spatial and temporal patterns due to the following missing factors. First, most GNN-based traffic prediction models have used static distance or sometimes haversine distance mechanisms between spatially separated traffic observations to estimate spatial correlation. Secondly, most GNN-based traffic prediction models have not incorporated environmental events that have a major impact on the normal traffic states. Finally, most of the GNN-based models did not use an attention mechanism to focus on only important traffic observations. The objective of this paper is to study and make real-time vehicular traffic predictions while incorporating the effect of weather conditions. To fill the previously mentioned gaps, our prediction model uses a real-time driving distance between sensors to build a distance matrix or spatial adjacency matrix and capture spatial correlation. In addition, our prediction model considers the effect of six types of weather conditions and has an attention mechanism in both spatial and temporal data aggregation. Our prediction model efficiently captures the spatial and temporal correlation between traffic events, and it relies on the graph attention network (GAT) and Bidirectional bidirectional long short-term memory (Bi-LSTM) plus attention layers and is called GAT-BILSTMA.

Keywords: deep learning, real time prediction, GAT, Bi-LSTM, attention

Procedia PDF Downloads 49

Authors: Anika Chebrolu

Abstract:

Mono-targeted drugs can be of limited efficacy against complex diseases. Recently, multi-target drug design has been approached as a promising tool to fight against these challenging diseases. However, the scope of current computational approaches for multi-target drug design is limited. DeepLig presents a de-novo drug discovery platform that uses reinforcement learning to generate and optimize novel, potent, and multitargeted drug candidates against protein targets. DeepLig’s model consists of two networks in interplay: a generative network and a predictive network. The generative network, a Stack- Augmented Recurrent Neural Network, utilizes a stack memory unit to remember and recognize molecular patterns when generating novel ligands from scratch. The generative network passes each newly created ligand to the predictive network, which then uses multiple Graph Attention Networks simultaneously to forecast the average binding affinity of the generated ligand towards multiple target proteins. With each iteration, given feedback from the predictive network, the generative network learns to optimize itself to create molecules with a higher average binding affinity towards multiple proteins. DeepLig was evaluated based on its ability to generate multi-target ligands against two distinct proteins, multi-target ligands against three distinct proteins, and multi-target ligands against two distinct binding pockets on the same protein. With each test case, DeepLig was able to create a library of valid, synthetically accessible, and novel molecules with optimal and equipotent binding energies. We propose that DeepLig provides an effective approach to design multi-targeted drug therapies that can potentially show higher success rates during in-vitro trials.

Keywords: drug design, multitargeticity, de-novo, reinforcement learning

Procedia PDF Downloads 59

Authors: Cai J. T. Ladd, Mollie F. Duggan-Edwards, Tjeerd J. Bouma, Jordi F. Pages, Martin W. Skov

Abstract:

Salt marshes are valued for their role in coastal flood protection, carbon storage, and for supporting biodiverse ecosystems. As a biogeomorphic landscape, marshes evolve through the complex interactions between sea level rise, sediment supply and wave/current forcing, as well as and socio-economic factors. Climate change and direct human modification could lead to a global decline marsh extent if left unchecked. Whilst the processes of saltmarsh erosion and expansion are well understood, empirical evidence on the key drivers of long-term lateral marsh dynamics is lacking. In a GIS, saltmarsh areal extent in 25 estuaries across Great Britain was calculated from historical maps and aerial photographs, at intervals of approximately 30 years between 1846 and 2016. Data on the key perceived drivers of lateral marsh change (namely sea level rise rates, suspended sediment concentration, bedload sediment flux rates, and frequency of both river flood and storm events) were collated from national monitoring centres. Continuous datasets did not extend beyond 1970, therefore predictor variables that best explained rate change of marsh extent between 1970 and 2016 was calculated using a Partial Least Squares Regression model. Information about the spread of Spartina anglica (an invasive marsh plant responsible for marsh expansion around the globe) and coastal engineering works that may have impacted on marsh extent, were also recorded from historical documents and their impacts assessed on long-term, large-scale marsh extent change. Results showed that salt marshes in the northern regions of Great Britain expanded an average of 2.0 ha/yr, whilst marshes in the south eroded an average of -5.3 ha/yr. Spartina invasion and coastal engineering works could not explain these trends since a trend of either expansion or erosion preceded these events. Results from the Partial Least Squares Regression model indicated that the rate of relative sea level rise (RSLR) and availability of suspended sediment concentration (SSC) best explained the patterns of marsh change. RSLR increased from 1.6 to 2.8 mm/yr, as SSC decreased from 404.2 to 78.56 mg/l along the north-to-south gradient of Great Britain, resulting in the shift from marsh expansion to erosion. Regional differences in RSLR and SSC are due to isostatic rebound since deglaciation, and tidal amplitudes respectively. Marshes exposed to low RSLR and high SSC likely leads to sediment accumulation at the coast suitable for colonisation by marsh plants and thus lateral expansion. In contrast, high RSLR with are likely not offset deposition under low SSC, thus average water depth at the marsh edge increases, allowing larger wind-waves to trigger marsh erosion. Current global declines in sediment flux to the coast are likely to diminish the resilience of salt marshes to RSLR. Monitoring and managing suspended sediment supply is not common-place, but may be critical to mitigating coastal impacts from climate change.

Keywords: lateral saltmarsh dynamics, sea level rise, sediment supply, wave forcing

Procedia PDF Downloads 111

Authors: Mohammed Abu Shquier

Abstract:

This paper introduces a word segmentation method using the novel BP-LSTM-CRF architecture for processing semantic output training. The objective of web morphological analysis tools is to link a formal morpho-syntactic description to a lemma, along with morpho-syntactic information, a vocalized form, a vocalized analysis with morpho-syntactic information, and a list of paradigms. A key objective is to continuously enhance the proposed system through an inductive learning approach that considers semantic influences. The system is currently under construction and development based on data-driven learning. To evaluate the tool, an experiment on homograph analysis was conducted. The tool also encompasses the assumption of deep binary segmentation hypotheses, the arbitrary choice of trigram or n-gram continuation probabilities, language limitations, and morphology for both Modern Standard Arabic (MSA) and Dialectal Arabic (DA), which provide justification for updating this system. Most Arabic word analysis systems are based on the phonotactic morpho-syntactic analysis of a word transmitted using lexical rules, which are mainly used in MENA language technology tools, without taking into account contextual or semantic morphological implications. Therefore, it is necessary to have an automatic analysis tool taking into account the word sense and not only the morpho-syntactic category. Moreover, they are also based on statistical/stochastic models. These stochastic models, such as HMMs, have shown their effectiveness in different NLP applications: part-of-speech tagging, machine translation, speech recognition, etc. As an extension, we focus on language modeling using Recurrent Neural Network (RNN); given that morphological analysis coverage was very low in dialectal Arabic, it is significantly important to investigate deeply how the dialect data influence the accuracy of these approaches by developing dialectal morphological processing tools to show that dialectal variability can support to improve analysis.

Keywords: NLP, DL, ML, analyser, MSA, RNN, CNN

Procedia PDF Downloads 12

Authors: John E. Boberg, Steven J. Bourgeois

Abstract:

The decline in student engagement and motivation through the middle years is well documented and clearly associated with a decline in mathematics achievement that persists through high school. To combat this trend and, very often, to meet high-stakes accountability standards, a growing number of parents, teachers, and schools have implemented various methods to incentivize learning. However, according to Self-Determination Theory, forms of incentivized learning such as public praise, tangible rewards, or threats of punishment tend to undermine intrinsic motivation and learning. By focusing on external forms of motivation that thwart autonomy in children, adults also potentially threaten relatedness measures such as trust and emotional engagement. Furthermore, these controlling motivational techniques tend to promote shallow forms of cognitive engagement at the expense of more effective deep processing strategies. Therefore, any short-term gains in apparent engagement or test scores are overshadowed by long-term diminished motivation, resulting in inauthentic approaches to learning and lower achievement. The current study focuses on the relationships between student trust, engagement, and motivation during these crucial years as students transition from elementary to middle school. In order to test the effects of controlled motivational techniques on achievement in mathematics, this quantitative study was conducted on a convenience sample of 22 elementary and middle schools from a single public charter school district in the south-central United States. The study employed multi-source data from students (N = 1,054), parents (N = 7,166), and teachers (N = 356), along with student achievement data and contextual campus variables. Cross-sectional questionnaires were used to measure the students’ self-regulated learning, emotional and cognitive engagement, and trust in teachers. Parents responded to a single item on incentivizing the academic performance of their child, and teachers responded to a series of questions about their acceptance of various incentive strategies. Structural equation modeling (SEM) was used to evaluate model fit and analyze the direct and indirect effects of the predictor variables on achievement. Although a student’s trust in teacher positively predicted both emotional and cognitive engagement, none of these three predictors accounted for any variance in achievement in mathematics. The parents’ use of incentives, on the other hand, predicted a student’s perception of his or her controlled motivation, and these two variables had significant negative effects on achievement. While controlled motivation had the greatest effects on achievement, parental incentives demonstrated both direct and indirect effects on achievement through the students’ self-reported controlled motivation. Comparing upper elementary student data with middle-school student data revealed that controlling forms of motivation may be taking their toll on student trust and engagement over time. While parental incentives positively predicted both cognitive and emotional engagement in the younger sub-group, such forms of controlling motivation negatively predicted both trust in teachers and emotional engagement in the middle-school sub-group. These findings support the claims, posited by Self-Determination Theory, about the dangers of incentivizing learning. Short-term gains belie the underlying damage to motivational processes that lead to decreased intrinsic motivation and achievement. Such practices also appear to thwart basic human needs such as relatedness.

Keywords: controlled motivation, student engagement, incentivized learning, mathematics achievement, self-determination theory, student trust

Procedia PDF Downloads 192