Search results for: clinical prediction models

Authors: Belalia Douma Omar, Bakhta Boukhatem, Mohamed Ghrici

Abstract:

Self-compacting concrete (SCC) developed in Japan in the late 80s has enabled the construction industry to reduce demand on the resources, improve the work condition and also reduce the impact of environment by elimination of the need for compaction. Fuzzy logic (FL) approaches has recently been used to model some of the human activities in many areas of civil engineering applications. Especially from these systems in the model experimental studies, very good results have been obtained. In the present study, a model for predicting compressive strength of SCC containing various proportions of fly ash, as partial replacement of cement has been developed by using Adaptive Neuro-Fuzzy Inference System (ANFIS). For the purpose of building this model, a database of experimental data were gathered from the literature and used for training and testing the model. The used data as the inputs of fuzzy logic models are arranged in a format of five parameters that cover the total binder content, fly ash replacement percentage, water content, super plasticizer and age of specimens. The training and testing results in the fuzzy logic model have shown a strong potential for predicting the compressive strength of SCC containing fly ash in the considered range.

Keywords: self-compacting concrete, fly ash, strength prediction, fuzzy logic

Procedia PDF Downloads 331

Authors: D. I. George Amalarethinam, A. Emima

Abstract:

Educational Data Mining (EDM) is one of the newest topics to emerge in recent years, and it is concerned with developing methods for analyzing various types of data gathered from the educational circle. EDM methods and techniques with machine learning algorithms are used to extract meaningful and usable information from huge databases. For scientists and researchers, realistic applications of Machine Learning in the EDM sectors offer new frontiers and present new problems. One of the most important research areas in EDM is predicting student success. The prediction algorithms and techniques must be developed to forecast students' performance, which aids the tutor, institution to boost the level of student’s performance. This paper examines various classification techniques in prediction methods and data mining tools used in EDM.

Keywords: classification technique, data mining, EDM methods, prediction methods

Procedia PDF Downloads 114

Authors: Osung Im, Neha Yadav, Eui Hoon Lee, Joong Hoon Kim

Abstract:

Artificial Neural Network (ANN) approach is commonly used in lots of fields for forecasting. In water resources engineering, forecast of water level or inflow of reservoir is useful for various kind of purposes. Due to advantages of ANN, many papers were written for inflow prediction in river networks, but in this study, ANN is used in urban sewer networks. The growth of severe rain storm in Korea has increased flood damage severely, and the precipitation distribution is getting more erratic. Therefore, effective pump operation in pump station is an essential task for the reduction in urban area. If real time inflow of pump station reservoir can be predicted, it is possible to operate pump effectively for reducing the flood damage. This study used ANN model for pump station reservoir inflow prediction using upstream sewer depth data. For this study, rainfall events, sewer depth, and inflow into Banpo pump station reservoir between years of 2013-2014 were considered. Feed – Forward Back Propagation (FFBF), Cascade – Forward Back Propagation (CFBP), Elman Back Propagation (EBP) and Nonlinear Autoregressive Exogenous (NARX) were used as ANN model for prediction. A comparison of results with ANN model suggests that ANN is a powerful tool for inflow prediction using the sewer depth data.

Keywords: artificial neural network, forecasting, reservoir inflow, sewer depth

Procedia PDF Downloads 312

Authors: S. O. Oyamakin, A. U. Chukwu

Abstract:

Richard's growth equation being a generalized logistic growth equation was improved upon by introducing an allometric parameter using the hyperbolic sine function. The integral solution to this was called hyperbolic Richard's growth model having transformed the solution from deterministic to a stochastic growth model. Its ability in model prediction was compared with the classical Richard's growth model an approach which mimicked the natural variability of heights/diameter increment with respect to age and therefore provides a more realistic height/diameter predictions using the coefficient of determination (R2), Mean Absolute Error (MAE) and Mean Square Error (MSE) results. The Kolmogorov-Smirnov test and Shapiro-Wilk test was also used to test the behavior of the error term for possible violations. The mean function of top height/Dbh over age using the two models under study predicted closely the observed values of top height/Dbh in the hyperbolic Richard's nonlinear growth models better than the classical Richard's growth model.

Keywords: height, Dbh, forest, Pinus caribaea, hyperbolic, Richard's, stochastic

Procedia PDF Downloads 474

Authors: Ayat E. Ali, Christeen R. Aziz, Merna A. Helmy, Mohammed M. Malek, Sherif H. El-Gohary

Abstract:

Goal: Purpose of the project was to make a plastic surgery prediction by using pre-operative images for the plastic surgeries’ patients and to show this prediction on a screen to compare between the current case and the appearance after the surgery. Methods: To this aim, we implemented a software which used data from the internet for facial skin diseases, skin burns, pre-and post-images for plastic surgeries then the post- surgical prediction is done by using K-nearest neighbor (KNN). So we designed and fabricated a smart mirror divided into two parts a screen and a reflective mirror so patient's pre- and post-appearance will be showed at the same time. Results: We worked on some skin diseases like vitiligo, skin burns and wrinkles. We classified the three degrees of burns using KNN classifier with accuracy 60%. We also succeeded in segmenting the area of vitiligo. Our future work will include working on more skin diseases, classify them and give a prediction for the look after the surgery. Also we will go deeper into facial deformities and plastic surgeries like nose reshaping and face slim down. Conclusion: Our project will give a prediction relates strongly to the real look after surgery and decrease different diagnoses among doctors. Significance: The mirror may have broad societal appeal as it will make the distance between patient's satisfaction and the medical standards smaller.

Keywords: k-nearest neighbor (knn), face detection, vitiligo, bone deformity

Procedia PDF Downloads 157

Authors: Shayla He

Abstract:

Background and Purpose: According to Chamie (2017), it’s estimated that no less than 150 million people, or about 2 percent of the world’s population, are homeless. The homeless population in the United States has grown rapidly in the past four decades. In New York City, the sheltered homeless population has increased from 12,830 in 1983 to 62,679 in 2020. Knowing the trend on the homeless population is crucial at helping the states and the cities make affordable housing plans, and other community service plans ahead of time to better prepare for the situation. This study utilized the data from New York City, examined the key factors associated with the homelessness, and developed systematic modeling to predict homeless populations of the future. Using the best model developed, named HP-RNN, an analysis on the homeless population change during the months of 2020 and 2021, which were impacted by the COVID-19 pandemic, was conducted. Moreover, HP-RNN was tested on the data from Seattle. Methods: The methodology involves four phases in developing robust prediction methods. Phase 1 gathered and analyzed raw data of homeless population and demographic conditions from five urban centers. Phase 2 identified the key factors that contribute to the rate of homelessness. In Phase 3, three models were built using Linear Regression, Random Forest, and Recurrent Neural Network (RNN), respectively, to predict the future trend of society's homeless population. Each model was trained and tuned based on the dataset from New York City for its accuracy measured by Mean Squared Error (MSE). In Phase 4, the final phase, the best model from Phase 3 was evaluated using the data from Seattle that was not part of the model training and tuning process in Phase 3. Results: Compared to the Linear Regression based model used by HUD et al (2019), HP-RNN significantly improved the prediction metrics of Coefficient of Determination (R2) from -11.73 to 0.88 and MSE by 99%. HP-RNN was then validated on the data from Seattle, WA, which showed a peak %error of 14.5% between the actual and the predicted count. Finally, the modeling results were collected to predict the trend during the COVID-19 pandemic. It shows a good correlation between the actual and the predicted homeless population, with the peak %error less than 8.6%. Conclusions and Implications: This work is the first work to apply RNN to model the time series of the homeless related data. The Model shows a close correlation between the actual and the predicted homeless population. There are two major implications of this result. First, the model can be used to predict the homeless population for the next several years, and the prediction can help the states and the cities plan ahead on affordable housing allocation and other community service to better prepare for the future. Moreover, this prediction can serve as a reference to policy makers and legislators as they seek to make changes that may impact the factors closely associated with the future homeless population trend.

Keywords: homeless, prediction, model, RNN

Procedia PDF Downloads 118

Authors: Phang Moon Leng

Abstract:

Automated Early Warning Scores is a newly developed clinical decision tool that is used to streamline and improve the process of obtaining a patient’s vital signs so a clinical decision can be made at an earlier stage to prevent the patient from further deterioration. This technology provides immediate update on the score and clinical decision to be taken based on the outcome. This paper aims to study the use of an automated early warning score system on whether the technology has assisted the hospital in early detection and escalation of clinical condition and improve patient outcome. The hospital adopted the Modified Early Warning Scores (MEWS) Scoring System and MEWS Clinical Response into Philips IntelliVue Guardian Automated Early Warning Score equipment and studied whether the process has been leaned, whether the use of technology improved the usage & experience of the nurses, and whether the technology has improved patient care and outcome. It was found the steps required to obtain vital signs has been significantly reduced and is used more frequently to obtain patient vital signs. The number of deaths, and length of stay has significantly decreased as clinical decisions can be made and escalated more quickly with the Automated EWS. The automated early warning score equipment has helped improve work efficiency by removing the need for documenting into patient’s EMR. The technology streamlines clinical decision-making and allows faster care and intervention to be carried out and improves overall patient outcome which translates to better care for patient.

Keywords: automated early warning score, clinical quality and safety, patient safety, medical technology

Procedia PDF Downloads 175

Authors: Angeliki Peponi, Paulo Morgado, Jorge Trindade

Abstract:

Artificial Neural Networks (ANNs) and Geographic Information Systems (GIS) are applied as a robust tool for modeling and forecasting the erosion changes in Costa Caparica, Lisbon, Portugal, for 2021. ANNs present noteworthy advantages compared with other methods used for prediction and decision making in urban coastal areas. Multilayer perceptron type of ANNs was used. Sensitivity analysis was conducted on natural and social forces and dynamic relations in the dune-beach system of the study area. Variations in network’s parameters were performed in order to select the optimum topology of the network. The developed methodology appears fitted to reality; however further steps would make it better suited.

Keywords: artificial neural networks, backpropagation, coastal urban zones, erosion prediction

Procedia PDF Downloads 386

Authors: Marcio Freire Cruz, Naoaki Ono, Shigehiko Kanaya, Carlos Arthur Mattos Teixeira Cavalcante

Abstract:

The systems that record patient care information, known as Electronic Medical Record (EMR) and those that monitor vital signs of patients, such as heart rate, body temperature, and blood pressure have been extremely valuable for the effectiveness of the patient’s treatment. Several kinds of research have been using data from EMRs and vital signs of patients to predict illnesses. Among them, we highlight those that intend to predict, classify, or, at least identify patterns, of sepsis illness in patients under vital signs monitoring. Sepsis is an organic dysfunction caused by a dysregulated patient's response to an infection that affects millions of people worldwide. Early detection of sepsis is expected to provide a significant improvement in its treatment. Preceding works usually combined medical, statistical, mathematical and computational models to develop detection methods for early prediction, getting higher accuracies, and using the smallest number of variables. Among other techniques, we could find researches using survival analysis, specialist systems, machine learning and deep learning that reached great results. In our research, patients are modeled as points moving each hour in an n-dimensional space where n is the number of vital signs (variables). These points can reach a sepsis target point after some time. For now, the sepsis target point was calculated using the median of all patients’ variables on the sepsis onset. From these points, we calculate for each hour the position vector, the first derivative (velocity vector) and the second derivative (acceleration vector) of the variables to evaluate their behavior. And we construct a prediction model based on a Long Short-Term Memory (LSTM) Network, including these derivatives as explanatory variables. The accuracy of the prediction 6 hours before the time of sepsis, considering only the vital signs reached 83.24% and by including the vectors position, speed, and acceleration, we obtained 94.96%. The data are being collected from Medical Information Mart for Intensive Care (MIMIC) Database, a public database that contains vital signs, laboratory test results, observations, notes, and so on, from more than 60.000 patients.

Keywords: dynamic analysis, long short-term memory, prediction, sepsis

Procedia PDF Downloads 122

Authors: Zunaira Zaman, David Bohannon

Abstract:

This study explores the application of machine learning (ML) for detecting security vulnerabilities in source code. The research aims to assist organizations with large application portfolios and limited security testing capabilities in prioritizing security activities. ML-based approaches offer benefits such as increased confidence scores, false positives and negatives tuning, and automated feedback. The initial approach using natural language processing techniques to extract features achieved 86% accuracy during the training phase but suffered from overfitting and performed poorly on unseen datasets during testing. To address these issues, the study proposes using the abstract syntax tree (AST) for Java and C++ codebases to capture code semantics and structure and generate path-context representations for each function. The Code2Vec model architecture is used to learn distributed representations of source code snippets for training a machine-learning classifier for vulnerability prediction. The study evaluates the performance of the proposed methodology using two datasets and compares the results with existing approaches. The Devign dataset yielded 60% accuracy in predicting vulnerable code snippets and helped resist overfitting, while the Juliet Test Suite predicted specific vulnerabilities such as OS-Command Injection, Cryptographic, and Cross-Site Scripting vulnerabilities. The Code2Vec model achieved 75% accuracy and a 98% recall rate in predicting OS-Command Injection vulnerabilities. The study concludes that even partial AST representations of source code can be useful for vulnerability prediction. The approach has the potential for automated intelligent analysis of source code, including vulnerability prediction on unseen source code. State-of-the-art models using natural language processing techniques and CNN models with ensemble modelling techniques did not generalize well on unseen data and faced overfitting issues. However, predicting vulnerabilities in source code using machine learning poses challenges such as high dimensionality and complexity of source code, imbalanced datasets, and identifying specific types of vulnerabilities. Future work will address these challenges and expand the scope of the research.

Keywords: code embeddings, neural networks, natural language processing, OS command injection, software security, code properties

Procedia PDF Downloads 103

Authors: Vahid Nourani, Atefeh Ashrafi

Abstract:

Prediction of treated wastewater quality is a matter of growing importance in water treatment procedure. In this way artificial neural network (ANN), as a robust data-driven approach, has been widely used for forecasting the effluent quality of wastewater treatment. However, developing ANN model based on appropriate input variables is a major concern due to the numerous parameters which are collected from treatment process and the number of them are increasing in the light of electronic sensors development. Various studies have been conducted, using different clustering methods, in order to classify most related and effective input variables. This issue has been overlooked in the selecting dominant input variables among wastewater treatment parameters which could effectively lead to more accurate prediction of water quality. In the presented study two ANN models were developed with the aim of forecasting effluent quality of Tabriz city’s wastewater treatment plant. Biochemical oxygen demand (BOD) was utilized to determine water quality as a target parameter. Model A used Principal Component Analysis (PCA) for input selection as a linear variance-based clustering method. Model B used those variables identified by the mutual information (MI) measure. Therefore, the optimal ANN structure when the result of model B compared with model A showed up to 15% percent increment in Determination Coefficient (DC). Thus, this study highlights the advantage of PCA method in selecting dominant input variables for ANN modeling of wastewater plant efficiency performance.

Keywords: Artificial Neural Networks, biochemical oxygen demand, principal component analysis, mutual information, Tabriz wastewater treatment plant, wastewater treatment plant

Procedia PDF Downloads 125

Authors: Alfred L. Guiffrida

Abstract:

A review of the literature on supply chain delivery models which use delivery windows to measure delivery performance is presented. The review herein serves to meet the following objectives: (i) provide a synthesis of previously published literature on supply chain delivery performance models, (ii) provide in one paper a consolidation of research that can serve as a single source to keep researchers up to date with the research developments in supply chain delivery models, and (iii) identify gaps in the modeling of supply chain delivery performance which could stimulate new research agendas.

Keywords: delivery performance, delivery window, supply chain delivery models, supply chain performance

Procedia PDF Downloads 416

Authors: Jamshid Qodirov, Sirojiddin Komolov, Ravilov Mirahmad, Olimjon Mirzayev

Abstract:

Nowadays, natural language processing tools play a crucial role in our daily lives, including various techniques with text processing. There are very advanced models in modern languages, such as English, Russian etc. But, in some languages, such as Uzbek, the NLP models have been developed recently. Thus, there are only a few NLP models in Uzbek language. Moreover, there is no such work that could show which Uzbek NLP model behaves in different situations and when to use them. This work tries to close this gap and compares the Uzbek NLP models existing as of the time this article was written. The authors try to compare the NLP models in two different scenarios: sentiment analysis and sentence similarity, which are the implementations of the two most common problems in the industry: classification and similarity. Another outcome from this work is two datasets for classification and sentence similarity in Uzbek language that we generated ourselves and can be useful in both industry and academia as well.

Keywords: NLP, benchmak, bert, vectorization

Procedia PDF Downloads 50

Authors: Salman Mohamadi, Seyed Mohammad Ali Tayaranian Hosseini, Hamidreza Amindavar

Abstract:

In this paper, we provide a procedure to analyze and model EEG (electroencephalogram) signal as a time series using ARIMA-GARCH to predict an epileptic attack. The heteroskedasticity of EEG signal is examined through the ARCH or GARCH, (Autore- gressive conditional heteroskedasticity, Generalized autoregressive conditional heteroskedasticity) test. The best ARIMA-GARCH model in AIC sense is utilized to measure the volatility of the EEG from epileptic canine subjects, to forecast the future values of EEG. ARIMA-only model can perform prediction, but the ARCH or GARCH model acting on the residuals of ARIMA attains a con- siderable improved forecast horizon. First, we estimate the best ARIMA model, then different orders of ARCH and GARCH modelings are surveyed to determine the best heteroskedastic model of the residuals of the mentioned ARIMA. Using the simulated conditional variance of selected ARCH or GARCH model, we suggest the procedure to predict the oncoming seizures. The results indicate that GARCH modeling determines the dynamic changes of variance well before the onset of seizure. It can be inferred that the prediction capability comes from the ability of the combined ARIMA-GARCH modeling to cover the heteroskedastic nature of EEG signal changes.

Keywords: epileptic seizure prediction , ARIMA, ARCH and GARCH modeling, heteroskedasticity, EEG

Procedia PDF Downloads 402

Authors: Samuel Oluwafemi Oyamakin, Angela Unna Chukwu

Abstract:

Richrads growth equation being a generalized logistic growth equation was improved upon by introducing an allometric parameter using the hyperbolic sine function. The integral solution to this was called hyperbolic Richards growth model having transformed the solution from deterministic to a stochastic growth model. Its ability in model prediction was compared with the classical Richards growth model an approach which mimicked the natural variability of heights/diameter increment with respect to age and therefore provides a more realistic height/diameter predictions using the coefficient of determination (R2), Mean Absolute Error (MAE) and Mean Square Error (MSE) results. The Kolmogorov-Smirnov test and Shapiro-Wilk test was also used to test the behavior of the error term for possible violations. The mean function of top height/Dbh over age using the two models under study predicted closely the observed values of top height/Dbh in the hyperbolic Richards nonlinear growth models better than the classical Richards growth model.

Keywords: height, diameter at breast height, DBH, hyperbolic sine function, Pinus caribaea, Richards' growth model

Procedia PDF Downloads 387

Authors: Paul Han, Jun-Geol Baek

Abstract:

In the flat panel display industry, the scheduler and dispatching system to meet production target quantities and the deadline of production are the major production management system which controls each facility production order and distribution of WIP (Work in Process). In dispatching system, delivery time is a key factor for the time when a lot can be supplied to the facility. In this paper, we use survival analysis methods to identify main factors and a forecasting model of delivery time. Of survival analysis techniques to select important explanatory variables, the cox proportional hazard model is used to. To make a prediction model, the Accelerated Failure Time (AFT) model was used. Performance comparisons were conducted with two other models, which are the technical statistics model based on transfer history and the linear regression model using same explanatory variables with AFT model. As a result, the Mean Square Error (MSE) criteria, the AFT model decreased by 33.8% compared to the existing prediction model, decreased by 5.3% compared to the linear regression model. This survival analysis approach is applicable to implementing a delivery time estimator in display manufacturing. And it can contribute to improve the productivity and reliability of production management system.

Keywords: delivery time, survival analysis, Cox PH model, accelerated failure time model

Procedia PDF Downloads 536

Authors: Maryam Kheirollahpour, Mahmoud Danaee, Amir Faisal Merican, Asma Ahmad Shariff

Abstract:

Background: The presence of nonlinearity among the risk factors of eating behavior causes a bias in the prediction models. The accuracy of estimation of eating behaviors risk factors in the primary prevention of obesity has been established. Objective: The aim of this study was to explore the potential of a hybrid model of structural equation modeling (SEM) and Artificial Neural Networks (ANN) to predict eating behaviors. Methods: The Partial Least Square-SEM (PLS-SEM) and a hybrid model (SEM-Artificial Neural Networks (SEM-ANN)) were applied to evaluate the factors affecting eating behavior patterns among university students. 340 university students participated in this study. The PLS-SEM analysis was used to check the effect of emotional eating scale (EES), body shape concern (BSC), and body appreciation scale (BAS) on different categories of eating behavior patterns (EBP). Then, the hybrid model was conducted using multilayer perceptron (MLP) with feedforward network topology. Moreover, Levenberg-Marquardt, which is a supervised learning model, was applied as a learning method for MLP training. The Tangent/sigmoid function was used for the input layer while the linear function applied for the output layer. The coefficient of determination (R²) and mean square error (MSE) was calculated. Results: It was proved that the hybrid model was superior to PLS-SEM methods. Using hybrid model, the optimal network happened at MPLP 3-17-8, while the R² of the model was increased by 27%, while, the MSE was decreased by 9.6%. Moreover, it was found that which one of these factors have significantly affected on healthy and unhealthy eating behavior patterns. The p-value was reported to be less than 0.01 for most of the paths. Conclusion/Importance: Thus, a hybrid approach could be suggested as a significant methodological contribution from a statistical standpoint, and it can be implemented as software to be able to predict models with the highest accuracy.

Keywords: hybrid model, structural equation modeling, artificial neural networks, eating behavior patterns

Procedia PDF Downloads 147

Authors: Danny Barash

Abstract:

Riboswitches are RNA genetic control elements that were originally discovered in bacteria and provide a unique mechanism of gene regulation. They work without the participation of proteins and are believed to represent ancient regulatory systems in the evolutionary timescale. One of the biggest challenges in riboswitch research is that many are found in prokaryotes but only a small percentage of known riboswitches have been found in certain eukaryotic organisms. The few examples of eukaryotic riboswitches were identified using sequence-based bioinformatics search methods that include some slight structural considerations. These pattern-matching methods were the first ones to be applied for the purpose of riboswitch detection and they can also be programmed very efficiently using a data structure called affix arrays, making them suitable for genome-wide searches of riboswitch patterns. However, they are limited by their ability to detect harder to find riboswitches that deviate from the known patterns. Several methods have been developed since then to tackle this problem. The most commonly used by practitioners is Infernal that relies on Hidden Markov Models (HMMs) and Covariance Models (CMs). Profile Hidden Markov Models were also carried out in the pHMM Riboswitch Scanner web application, independently from Infernal. Other computational approaches that have been developed include RMDetect by the use of 3D structural modules and RNAbor that utilizes Boltzmann probability of structural neighbors. We have tried to incorporate more sophisticated secondary structure considerations based on RNA folding prediction using several strategies. The first idea was to utilize window-based methods in conjunction with folding predictions by energy minimization. The moving window approach is heavily geared towards secondary structure consideration relative to sequence that is treated as a constraint. However, the method cannot be used genome-wide due to its high cost because each folding prediction by energy minimization in the moving window is computationally expensive, enabling to scan only at the vicinity of genes of interest. The second idea was to remedy the inefficiency of the previous approach by constructing a pipeline that consists of inverse RNA folding considering RNA secondary structure, followed by a BLAST search that is sequence-based and highly efficient. This approach, which relies on inverse RNA folding in general and our own in-house fragment-based inverse RNA folding program called RNAfbinv in particular, shows capability to find attractive candidates that are missed by Infernal and other standard methods being used for riboswitch detection. We demonstrate attractive candidates found by both the moving-window approach and the inverse RNA folding approach performed together with BLAST. We conclude that structure-based methods like the two strategies outlined above hold considerable promise in detecting riboswitches and other conserved RNAs of functional importance in a variety of organisms.

Keywords: riboswitches, RNA folding prediction, RNA structure, structure-based methods

Procedia PDF Downloads 233

Authors: Shenlun Chen, Leonard Wee

Abstract:

Tumor grading is an essential reference for colorectal cancer (CRC) staging and survival prognostication. The widely used World Health Organization (WHO) grading system defines histological grade of CRC adenocarcinoma based on the density of glandular formation on whole slide images (WSI). Tumors are classified as well-, moderately-, poorly- or un-differentiated depending on the percentage of the tumor that is gland forming; >95%, 50-95%, 5-50% and <5%, respectively. However, manually grading WSIs is a time-consuming process and can cause observer error due to subjective judgment and unnoticed regions. Furthermore, pathologists’ grading is usually coarse while a finer and continuous differentiation grade may help to stratifying CRC patients better. In this study, a deep learning based automatic differentiation grading algorithm was developed and evaluated by survival analysis. Firstly, a gland segmentation model was developed for segmenting gland structures. Gland regions of WSIs were delineated and used for differentiation annotating. Tumor regions were annotated by experienced pathologists into high-, medium-, low-differentiation and normal tissue, which correspond to tumor with clear-, unclear-, no-gland structure and non-tumor, respectively. Then a differentiation prediction model was developed on these human annotations. Finally, all enrolled WSIs were processed by gland segmentation model and differentiation prediction model. The differentiation grade can be calculated by deep learning models’ prediction of tumor regions and tumor differentiation status according to WHO’s defines. If multiple WSIs were possessed by a patient, the highest differentiation grade was chosen. Additionally, the differentiation grade was normalized into scale between 0 to 1. The Cancer Genome Atlas, project COAD (TCGA-COAD) project was enrolled into this study. For the gland segmentation model, receiver operating characteristic (ROC) reached 0.981 and accuracy reached 0.932 in validation set. For the differentiation prediction model, ROC reached 0.983, 0.963, 0.963, 0.981 and accuracy reached 0.880, 0.923, 0.668, 0.881 for groups of low-, medium-, high-differentiation and normal tissue in validation set. Four hundred and one patients were selected after removing WSIs without gland regions and patients without follow up data. The concordance index reached to 0.609. Optimized cut off point of 51% was found by “Maxstat” method which was almost the same as WHO system’s cut off point of 50%. Both WHO system’s cut off point and optimized cut off point performed impressively in Kaplan-Meier curves and both p value of logrank test were below 0.005. In this study, gland structure of WSIs and differentiation status of tumor regions were proven to be predictable through deep leaning method. A finer and continuous differentiation grade can also be automatically calculated through above models. The differentiation grade was proven to stratify CAC patients well in survival analysis, whose optimized cut off point was almost the same as WHO tumor grading system. The tool of automatically calculating differentiation grade may show potential in field of therapy decision making and personalized treatment.

Keywords: colorectal cancer, differentiation, survival analysis, tumor grading

Procedia PDF Downloads 133

Authors: Adrian Kong, William Chang, Rolando Valdes, Alec Rodriguez, Roberto Miki

Abstract:

The Pneumask consists of a custom snorkel-specific adapter that attaches a snorkel-port of the mask to a 3D-printed filter. This full-face snorkel mask was designed for use as personal protective equipment (PPE) during the COVID-19 pandemic when there was a widespread shortage of PPE for medical personnel. Various clinical validation tests have been conducted, including the sealing capability of the mask, filter performance, CO2 buildup, and clinical usability. However, data regarding the filter efficiencies of Pneumask and multiple filter types have not been determined. Using an experimental system, we evaluated the filtration efficiency across various masks and filters during inhalation. Eighteen combinations of respirator models (5 P100 FFRs, 4 Dolfino Masks) and filters (2091, 7093, 7093CN, BB50T) were evaluated for their exposure to airborne particles sized 0.3 - 10.0 microns using an electronic airborne particle counter. All respirator model combinations provided similar performance levels for 1.0-micron, 3.0-micron, 5.0-micron, 10.0-microns, with the greatest differences in the 0.3-micron and 0.5-micron range. All models provided expected performances against all particle sizes, with Class P100 respirators providing the highest performance levels across all particle size ranges. In conclusion, the modified snorkel mask has the potential to protect providers who care for patients with COVID-19 from increased airborne particle exposure.

Keywords: COVID-19, PPE, mask, filtration, efficiency

Procedia PDF Downloads 163

Authors: Arian Hosseini, Mahmudul Hasan

Abstract:

To address the increasing need for efficient and accurate content moderation, we propose an efficient and lightweight deep classification ensemble structure. Our approach is based on a combination of simple visual features, designed for high-accuracy classification of violent content with low false positives. Our ensemble architecture utilizes a set of lightweight models with narrowed-down color features, and we apply it to both images and videos. We evaluated our approach using a large dataset of explosion and blast contents and compared its performance to popular deep learning models such as ResNet-50. Our evaluation results demonstrate significant improvements in prediction accuracy, while benefiting from 7.64x faster inference and lower computation cost. While our approach is tailored to explosion detection, it can be applied to other similar content moderation and violence detection use cases as well. Based on our experiments, we propose a "think small, think many" philosophy in classification scenarios. We argue that transforming a single, large, monolithic deep model into a verification-based step model ensemble of multiple small, simple, and lightweight models with narrowed-down visual features can possibly lead to predictions with higher accuracy.

Keywords: deep classification, content moderation, ensemble learning, explosion detection, video processing

Procedia PDF Downloads 48

Authors: Jacob Nortey

Abstract:

Introduction: In recent years, there has been an enormous success in discoveries of scientific knowledge in medicine coupled with the advancement of technology. Despite all these successes, diagnoses and treatment of diseases have become complex. According to the Ibero – American Study of Adverse Effects (IBEAS), about 10% of hospital patients suffer from secondary damage during the care process, and approximately 2% die from this process. Many clinical decision support systems have been developed to help mitigate some healthcare medical errors. Method: Relevant databases were searched, including ones that were peculiar to the clinical decision support system (that is, using google scholar, Pub Med and general google searches). The articles were then screened for a comprehensive overview of the functionality, consultative style and statistical usage of Dxplain Clinical decision support systems. Results: Inferences drawn from the articles showed high usage of Dxplain clinical decision support system for problem-based learning among students in developed countries as against little or no usage among students in Low – and Middle – income Countries. The results also indicated high usage among general practitioners. Conclusion: Despite the challenges Dxplain presents, the benefits of its usage to clinicians and students are enormous.

Keywords: dxplain, clinical decision support sytem, diagnosis, support systems

Procedia PDF Downloads 76

Authors: Mohammad Namazi, Mohammad Sadeghzadeh Maharluie

Abstract:

Predicting earnings management is vital for the capital market participants, financial analysts and managers. The aim of this research is attempting to respond to this query: Is there a significant difference between the regression model and neural networks’ models in predicting earnings management, and which one leads to a superior prediction of it? In approaching this question, a Linear Regression (LR) model was compared with two neural networks including Multi-Layer Perceptron (MLP), and Generalized Regression Neural Network (GRNN). The population of this study includes 94 listed companies in Tehran Stock Exchange (TSE) market from 2003 to 2011. After the results of all models were acquired, ANOVA was exerted to test the hypotheses. In general, the summary of statistical results showed that the precision of GRNN did not exhibit a significant difference in comparison with MLP. In addition, the mean square error of the MLP and GRNN showed a significant difference with the multi variable LR model. These findings support the notion of nonlinear behavior of the earnings management. Therefore, it is more appropriate for capital market participants to analyze earnings management based upon neural networks techniques, and not to adopt linear regression models.

Keywords: earnings management, generalized linear regression, neural networks multi-layer perceptron, Tehran stock exchange

Procedia PDF Downloads 418

Authors: L. Ramirez, E. Guillén, J. Sánchez

Abstract:

Some of the main goals about telecare such as monitoring, treatment, telediagnostic are deployed with the integration of applications with specific appliances. In order to achieve a coherent model to integrate software, hardware, and healthcare systems, different telehealth models with Internet of Things (IoT), cloud computing, artificial intelligence, etc. have been implemented, and their advantages are still under analysis. In this paper, we propose an integrated model based on IoT architecture and cloud computing telehealth center. Analytics module is presented as a solution to control an ideal diagnostic about some diseases. Specific features are then compared with the recently deployed conventional models in telemedicine. The main advantage of this model is the availability of controlling the security and privacy about patient information and the optimization on processing and acquiring clinical parameters according to technical characteristics.

Keywords: analytics, telemedicine, internet of things, cloud computing

Procedia PDF Downloads 322

Authors: Belkacem Laimouche

Abstract:

With the field of artificial intelligence (AI) experiencing exponential growth, fueled by technological advancements that pave the way for increasingly innovative and promising applications, there is an escalating need to develop rigorous methods for assessing their performance in pursuit of transparency and equity. This article proposes a metrology-inspired statistical framework for evaluating bias and explainability in AI systems. Drawing from the principles of metrology, we propose a pioneering approach, using a concrete example, to evaluate the accuracy and precision of AI models, as well as to quantify the sources of measurement uncertainty that can lead to bias in their predictions. Furthermore, we explore a statistical approach for evaluating the explainability of AI systems based on their ability to provide interpretable and transparent explanations of their predictions.

Keywords: artificial intelligence, metrology, measurement uncertainty, prediction error, bias, machine learning algorithms, probabilistic models, interlaboratory comparison, data analysis, data reliability, measurement of bias impact on predictions, improvement of model accuracy and reliability

Procedia PDF Downloads 103

Authors: Ergin Toros, Manar Aslan

Abstract:

This study was planned as a descriptive study in order to learn the opinions of the students who are studying in nursing undergraduate program about their theoretical/practical lessons and departments. The education in the undergraduate nursing programs has great importance because it contains the knowledge and skills to prepare student nurses to the clinic in the future. In order to provide quality-nursing services in the future, the quality of nursing education should be measured, and opinions of student nurses about education should be taken. The research population was composed of students educated in a university with 1-4 years of theoretical and clinical education (N=550), and the sample was composed of 460 students that accepted to take part in the study. It was reached to 83.6% of target population. Data collected through a survey developed by the researchers. Survey consists of 48 questions about sociodemographic characteristics (9 questions), theoretical courses (9 questions), laboratory applications (7 questions), clinical education (14 questions) and services provided by the faculty (9 questions). It was determined that 83.3% of the nursing students found the nursing profession to be suitable for them, 53% of them selected nursing because of easy job opportunity, and 48.9% of them stayed in state dormitory. Regarding the theoretical courses, 84.6% of the students were determined to agree that the question ‘Course schedule is prepared before the course and published on the university web page.’ 28.7% of them were determined to do not agree that the question ‘Feedback is given to students about the assignments they prepare.’. It has been determined that 41,5% of the students agreed that ‘The time allocated to laboratory applications is sufficient.’ Students said that physical conditions in laboratory (41,5%), and the materials used are insufficient (44.6%), and ‘The number of students in the group is not appropriate for laboratory applications.’ (45.2%). 71.3% of the students think that the nurses view in the clinics the students as a tool to remove the workload, 40.7% of them reported that nurses in the clinic area did not help through the purposes of the course, 39.6% of them said that nurses' communication with students is not good. 37.8% of students stated that nurses did not provide orientation to students, 37.2% of them think that nurses are not role models for students. 53.7% of the students stated that the incentive and support for the student exchange program were insufficient., %48 of the students think that career planning services, %47.2 security services,%45.4 the advisor spent time with students are not enough. It has been determined that nursing students are most disturbed by the approach of the nurses in the clinical area within the undergraduate education program. The clinical area education which is considered as an integral part of nursing education is important and affect to student satisfaction.

Keywords: nursing education, student, clinical area, opinion

Procedia PDF Downloads 173

Authors: Binger Lu

Abstract:

It remains unclear whether second language (L2) speakers could use discourse context cues to predict upcoming information as native speakers do during online comprehension. Some researchers propose that L2 learners may have a reduced ability to generate predictions during discourse processing. At the same time, there is evidence that discourse-level cues are weighed more heavily in L2 processing than in L1. Previous studies showed that L1 prediction is sensitive to the global validity of predictive cues. The current study aims to explore whether and to what extent L2 learners can dynamically and strategically adjust their prediction in accord with the global validity of predictive cues in L2 discourse comprehension as native speakers do. In a self-paced reading experiment, Chinese native speakers (N=128), C-E bilinguals (N=128), and English native speakers (N=128) read high-predictable (e.g., Jimmy felt thirsty after running. He wanted to get some water from the refrigerator.) and low-predictable (e.g., Jimmy felt sick this morning. He wanted to get some water from the refrigerator.) discourses in two-sentence frames. The global validity of predictive cues was manipulated by varying the ratio of predictable (e.g., Bill stood at the door. He opened it with the key.) and unpredictable fillers (e.g., Bill stood at the door. He opened it with the card.), such that across conditions, the predictability of the final word of the fillers ranged from 100% to 0%. The dependent variable was reading time on the critical region (the target word and the following word), analyzed with linear mixed-effects models in R. C-E bilinguals showed reliable prediction across all validity conditions (β = -35.6 ms, SE = 7.74, t = -4.601, p< .001), and Chinese native speakers showed significant effect (β = -93.5 ms, SE = 7.82, t = -11.956, p< .001) in two of the four validity conditions (namely, the High-validity and MedLow conditions, where fillers ended with predictable words in 100% and 25% cases respectively), whereas English native speakers didn’t predict at all (β = -2.78 ms, SE = 7.60, t = -.365, p = .715). There was neither main effect (χ^²(3) = .256, p = .968) nor interaction (Predictability: Background: Validity, χ^²(3) = 1.229, p = .746; Predictability: Validity, χ^²(3) = 2.520, p = .472; Background: Validity, χ^²(3) = 1.281, p = .734) of Validity with speaker groups. The results suggest that prediction occurs in L2 discourse processing but to a much less extent in L1, witha significant effect in some conditions of L1 Chinese and anull effect in L1 English processing, consistent with the view that L2 speakers are more sensitive to discourse cues compared with L1 speakers. Additionally, the pattern of L1 and L2 predictive processing was not affected by the global validity of predictive cues. C-E bilinguals’ predictive processing could be partly transferred from their L1, as prior research showed that discourse information played a more significant role in L1 Chinese processing.

Keywords: bilingualism, discourse processing, global validity, prediction, self-paced reading

Procedia PDF Downloads 137

Authors: Kuo-Chun Chien, Chia-Hui Chang, Ren-Der Sun

Abstract:

Legal Judgment Prediction (LJP) is a subtask for legal AI. Its main purpose is to use the facts of a case to predict the judgment result. In Taiwan's criminal procedure, when prosecutors complete the investigation of the case, they will decide whether to prosecute the suspect and which article of criminal law should be used based on the facts and evidence of the case. In this study, we collected 305,240 indictments from the public inquiry system of the procuratorate of the Ministry of Justice, which included 169 charges and 317 articles from 21 laws. We take the crime facts in the indictments as the main input to jointly learn the prediction model for law source, article, and charge simultaneously based on the pre-trained Bert model. For single article cases where the frequency of the charge and article are greater than 50, the prediction performance of law sources, articles, and charges reach 97.66, 92.22, and 60.52 macro-f1, respectively. To understand the big performance gap between articles and charges, we used a bipartite graph to visualize the relationship between the articles and charges, and found that the reason for the poor prediction performance was actually due to the wording precision. Some charges use the simplest words, while others may include the perpetrator or the result to make the charges more specific. For example, Article 284 of the Criminal Law may be indicted as “negligent injury”, "negligent death”, "business injury", "driving business injury", or "non-driving business injury". As another example, Article 10 of the Drug Hazard Control Regulations can be charged as “Drug Control Regulations” or “Drug Hazard Control Regulations”. In order to solve the above problems and more accurately predict the article and charge, we plan to include the article content or charge names in the input, and use the sentence-pair classification method for question-answer problems in the BERT model to improve the performance. We will also consider a sequence-to-sequence approach to charge prediction.

Keywords: legal judgment prediction, deep learning, natural language processing, BERT, data visualization

Procedia PDF Downloads 118

Authors: Josip Arneric, Blanka Skrabic Peric

Abstract:

Forecasting of volatility, i.e. returns fluctuations, has been a topic of interest to portfolio managers, option traders and market makers in order to get higher profits or less risky positions. Based on the fact that volatility is time varying in high frequency data and that periods of high volatility tend to cluster, the most common used models are GARCH type models. As standard GARCH models show high volatility persistence, i.e. integrated behaviour of the conditional variance, it is difficult the predict volatility using standard GARCH models. Due to practical limitations of these models different approaches have been proposed in the literature, based on Markov switching models. In such situations models in which the parameters are allowed to change over time are more appropriate because they allow some part of the model to depend on the state of the economy. The empirical analysis demonstrates that Markov switching GARCH model resolves the problem of excessive persistence and outperforms uni-regime GARCH models in forecasting volatility for selected emerging markets.

Keywords: emerging markets, Markov switching, GARCH model, transition probabilities

Procedia PDF Downloads 451

Authors: Mehdi Mirzaei Alavijeh, Farzad Jalilian

Abstract:

Background: Marijuana is the most widely used illicit drug worldwide, especially among adolescents and young adults, which can cause numerous complications. The aim of this study was to determine the pattern, motivation use, and factors related to marijuana use among Iranian youths based on the integrative model of behavioral prediction Methods: A cross-sectional study was conducted among 174 youths marijuana user in Kermanshah County and Isfahan County, during summer 2014 which was selected with the convenience sampling for participation in this study. A self-reporting questionnaire was applied for collecting data. Data were analyzed by SPSS version 21 using bivariate correlations and linear regression statistical tests. Results: The mean marijuana use of respondents was 4.60 times at during week [95% CI: 4.06, 5.15]. Linear regression statistical showed, the structures of integrative model of behavioral prediction accounted for 36% of the variation in the outcome measure of the marijuana use at during week (R2 = 36% & P < 0.001); and among them attitude, marijuana refuse, and subjective norms were a stronger predictors. Conclusion: Comprehensive health education and prevention programs need to emphasize on cognitive factors that predict youth’s health-related behaviors. Based on our findings it seems, designing educational and behavioral intervention for reducing positive belief about marijuana, marijuana self-efficacy refuse promotion and reduce subjective norms encourage marijuana use has an effective potential to protect youths marijuana use.

Keywords: marijuana, youth, integrative model of behavioral prediction, Iran

Procedia PDF Downloads 552