Search results for: prediction model accuracy

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 99

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: V. Rashtchi, H. Bizhani, F. R. Tatari

Abstract:

This paper presents a new online loss minimization for an induction motor drive. Among the many loss minimization algorithms (LMAs) for an induction motor, a particle swarm optimization (PSO) has the advantages of fast response and high accuracy. However, the performance of the PSO and other optimization algorithms depend on the accuracy of the modeling of the motor drive and losses. In the development of the loss model, there is always a trade off between accuracy and complexity. This paper presents a new online optimization to determine an optimum flux level for the efficiency optimization of the vector-controlled induction motor drive. An induction motor (IM) model in d-q coordinates is referenced to the rotor magnetizing current. This transformation results in no leakage inductance on the rotor side, thus the decomposition into d-q components in the steady-state motor model can be utilized in deriving the motor loss model. The suggested algorithm is simple for implementation.

Keywords: induction machine, loss minimization, magnetizing current, particle swarm optimization

Procedia PDF Downloads 612

Authors: Sohyoung Won, Heebal Kim, Dajeong Lim

Abstract:

Genomic prediction is an effective way to measure the abilities of livestock for breeding based on genomic estimated breeding values, statistically predicted values from genotype data using best linear unbiased prediction (BLUP). Using haplotypes, clusters of linked single nucleotide polymorphisms (SNPs), as markers instead of individual SNPs can improve the reliability of genomic prediction since the probability of a quantitative trait loci to be in strong linkage disequilibrium (LD) with markers is higher. To efficiently use haplotypes in genomic prediction, finding optimal ways to define haplotypes is needed. In this study, 770K SNP chip data was collected from Hanwoo (Korean cattle) population consisted of 2506 cattle. Haplotypes were first defined in three different ways using 770K SNP chip data: haplotypes were defined based on 1) length of haplotypes (bp), 2) the number of SNPs, and 3) k-medoids clustering by LD. To compare the methods in parallel, haplotypes defined by all methods were set to have comparable sizes; in each method, haplotypes defined to have an average number of 5, 10, 20 or 50 SNPs were tested respectively. A modified GBLUP method using haplotype alleles as predictor variables was implemented for testing the prediction reliability of each haplotype set. Also, conventional genomic BLUP (GBLUP) method, which uses individual SNPs were tested to evaluate the performance of the haplotype sets on genomic prediction. Carcass weight was used as the phenotype for testing. As a result, using haplotypes defined by all three methods showed increased reliability compared to conventional GBLUP. There were not many differences in the reliability between different haplotype defining methods. The reliability of genomic prediction was highest when the average number of SNPs per haplotype was 20 in all three methods, implying that haplotypes including around 20 SNPs can be optimal to use as markers for genomic prediction. When the number of alleles generated by each haplotype defining methods was compared, clustering by LD generated the least number of alleles. Using haplotype alleles for genomic prediction showed better performance, suggesting improved accuracy in genomic selection. The number of predictor variables was decreased when the LD-based method was used while all three haplotype defining methods showed similar performances. This suggests that defining haplotypes based on LD can reduce computational costs and allows efficient prediction. Finding optimal ways to define haplotypes and using the haplotype alleles as markers can provide improved performance and efficiency in genomic prediction.

Keywords: best linear unbiased predictor, genomic prediction, haplotype, linkage disequilibrium

Procedia PDF Downloads 117

Authors: Duncan Oteki, Andebut Yeneneh, Daba Gedafa, Nabil Suleiman

Abstract:

Most agencies lack the equipment required to measure the dynamic modulus (|E*|) of asphalt mixtures, necessitating the need to use predictive models. This study compared measured |E*| values for nine North Dakota asphalt mixes using the original Witczak, modified Witczak, and Hirsch models. The influence of temperature on the |E*| models was investigated, and Pavement ME simulations were conducted using measured |E*| and predictions from the most accurate |E*| model. The results revealed that the original Witczak model yielded the lowest Se/Sy and highest R² values, indicating the lowest bias and highest accuracy, while the poorest overall performance was exhibited by the Hirsch model. Using predicted |E*| as inputs in the Pavement ME generated conservative distress predictions compared to using measured |E*|. The original Witczak model was recommended for predicting |E*| for low-reliability pavements in North Dakota.

Keywords: asphalt mixture, binder, dynamic modulus, MEPDG, pavement ME, performance, prediction

Procedia PDF Downloads 24

Authors: Yijun Shao, Yan Cheng, Rashmee U. Shah, Charlene R. Weir, Bruce E. Bray, Qing Zeng-Treitler

Abstract:

Deep neural network (DNN) models are being explored in the clinical domain, following the recent success in other domains such as image recognition. For clinical adoption, outcome prediction models require explanation, but due to the multiple non-linear inner transformations, DNN models are viewed by many as a black box. In this study, we developed a deep neural network model for predicting 1-year mortality of patients who underwent major cardio vascular procedures (MCVPs), using temporal image representation of past medical history as input. The dataset was obtained from the electronic medical data warehouse administered by Veteran Affairs Information and Computing Infrastructure (VINCI). We identified 21,355 veterans who had their first MCVP in 2014. Features for prediction included demographics, diagnoses, procedures, medication orders, hospitalizations, and frailty measures extracted from clinical notes. Temporal variables were created based on the patient history data in the 2-year window prior to the index MCVP. A temporal image was created based on these variables for each individual patient. To generate the explanation for the DNN model, we defined a new concept called impact score, based on the presence/value of clinical conditions’ impact on the predicted outcome. Like (log) odds ratio reported by the logistic regression (LR) model, impact scores are continuous variables intended to shed light on the black box model. For comparison, a logistic regression model was fitted on the same dataset. In our cohort, about 6.8% of patients died within one year. The prediction of the DNN model achieved an area under the curve (AUC) of 78.5% while the LR model achieved an AUC of 74.6%. A strong but not perfect correlation was found between the aggregated impact scores and the log odds ratios (Spearman’s rho = 0.74), which helped validate our explanation.

Keywords: deep neural network, temporal data, prediction, frailty, logistic regression model

Procedia PDF Downloads 135

Authors: Afaneen Anwer, Samara M. Kamil

Abstract:

Load Forecast required prediction accuracy based on optimal operation and maintenance. A good accuracy is the basis of economic dispatch, unit commitment, and system reliability. A good load forecasting system fulfilled fast speed, automatic bad data detection, and ability to access the system automatically to get the needed data. In this paper, the formulation of the load forecasting is discussed and the solution is obtained by using artificial neural network method. A MATLAB environment has been used to solve the load forecasting schedule of Iraqi super grid network considering the daily load for three years. The obtained results showed a good accuracy in predicting the forecasted load.

Keywords: load forecasting, neural network, back-propagation algorithm, Iraqi power system

Procedia PDF Downloads 558

Authors: Yujiang Wu

Abstract:

As electrical machine (e-machine) power density re-querulents become more stringent in vehicle electrification, mounting a temperature sensor for e-machine stator windings becomes increasingly difficult. This can lead to higher manufacturing costs, complicated harnesses, and reduced reliability. In this paper, we propose a deep-learning method for predicting electric machine winding temperature, which can either replace the sensor entirely or serve as a backup to the existing sensor. We compare the performance of our method, the stateful long short-term memory networks (LSTM) with truncated backpropagation through time (TBTT), with that of linear regression, as well as stateless LSTM with/without residual connection. Our results demonstrate the strength of combining stateful LSTM and TBTT in tackling nonlinear time series prediction problems with long sequence lengths. Additionally, in industrial applications, high-temperature region prediction accuracy is more important because winding temperature sensing is typically used for derating machine power when the temperature is high. To evaluate the performance of our algorithm, we developed a temperature-stratified MSE. We propose a simple but effective data preprocessing trick to improve the high-temperature region prediction accuracy. Our experimental results demonstrate the effectiveness of our proposed method in accurately predicting winding temperature, particularly in high-temperature regions, while also reducing manufacturing costs and improving reliability.

Keywords: deep learning, electrical machine, functional safety, long short-term memory networks (LSTM), thermal management, time series prediction

Procedia PDF Downloads 65

Authors: Joselito Medina-Marin, Maria G. Serna-Diaz, Juan C. Seck-Tuoh-Mora, Norberto Hernandez-Romero, Irving Barragán-Vite

Abstract:

Wind speed forecasting is an important issue for planning wind power generation facilities. The accuracy in the wind speed prediction allows a good performance of wind turbines for electricity generation. A model based on artificial neural networks is presented in this work. A dataset with atmospheric information about air temperature, atmospheric pressure, wind direction, and wind speed in Pachuca, Hidalgo, México, was used to train the artificial neural network. The data was downloaded from the web page of the National Meteorological Service of the Mexican government. The records were gathered for three months, with time intervals of ten minutes. This dataset was used to develop an iterative algorithm to create 1,110 ANNs, with different configurations, starting from one to three hidden layers and every hidden layer with a number of neurons from 1 to 10. Each ANN was trained with the Levenberg-Marquardt backpropagation algorithm, which is used to learn the relationship between input and output values. The model with the best performance contains three hidden layers and 9, 6, and 5 neurons, respectively; and the coefficient of determination obtained was r²=0.9414, and the Root Mean Squared Error is 1.0559. In summary, the ANN approach is suitable to predict the wind speed in Pachuca City because the r² value denotes a good fitting of gathered records, and the obtained ANN model can be used in the planning of wind power generation grids.

Keywords: wind power generation, artificial neural networks, wind speed, coefficient of determination

Procedia PDF Downloads 87

Authors: Nan-Ting Yu, Boksun Kim, Long-Yuan Li

Abstract:

The cold-formed steel beams with web holes are widely used as the load-carrying members in structural engineering. The perforations can release the space of the building and let the pipes go through. However, the perforated cold-formed steel (PCFS) beams may fail by distortional buckling more easily than beams with plain web; this is because the rotational stiffness from the web decreases. It is well known that the distortional buckling can be described as the buckling of the compressed flange-lip system. In fact, near the ultimate failure, the flange/web corner would move laterally, which indicates the bending of the web should be taken account. The purpose of this study is to give a specific solution for the critical stress of flange/web distortional buckling of PCFS beams. The new model is deduced based on classical energy method, and the deflection of the web is represented by the shape function of the plane beam element. The finite element analyses have been performed to validate the accuracy of the proposed model. The comparison of the critical stress calculated from Hancock's model, FEA, and present model, shows that the present model can provide a splendid prediction for the flange/web distortional buckling of PCFS beams.

Keywords: cold-formed steel, beams, perforations, flange-web distortional buckling, finite element analysis

Procedia PDF Downloads 104

Authors: D.Mendes, J. Henriques, P. Carvalho, T. Rocha, S. Paredes, R. Cabiddu, R. Trimer, R. Mendes, A. Borghi-Silva, L. Kaminsky, E. Ashley, R. Arena, J. Myers

Abstract:

The continued exploration of clinically relevant predictive models continues to be an important pursuit. Cardiorespiratory fitness (CRF) portends clinical vital information and as such its accurate prediction is of high importance. Therefore, the aim of the current study was to develop a data-driven model, based on computational intelligence techniques and, in particular, clustering approaches, to predict CRF. Two prediction models were implemented and compared: 1) the traditional Wasserman/Hansen Equations; and 2) an interpretable clustering approach. Data used for this analysis were from the 'FRIEND - Fitness Registry and the Importance of Exercise: The National Data Base'; in the present study a subset of 10690 apparently healthy individuals were utilized. The accuracy of the models was performed through the computation of sensitivity, specificity, and geometric mean values. The results show the superiority of the clustering approach in the accurate estimation of CRF (i.e., maximal oxygen consumption).

Keywords: cardiorespiratory fitness, data-driven models, knowledge extraction, machine learning

Procedia PDF Downloads 263

Authors: S. Benchelha, H. C. Aoudjehane, M. Hakdaoui, R. El Hamdouni, H. Mansouri, T. Benchelha, M. Layelmam, M. Alaoui

Abstract:

The logistic regression (LR) and multivariate adaptive regression spline (MarSpline) are applied and verified for analysis of landslide susceptibility map in Oudka, Morocco, using geographical information system. From spatial database containing data such as landslide mapping, topography, soil, hydrology and lithology, the eight factors related to landslides such as elevation, slope, aspect, distance to streams, distance to road, distance to faults, lithology map and Normalized Difference Vegetation Index (NDVI) were calculated or extracted. Using these factors, landslide susceptibility indexes were calculated by the two mentioned methods. Before the calculation, this database was divided into two parts, the first for the formation of the model and the second for the validation. The results of the landslide susceptibility analysis were verified using success and prediction rates to evaluate the quality of these probabilistic models. The result of this verification was that the MarSpline model is the best model with a success rate (AUC = 0.963) and a prediction rate (AUC = 0.951) higher than the LR model (success rate AUC = 0.918, rate prediction AUC = 0.901).

Keywords: landslide susceptibility mapping, regression logistic, multivariate adaptive regression spline, Oudka, Taounate

Procedia PDF Downloads 164

Authors: Xiao Zhou, Jianlin Cheng

Abstract:

A single amino acid mutation can have a significant impact on the stability of protein structure. Thus, the prediction of protein stability change induced by single site mutations is critical and useful for studying protein function and structure. Here, we presented a deep learning network with the dropout technique for predicting protein stability changes upon single amino acid substitution. While using only protein sequence as input, the overall prediction accuracy of the method on a standard benchmark is >85%, which is higher than existing sequence-based methods and is comparable to the methods that use not only protein sequence but also tertiary structure, pH value and temperature. The results demonstrate that deep learning is a promising technique for protein stability prediction. The good performance of this sequence-based method makes it a valuable tool for predicting the impact of mutations on most proteins whose experimental structures are not available. Both the downloadable software package and the user-friendly web server (DNpro) that implement the method for predicting protein stability changes induced by amino acid mutations are freely available for the community to use.

Keywords: bioinformatics, deep learning, protein stability prediction, biological data mining

Procedia PDF Downloads 433

Authors: C. S. Subhashini, H. L. Premaratne

Abstract:

Landslides are the most recurrent and prominent disaster in Sri Lanka. Sri Lanka has been subjected to a number of extreme landslide disasters that resulted in a significant loss of life, material damage, and distress. It is required to explore a solution towards preparedness and mitigation to reduce recurrent losses associated with landslides. Artificial Neural Networks (ANNs) and Hidden Markov Model (HMMs) are now widely used in many computer applications spanning multiple domains. This research examines the effectiveness of using Artificial Neural Networks and Hidden Markov Model in landslides predictions and the possibility of applying the modern technology to predict landslides in a prominent geographical area in Sri Lanka. A thorough survey was conducted with the participation of resource persons from several national universities in Sri Lanka to identify and rank the influencing factors for landslides. A landslide database was created using existing topographic; soil, drainage, land cover maps and historical data. The landslide related factors which include external factors (Rainfall and Number of Previous Occurrences) and internal factors (Soil Material, Geology, Land Use, Curvature, Soil Texture, Slope, Aspect, Soil Drainage, and Soil Effective Thickness) are extracted from the landslide database. These factors are used to recognize the possibility to occur landslides by using an ANN and HMM. The model acquires the relationship between the factors of landslide and its hazard index during the training session. These models with landslide related factors as the inputs will be trained to predict three classes namely, ‘landslide occurs’, ‘landslide does not occur’ and ‘landslide likely to occur’. Once trained, the models will be able to predict the most likely class for the prevailing data. Finally compared two models with regards to prediction accuracy, False Acceptance Rates and False Rejection rates and This research indicates that the Artificial Neural Network could be used as a strong decision support system to predict landslides efficiently and effectively than Hidden Markov Model.

Keywords: landslides, influencing factors, neural network model, hidden markov model

Procedia PDF Downloads 362

Authors: Sneha Thakur, Sanjeev Karmakar

Abstract:

This paper proposed hybrid Particle Swarm Optimization (PSO) – Long-Short Term Memory (LSTM) model for groundwater level prediction. The evaluation of the performance is realized using the parameters: root mean square error (RMSE) and mean absolute error (MAE). Ground water level forecasting will be very effective for planning water harvesting. Proper calculation of water level forecasting can overcome the problem of drought and flood to some extent. The objective of this work is to develop a ground water level forecasting model using deep learning technique integrated with optimization technique PSO by applying 29 years data of Chhattisgarh state, In-dia. It is important to find the precise forecasting in case of ground water level so that various water resource planning and water harvesting can be managed effectively.

Keywords: long short-term memory, particle swarm optimization, prediction, deep learning, groundwater level

Procedia PDF Downloads 48

Authors: Khalaf Khatatneh, Nabeel Al-Milli, Amjad Hudaib, Monther Ali Tarawneh

Abstract:

Software fault prediction identify potential faults in software modules during the development process. In this paper, we present a novel approach for software fault prediction by combining a feedforward neural network with particle swarm optimization (PSO). The PSO algorithm is employed as a feature selection technique to identify the most relevant metrics as inputs to the neural network. Which enhances the quality of feature selection and subsequently improves the performance of the neural network model. Through comprehensive experiments on software fault prediction datasets, the proposed hybrid approach achieves better results, outperforming traditional classification methods. The integration of PSO-based feature selection with the neural network enables the identification of critical metrics that provide more accurate fault prediction. Results shows the effectiveness of the proposed approach and its potential for reducing development costs and effort by detecting faults early in the software development lifecycle. Further research and validation on diverse datasets will help solidify the practical applicability of the new approach in real-world software engineering scenarios.

Keywords: feature selection, neural network, particle swarm optimization, software fault prediction

Procedia PDF Downloads 64

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 138

Authors: Harneet Walia, Morteza Zihayat

Abstract:

Customer acquisition has become one of the critical issues of any business in the 21st century; having a healthy customer base is the essential asset of the bank business. Term deposits act as a major source of cheap funds for the banks to invest and benefit from interest rate arbitrage. To attract customers, the marketing campaigns at most financial institutions consist of multiple outbound telephonic calls with more than one contact to a customer which is a very time-consuming process. Therefore, customized direct marketing has become more critical than ever for attracting new clients. As customer acquisition is becoming more difficult to archive, having an intelligent and redefined list is necessary to sell a product smartly. Our aim of this research is to increase the effectiveness of campaigns by predicting customers who will most likely subscribe to the fixed deposit and suggest the most suitable month to reach out to customers. We design a Time Aware Upsell Prediction Framework (TAUPF) using two different approaches, with an aim to find the best approach and technique to build the prediction model. TAUPF is implemented using Upsell Prediction Approach (UPA) and Clustered Upsell Prediction Approach (CUPA). We also address the data imbalance problem by examining and comparing different methods of sampling (Up-sampling and down-sampling). Our results have shown building such a model is quite feasible and profitable for the financial institutions. The Time Aware Upsell Prediction Framework (TAUPF) can be easily used in any industry such as telecom, automobile, tourism, etc. where the TAUPF (Clustered Upsell Prediction Approach (CUPA) or Upsell Prediction Approach (UPA)) holds valid. In our case, CUPA books more reliable. As proven in our research, one of the most important challenges is to define measures which have enough predictive power as the subscription to a fixed deposit depends on highly ambiguous situations and cannot be easily isolated. While we have shown the practicality of time-aware upsell prediction model where financial institutions can benefit from contacting the customers at the specified month, further research needs to be done to understand the specific time of the day. In addition, a further empirical/pilot study on real live customer needs to be conducted to prove the effectiveness of the model in the real world.

Keywords: customer acquisition, predictive analysis, targeted marketing, time-aware analysis

Procedia PDF Downloads 100

Authors: Shahad Nagoor, Lucy Hederman, Kevin Koidl, Annalina Caputo

Abstract:

Doctors’ notes reflect their impressions, attitudes, clinical sense, and opinions about patients’ conditions and progress, and other information that is essential for doctors’ daily clinical decisions. Despite their value, clinical notes are insufficiently researched within the language processing community. Automatically extracting information from unstructured text data is known to be a difficult task as opposed to dealing with structured information such as vital physiological signs, images, and laboratory results. The aim of this research is to investigate how Natural Language Processing (NLP) techniques and machine learning techniques applied to clinician notes can assist in doctors’ decision-making in Intensive Care Unit (ICU) for coronavirus disease 2019 (COVID-19) patients. The hypothesis is that clinical outcomes like survival or mortality can be useful in influencing the judgement of clinical sentiment in ICU clinical notes. This paper introduces two contributions: first, we introduce COVID_ICU_BERT, a fine-tuned version of clinical transformer models that can reliably predict clinical sentiment for notes of COVID patients in the ICU. We train the model on clinical notes for COVID-19 patients, a type of notes that were not previously seen by clinicalBERT, and Bio_Discharge_Summary_BERT. The model, which was based on clinicalBERT achieves higher predictive accuracy (Acc 93.33%, AUC 0.98, and precision 0.96 ). Second, we perform data augmentation using clinical contextual word embedding that is based on a pre-trained clinical model to balance the samples in each class in the data (survived vs. deceased patients). Data augmentation improves the accuracy of prediction slightly (Acc 96.67%, AUC 0.98, and precision 0.92 ).

Keywords: BERT fine-tuning, clinical sentiment, COVID-19, data augmentation

Procedia PDF Downloads 177

Authors: Shuo Liu

Abstract:

In Chinese text classification tasks, redundant words and phrases can interfere with the formation of extracted and analyzed text information, leading to a decrease in the accuracy of the classification model. To reduce irrelevant elements, extract and utilize text content information more efficiently and improve the accuracy of text classification models. In this paper, the text in the corpus is first extracted using the TextRank algorithm for abstraction, the words in the abstract are used as nodes to construct a text graph, and then the graph attention network (GAT) is used to complete the task of classifying the text. Testing on a Chinese dataset from the network, the classification accuracy was improved over the direct method of generating graph structures using text.

Keywords: Chinese natural language processing, text classification, abstract extraction, graph attention network

Procedia PDF Downloads 70

Authors: Jan Stodt, Christoph Reich

Abstract:

The usage of machine learning models for prediction is growing rapidly and proof that the intended requirements are met is essential. Audits are a proven method to determine whether requirements or guidelines are met. However, machine learning models have intrinsic characteristics, such as the quality of training data, that make it difficult to demonstrate the required behavior and make audits more challenging. This paper describes an ML audit framework that evaluates and reviews the risks of machine learning applications, the quality of the training data, and the machine learning model. We evaluate and demonstrate the functionality of the proposed framework by auditing an steel plate fault prediction model.

Keywords: audit, machine learning, assessment, metrics

Procedia PDF Downloads 245

Authors: Kennedy Efosa Ehimwenma, Sujatha Krishnamoorthy, Safiya Al‑Sharji

Abstract:

The probability computation of events is in the interval of [0, 1], which are values that are determined by the number of outcomes of events in a sample space S. The probability Pr(A) that an event A will never occur is 0. The probability Pr(B) that event B will certainly occur is 1. This makes both events A and B a certainty. Furthermore, the sum of probabilities Pr(E₁) + Pr(E₂) + … + Pr(Eₙ) of a finite set of events in a given sample space S equals 1. Conversely, the difference of the sum of two probabilities that will certainly occur is 0. This paper first discusses Bayes, the complement of probability, and the difference of probability for occurrences of learning-events before applying them in the prediction of learning objects in student learning. Given the sum of 1; to make a recommendation for student learning, this paper proposes that the difference of argMaxPr(S) and the probability of student-performance quantifies the weight of learning objects for students. Using a dataset of skill-set, the computational procedure demonstrates i) the probability of skill-set events that have occurred that would lead to higher-level learning; ii) the probability of the events that have not occurred that requires subject-matter relearning; iii) accuracy of the decision tree in the prediction of student performance into class labels and iv) information entropy about skill-set data and its implication on student cognitive performance and recommendation of learning.

Keywords: complement of probability, Bayes’ rule, prediction, pre-assessments, computational education, information theory

Procedia PDF Downloads 135

Authors: Kemka Ihemelandu, Chukwuemeka Ihemelandu

Abstract:

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

Keywords: bias, augmentation, melanoma, convolutional neural network

Procedia PDF Downloads 179

Authors: Gizem Eser Erdek

Abstract:

This study is research on predicting the remaining life of industrial cutting tools used in the industrial production process with deep learning methods. When the life of cutting tools decreases, they cause destruction to the raw material they are processing. This study it is aimed to predict the remaining life of the cutting tool based on the damage caused by the cutting tools to the raw material. For this, hole photos were collected from the hole-drilling machine for 8 months. Photos were labeled in 5 classes according to hole quality. In this way, the problem was transformed into a classification problem. Using the prepared data set, a model was created with convolutional neural networks, which is a deep learning method. In addition, VGGNet and ResNet architectures, which have been successful in the literature, have been tested on the data set. A hybrid model using convolutional neural networks and support vector machines is also used for comparison. When all models are compared, it has been determined that the model in which convolutional neural networks are used gives successful results of a %74 accuracy rate. In the preliminary studies, the data set was arranged to include only the best and worst classes, and the study gave ~93% accuracy when the binary classification model was applied. The results of this study showed that the remaining life of the cutting tools could be predicted by deep learning methods based on the damage to the raw material. Experiments have proven that deep learning methods can be used as an alternative for cutting tool life estimation.

Keywords: classification, convolutional neural network, deep learning, remaining life of industrial cutting tools, ResNet, support vector machine, VggNet

Procedia PDF Downloads 51

Authors: Said Boukais, Ali Kezmane, Kahil Amar, Mohand Hamizi, Hannachi Neceur Eddine

Abstract:

This paper presents an analytical study on the behavior of rectangular reinforced concrete walls with an aspect ratio between one and tow. Several experiments on such walls have been selected to be studied. Database from various experiments were collected and nominal wall strengths have been calculated using formulas, such as those of the ACI (American), NZS (New Zealand), Mexican (NTCC), and Wood equation for shear and strain compatibility analysis for flexure. Subsequently, nominal ultimate wall strengths from the formulas were compared with the ultimate wall strengths from the database. These formulas vary substantially in functional form and do not account for all variables that affect the response of walls. There is substantial scatter in the predicted values of ultimate strength. New semi empirical equation are developed using data from tests of 46 walls with the objective of improving the prediction of ultimate strength of walls with the most possible accuracy and for all failure modes.

Keywords: prediction, ultimate strength, reinforced concrete walls, walls, rectangular walls

Procedia PDF Downloads 317

Authors: Adel Edwar Waheeb Louka

Abstract:

Purpose AI-driven solutions are at the forefront of many pathology and medical imaging methods. Using algorithms designed to better the experience of medical professionals within their respective fields, the efficiency and accuracy of diagnosis can improve. In particular, X-rays are a fast and relatively inexpensive test that can diagnose diseases. In recent years, X-rays have not been widely used to detect and diagnose COVID-19. The under use of Xrays is mainly due to the low diagnostic accuracy and confounding with pneumonia, another respiratory disease. However, research in this field has expressed a possibility that artificial neural networks can successfully diagnose COVID-19 with high accuracy. Models and Data The dataset used is the COVID-19 Radiography Database. This dataset includes images and masks of chest X-rays under the labels of COVID-19, normal, and pneumonia. The classification model developed uses an autoencoder and a pre-trained convolutional neural network (DenseNet201) to provide transfer learning to the model. The model then uses a deep neural network to finalize the feature extraction and predict the diagnosis for the input image. This model was trained on 4035 images and validated on 807 separate images from the ones used for training. The images used to train the classification model include an important feature: the pictures are cropped beforehand to eliminate distractions when training the model. The image segmentation model uses an improved U-Net architecture. This model is used to extract the lung mask from the chest X-ray image. The model is trained on 8577 images and validated on a validation split of 20%. These models are calculated using the external dataset for validation. The models’ accuracy, precision, recall, f1-score, IOU, and loss are calculated. Results The classification model achieved an accuracy of 97.65% and a loss of 0.1234 when differentiating COVID19-infected, pneumonia-infected, and normal lung X-rays. The segmentation model achieved an accuracy of 97.31% and an IOU of 0.928. Conclusion The models proposed can detect COVID-19, pneumonia, and normal lungs with high accuracy and derive the lung mask from a chest X-ray with similarly high accuracy. The hope is for these models to elevate the experience of medical professionals and provide insight into the future of the methods used.

Keywords: artificial intelligence, convolutional neural networks, deeplearning, image processing, machine learningSarapin, intraarticular, chronic knee pain, osteoarthritisFNS, trauma, hip, neck femur fracture, minimally invasive surgery

Procedia PDF Downloads 32

Authors: Mikiyas Adugna

Abstract:

Effort estimation is among the activities carried out in software development processes. An accurate model of estimation leads to project success. The method of agile effort estimation is a complex task because of the dynamic nature of software development. Researchers are still conducting studies on agile effort estimation to enhance prediction accuracy. Due to these reasons, we investigated and proposed a model on LASSO and Elastic Net regression to enhance estimation accuracy. The proposed model has major components: preprocessing, train-test split, training with default parameters, and cross-validation. During the preprocessing phase, the entire dataset is normalized. After normalization, a train-test split is performed on the dataset, setting training at 80% and testing set to 20%. We chose two different phases for training the two algorithms (Elastic Net and LASSO) regression following the train-test-split. In the first phase, the two algorithms are trained using their default parameters and evaluated on the testing data. In the second phase, the grid search technique (the grid is used to search for tuning and select optimum parameters) and 5-fold cross-validation to get the final trained model. Finally, the final trained model is evaluated using the testing set. The experimental work is applied to the agile story point dataset of 21 software projects collected from six firms. The results show that both Elastic Net and LASSO regression outperformed the compared ones. Compared to the proposed algorithms, LASSO regression achieved better predictive performance and has acquired PRED (8%) and PRED (25%) results of 100.0, MMRE of 0.0491, MMER of 0.0551, MdMRE of 0.0593, MdMER of 0.063, and MSE of 0.0007. The result implies LASSO regression algorithm trained model is the most acceptable, and higher estimation performance exists in the literature.

Keywords: agile software development, effort estimation, elastic net regression, LASSO

Procedia PDF Downloads 33

Authors: Hilya Mudrika Arini, Nur Aini Masruroh, Budi Hartono

Abstract:

There are more than 20 terrorist threats from 2002 to 2012 in Indonesia. Despite of this fact, preventive solution through studies in the field of national security in Indonesia has not been conducted comprehensively. This study aims to provide a preventive solution by developing prediction model of the terrorist threat in Indonesia by using Bayesian network. There are eight stages to build the model, started from literature review, build and verify Bayesian belief network to what-if scenario. In order to build the model, four experts from different perspectives are utilized. This study finds several significant findings. First, news and the readiness of terrorist group are the most influent factor. Second, according to several scenarios of the news portion, it can be concluded that the higher positive news proportion, the higher probability of terrorist threat will occur. Therefore, the preventive solution to reduce the terrorist threat in Indonesia based on the model is by keeping the positive news portion to a maximum of 38%.

Keywords: Bayesian network, decision analysis, national security system, text mining

Procedia PDF Downloads 368

Authors: X. Lu, T. Lu, S. Javadi

Abstract:

A simple dynamic approach is presented for analyzing thermal and moisture dynamics of buildings, which is of particular relevance to understanding climate change impacts on buildings, including assessment of risks and applications of resilience strategies. With the goal to demonstrate the proposed modeling methodology, to verify the model, and to show that wooden materials provide a mechanism that can facilitate the reduction of moisture risks and be more resilient to global warming, a wooden church equipped with high precision measurement systems was taken as a test building for full-scale time-series measurements. Sensitivity analyses indicate a high degree of accuracy in the model prediction regarding the indoor environment. The model is then applied to a future projection of climate indoors aiming to identify significant environmental factors, the changing temperature and humidity, and effective response to the climate change impacts. The paper suggests that wooden building materials offer an effective and resilient response to anticipated future climate changes.

Keywords: dynamic model, forecast, climate change impact, wooden structure, buildings

Procedia PDF Downloads 126

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 86