Search results for: discriminate accuracy
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 3676

Search results for: discriminate accuracy

3406 Predicting Survival in Cancer: How Cox Regression Model Compares to Artifial Neural Networks?

Authors: Dalia Rimawi, Walid Salameh, Amal Al-Omari, Hadeel AbdelKhaleq

Abstract:

Predication of Survival time of patients with cancer, is a core factor that influences oncologist decisions in different aspects; such as offered treatment plans, patients’ quality of life and medications development. For a long time proportional hazards Cox regression (ph. Cox) was and still the most well-known statistical method to predict survival outcome. But due to the revolution of data sciences; new predication models were employed and proved to be more flexible and provided higher accuracy in that type of studies. Artificial neural network is one of those models that is suitable to handle time to event predication. In this study we aim to compare ph Cox regression with artificial neural network method according to data handling and Accuracy of each model.

Keywords: Cox regression, neural networks, survival, cancer.

Procedia PDF Downloads 169
3405 Slice Bispectrogram Analysis-Based Classification of Environmental Sounds Using Convolutional Neural Network

Authors: Katsumi Hirata

Abstract:

Certain systems can function well only if they recognize the sound environment as humans do. In this research, we focus on sound classification by adopting a convolutional neural network and aim to develop a method that automatically classifies various environmental sounds. Although the neural network is a powerful technique, the performance depends on the type of input data. Therefore, we propose an approach via a slice bispectrogram, which is a third-order spectrogram and is a slice version of the amplitude for the short-time bispectrum. This paper explains the slice bispectrogram and discusses the effectiveness of the derived method by evaluating the experimental results using the ESC‑50 sound dataset. As a result, the proposed scheme gives high accuracy and stability. Furthermore, some relationship between the accuracy and non-Gaussianity of sound signals was confirmed.

Keywords: environmental sound, bispectrum, spectrogram, slice bispectrogram, convolutional neural network

Procedia PDF Downloads 101
3404 Generating Synthetic Chest X-ray Images for Improved COVID-19 Detection Using Generative Adversarial Networks

Authors: Muneeb Ullah, Daishihan, Xiadong Young

Abstract:

Deep learning plays a crucial role in identifying COVID-19 and preventing its spread. To improve the accuracy of COVID-19 diagnoses, it is important to have access to a sufficient number of training images of CXRs (chest X-rays) depicting the disease. However, there is currently a shortage of such images. To address this issue, this paper introduces COVID-19 GAN, a model that uses generative adversarial networks (GANs) to generate realistic CXR images of COVID-19, which can be used to train identification models. Initially, a generator model is created that uses digressive channels to generate images of CXR scans for COVID-19. To differentiate between real and fake disease images, an efficient discriminator is developed by combining the dense connectivity strategy and instance normalization. This approach makes use of their feature extraction capabilities on CXR hazy areas. Lastly, the deep regret gradient penalty technique is utilized to ensure stable training of the model. With the use of 4,062 grape leaf disease images, the Leaf GAN model successfully produces 8,124 COVID-19 CXR images. The COVID-19 GAN model produces COVID-19 CXR images that outperform DCGAN and WGAN in terms of the Fréchet inception distance. Experimental findings suggest that the COVID-19 GAN-generated CXR images possess noticeable haziness, offering a promising approach to address the limited training data available for COVID-19 model training. When the dataset was expanded, CNN-based classification models outperformed other models, yielding higher accuracy rates than those of the initial dataset and other augmentation techniques. Among these models, ImagNet exhibited the best recognition accuracy of 99.70% on the testing set. These findings suggest that the proposed augmentation method is a solution to address overfitting issues in disease identification and can enhance identification accuracy effectively.

Keywords: classification, deep learning, medical images, CXR, GAN.

Procedia PDF Downloads 57
3403 A Recommender System Fusing Collaborative Filtering and User’s Review Mining

Authors: Seulbi Choi, Hyunchul Ahn

Abstract:

Collaborative filtering (CF) algorithm has been popularly used for recommender systems in both academic and practical applications. It basically generates recommendation results using users’ numeric ratings. However, the additional use of the information other than user ratings may lead to better accuracy of CF. Considering that a lot of people are likely to share their honest opinion on the items they purchased recently due to the advent of the Web 2.0, user's review can be regarded as the new informative source for identifying user's preference with accuracy. Under this background, this study presents a hybrid recommender system that fuses CF and user's review mining. Our system adopts conventional memory-based CF, but it is designed to use both user’s numeric ratings and his/her text reviews on the items when calculating similarities between users.

Keywords: Recommender system, Collaborative filtering, Text mining, Review mining

Procedia PDF Downloads 314
3402 Evaluating Classification with Efficacy Metrics

Authors: Guofan Shao, Lina Tang, Hao Zhang

Abstract:

The values of image classification accuracy are affected by class size distributions and classification schemes, making it difficult to compare the performance of classification algorithms across different remote sensing data sources and classification systems. Based on the term efficacy from medicine and pharmacology, we have developed the metrics of image classification efficacy at the map and class levels. The novelty of this approach is that a baseline classification is involved in computing image classification efficacies so that the effects of class statistics are reduced. Furthermore, the image classification efficacies are interpretable and comparable, and thus, strengthen the assessment of image data classification methods. We use real-world and hypothetical examples to explain the use of image classification efficacies. The metrics of image classification efficacy meet the critical need to rectify the strategy for the assessment of image classification performance as image classification methods are becoming more diversified.

Keywords: accuracy assessment, efficacy, image classification, machine learning, uncertainty

Procedia PDF Downloads 182
3401 Diagnostic Properties of Exercise or Pharmacological Stress Myocardial Perfusion Scintigraphy in Per-Vessel Basis: A Clinical Validation Study

Authors: Ahmadreza Bagheri, Seyyed S. Eftekhari, Shervin Rashidinia

Abstract:

Background: Various stress tests have been proposed yet to assess patients with suspected coronary artery disease. However, their diagnostic properties in terms of sensitivity, specificity, and accuracy are variable and their applicability remained somewhat vague. The aim of this study is to validate per-vessel diagnostic properties of 3 types of stress myocardial perfusion scintigraphy in gated SPECT (Single-Photon Emission Computed Tomography) using either exercise or pharmacological stress testing with dipyridamole or dobutamine. Materials and Methods: Hospital records of 314 patients who referred to Imam Khomeini hospital of Tehran between September 2015 and January 2017 were completely reviewed in this study. All patients underwent coronary angiography within 3 months after stress myocardial perfusion scan. Eventually, the results were analyzed in per-vessel basis to find the proper modality for each involved vessel or scanned site. Results: The mean age of patients was 62.15 ± 4.94 years (30-85) and 35.03% were women. The overall sensitivity, specificity, and accuracy were calculated as 56.59%, 54.24%, and 55.09%, respectively. These values were 56.43% and 53.25%, 54.46% and 47.36%, 56.75% and 54.83% for dipyridamole and exercise, respectively. Ischemia of the anterior wall through exercise stress testing has the highest diagnostic accuracy in detecting LAD (Left Anterior Descending artery) involvement. Inferior wall hypokinesia and anterolateral wall ischemia during exercise stress testing have the highest diagnostic accuracy in detecting RCA (Right Coronary Artery) and LCX artery (Left Circumflex Artery) stenosis, respectively. Conclusion: Stress myocardial perfusion scan should be carried out on the basis of the findings of the preliminary investigations on suspicion of a specific coronary artery or involved myocardial wall.

Keywords: dipyridamole, dobutamine, single-photon emission computed tomography, stress myocardial perfusion scintigraphy

Procedia PDF Downloads 130
3400 Bi-Lateral Comparison between NIS-Egypt and NMISA-South Africa for the Calibration of an Optical Spectrum Analyzer

Authors: Osama Terra, Hatem Hussein, Adriaan Van Brakel

Abstract:

Dense wavelength division multiplexing (DWDM) technology requires tight specification and therefore measurement of wavelength accuracy and stability of the telecommunication lasers. Thus, calibration of the used Optical Spectrum Analyzers (OSAs) that are used to measure wavelength is of a great importance. Proficiency testing must be performed on such measuring activity to insure the accuracy of the measurement results. In this paper, a new comparison scheme is introduced to test the performance of such calibrations. This comparison scheme is implemented between NIS-Egypt and NMISA-South Africa for the calibration of the wavelength scale of an OSA. Both institutes employ reference gas cell to calibrate OSA according to the standard IEC/ BS EN 62129 (2006). The result of this comparison is compiled in this paper.

Keywords: OSA calibration, HCN gas cell, DWDM technology, wavelength measurement

Procedia PDF Downloads 278
3399 Calibration of the Radical Installation Limit Error of the Accelerometer in the Gravity Gradient Instrument

Authors: Danni Cong, Meiping Wu, Xiaofeng He, Junxiang Lian, Juliang Cao, Shaokuncai, Hao Qin

Abstract:

Gravity gradient instrument (GGI) is the core of the gravity gradiometer, so the structural error of the sensor has a great impact on the measurement results. In order not to affect the aimed measurement accuracy, limit error is required in the installation of the accelerometer. In this paper, based on the established measuring principle model, the radial installation limit error is calibrated, which is taken as an example to provide a method to calculate the other limit error of the installation under the premise of ensuring the accuracy of the measurement result. This method provides the idea for deriving the limit error of the geometry structure of the sensor, laying the foundation for the mechanical precision design and physical design.

Keywords: gravity gradient sensor, radial installation limit error, accelerometer, uniaxial rotational modulation

Procedia PDF Downloads 400
3398 Efficient Passenger Counting in Public Transport Based on Machine Learning

Authors: Chonlakorn Wiboonsiriruk, Ekachai Phaisangittisagul, Chadchai Srisurangkul, Itsuo Kumazawa

Abstract:

Public transportation is a crucial aspect of passenger transportation, with buses playing a vital role in the transportation service. Passenger counting is an essential tool for organizing and managing transportation services. However, manual counting is a tedious and time-consuming task, which is why computer vision algorithms are being utilized to make the process more efficient. In this study, different object detection algorithms combined with passenger tracking are investigated to compare passenger counting performance. The system employs the EfficientDet algorithm, which has demonstrated superior performance in terms of speed and accuracy. Our results show that the proposed system can accurately count passengers in varying conditions with an accuracy of 94%.

Keywords: computer vision, object detection, passenger counting, public transportation

Procedia PDF Downloads 126
3397 A Convolution Neural Network Approach to Predict Pes-Planus Using Plantar Pressure Mapping Images

Authors: Adel Khorramrouz, Monireh Ahmadi Bani, Ehsan Norouzi, Morvarid Lalenoor

Abstract:

Background: Plantar pressure distribution measurement has been used for a long time to assess foot disorders. Plantar pressure is an important component affecting the foot and ankle function and Changes in plantar pressure distribution could indicate various foot and ankle disorders. Morphologic and mechanical properties of the foot may be important factors affecting the plantar pressure distribution. Accurate and early measurement may help to reduce the prevalence of pes planus. With recent developments in technology, new techniques such as machine learning have been used to assist clinicians in predicting patients with foot disorders. Significance of the study: This study proposes a neural network learning-based flat foot classification methodology using static foot pressure distribution. Methodologies: Data were collected from 895 patients who were referred to a foot clinic due to foot disorders. Patients with pes planus were labeled by an experienced physician based on clinical examination. Then all subjects (with and without pes planus) were evaluated for static plantar pressures distribution. Patients who were diagnosed with the flat foot in both feet were included in the study. In the next step, the leg length was normalized and the network was trained for plantar pressure mapping images. Findings: From a total of 895 image data, 581 were labeled as pes planus. A computational neural network (CNN) ran to evaluate the performance of the proposed model. The prediction accuracy of the basic CNN-based model was performed and the prediction model was derived through the proposed methodology. In the basic CNN model, the training accuracy was 79.14%, and the test accuracy was 72.09%. Conclusion: This model can be easily and simply used by patients with pes planus and doctors to predict the classification of pes planus and prescreen for possible musculoskeletal disorders related to this condition. However, more models need to be considered and compared for higher accuracy.

Keywords: foot disorder, machine learning, neural network, pes planus

Procedia PDF Downloads 330
3396 An Automated R-Peak Detection Method Using Common Vector Approach

Authors: Ali Kirkbas

Abstract:

R peaks in an electrocardiogram (ECG) are signs of cardiac activity in individuals that reveal valuable information about cardiac abnormalities, which can lead to mortalities in some cases. This paper examines the problem of detecting R-peaks in ECG signals, which is a two-class pattern classification problem in fact. To handle this problem with a reliable high accuracy, we propose to use the common vector approach which is a successful machine learning algorithm. The dataset used in the proposed method is obtained from MIT-BIH, which is publicly available. The results are compared with the other popular methods under the performance metrics. The obtained results show that the proposed method shows good performance than that of the other. methods compared in the meaning of diagnosis accuracy and simplicity which can be operated on wearable devices.

Keywords: ECG, R-peak classification, common vector approach, machine learning

Procedia PDF Downloads 31
3395 Using Audit Tools to Maintain Data Quality for ACC/NCDR PCI Registry Abstraction

Authors: Vikrum Malhotra, Manpreet Kaur, Ayesha Ghotto

Abstract:

Background: Cardiac registries such as ACC Percutaneous Coronary Intervention Registry require high quality data to be abstracted, including data elements such as nuclear cardiology, diagnostic coronary angiography, and PCI. Introduction: The audit tool created is used by data abstractors to provide data audits and assess the accuracy and inter-rater reliability of abstraction performed by the abstractors for a health system. This audit tool solution has been developed across 13 registries, including ACC/NCDR registries, PCI, STS, Get with the Guidelines. Methodology: The data audit tool was used to audit internal registry abstraction for all data elements, including stress test performed, type of stress test, data of stress test, results of stress test, risk/extent of ischemia, diagnostic catheterization detail, and PCI data elements for ACC/NCDR PCI registries. This is being used across 20 hospital systems internally and providing abstraction and audit services for them. Results: The data audit tool had inter-rater reliability and accuracy greater than 95% data accuracy and IRR score for the PCI registry in 50 PCI registry cases in 2021. Conclusion: The tool is being used internally for surgical societies and across hospital systems. The audit tool enables the abstractor to be assessed by an external abstractor and includes all of the data dictionary fields for each registry.

Keywords: abstraction, cardiac registry, cardiovascular registry, registry, data

Procedia PDF Downloads 82
3394 Musical Instrument Recognition in Polyphonic Audio Through Convolutional Neural Networks and Spectrograms

Authors: Rujia Chen, Akbar Ghobakhlou, Ajit Narayanan

Abstract:

This study investigates the task of identifying musical instruments in polyphonic compositions using Convolutional Neural Networks (CNNs) from spectrogram inputs, focusing on binary classification. The model showed promising results, with an accuracy of 97% on solo instrument recognition. When applied to polyphonic combinations of 1 to 10 instruments, the overall accuracy was 64%, reflecting the increasing challenge with larger ensembles. These findings contribute to the field of Music Information Retrieval (MIR) by highlighting the potential and limitations of current approaches in handling complex musical arrangements. Future work aims to include a broader range of musical sounds, including electronic and synthetic sounds, to improve the model's robustness and applicability in real-time MIR systems.

Keywords: binary classifier, CNN, spectrogram, instrument

Procedia PDF Downloads 17
3393 Adversarial Attacks and Defenses on Deep Neural Networks

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 163
3392 CMOS Solid-State Nanopore DNA System-Level Sequencing Techniques Enhancement

Authors: Syed Islam, Yiyun Huang, Sebastian Magierowski, Ebrahim Ghafar-Zadeh

Abstract:

This paper presents system level CMOS solid-state nanopore techniques enhancement for speedup next generation molecular recording and high throughput channels. This discussion also considers optimum number of base-pair (bp) measurements through channel as an important role to enhance potential read accuracy. Effective power consumption estimation offered suitable rangeof multi-channel configuration. Nanopore bp extraction model in statistical method could contribute higher read accuracy with longer read-length (200 < read-length). Nanopore ionic current switching with Time Multiplexing (TM) based multichannel readout system contributed hardware savings.

Keywords: DNA, nanopore, amplifier, ADC, multichannel

Procedia PDF Downloads 430
3391 Application of KL Divergence for Estimation of Each Metabolic Pathway Genes

Authors: Shohei Maruyama, Yasuo Matsuyama, Sachiyo Aburatani

Abstract:

The development of the method to annotate unknown gene functions is an important task in bioinformatics. One of the approaches for the annotation is The identification of the metabolic pathway that genes are involved in. Gene expression data have been utilized for the identification, since gene expression data reflect various intracellular phenomena. However, it has been difficult to estimate the gene function with high accuracy. It is considered that the low accuracy of the estimation is caused by the difficulty of accurately measuring a gene expression. Even though they are measured under the same condition, the gene expressions will vary usually. In this study, we proposed a feature extraction method focusing on the variability of gene expressions to estimate the genes' metabolic pathway accurately. First, we estimated the distribution of each gene expression from replicate data. Next, we calculated the similarity between all gene pairs by KL divergence, which is a method for calculating the similarity between distributions. Finally, we utilized the similarity vectors as feature vectors and trained the multiclass SVM for identifying the genes' metabolic pathway. To evaluate our developed method, we applied the method to budding yeast and trained the multiclass SVM for identifying the seven metabolic pathways. As a result, the accuracy that calculated by our developed method was higher than the one that calculated from the raw gene expression data. Thus, our developed method combined with KL divergence is useful for identifying the genes' metabolic pathway.

Keywords: metabolic pathways, gene expression data, microarray, Kullback–Leibler divergence, KL divergence, support vector machines, SVM, machine learning

Procedia PDF Downloads 380
3390 A Clinical Cutoff to Identify Metabolically Unhealthy Obese and Normal-Weight Phenotype in Young Adults

Authors: Lívia Pinheiro Carvalho, Luciana Di Thommazo-Luporini, Rafael Luís Luporini, José Carlos Bonjorno Junior, Renata Pedrolongo Basso Vanelli, Manoel Carneiro de Oliveira Junior, Rodolfo de Paula Vieira, Renata Trimer, Renata G. Mendes, Mylène Aubertin-Leheudre, Audrey Borghi-Silva

Abstract:

Rationale: Cardiorespiratory fitness (CRF) and functional capacity in young obese and normal-weight people are associated with metabolic and cardiovascular diseases and mortality. However, it remains unclear whether their metabolically healthy (MH) or at risk (AR) phenotype influences cardiorespiratory fitness in this vulnerable population such as obese adults but also in normal-weight people. HOMA insulin resistance index (HI) and leptin-adiponectin ratio (LA) are strong markers for characterizing those phenotypes that we hypothesized to be associated with physical fitness. We also hypothesized that an easy and feasible exercise test could identify a subpopulation at risk to develop metabolic and related disorders. Methods: Thirty-nine sedentary men and women (20-45y; 18.530 kg.m-2) underwent a clinical evaluation, including the six-minute step test (ST), a well-validated and reliable test for young people. Body composition assessment was done by a tetrapolar bioimpedance in a fasting state and in the folicular phase for women. A maximal cardiopulmonary exercise testing, as well as the ST, evaluated the oxygen uptake at the peak of the test (VO2peak) by an ergospirometer Oxycon Mobile. Lipids, glucose, insulin were analysed and the ELISA method quantified the serum leptin and adiponectin from blood samples. Volunteers were divided in two groups: AR or MH according to a HI cutoff of 1.95, which was previously determined in the literature. T-test for comparison between groups, Pearson´s test to correlate main variables and ROC analysis for discriminating AR from up-and-down cycles in ST (SC) were applied (p<0.05). Results: Higher LA, fat mass (FM) and lower HDL, SC, leg lean mass (LM) and VO2peak were found in AR than in MH. Significant correlations were found between VO2peak and SC (r= 0.80) as well as between LA and FM (r=0.87), VO2peak (r=-0.73), and SC (r=-0.65). Area under de curve showed moderate accuracy (0.75) of SC <173 to discriminate AR phenotype. Conclusion: Our study found that at risk obese and normal-weight subjects showed an unhealthy metabolism as well as a poor CRF and functional daily activity capacity. Additionally, a simple and less costly functional test associated with above-mentioned aspects is able to identify ‘at risk’ subjects for primary intervention with important clinical and health implications.

Keywords: aerobic capacity, exercise, fitness, metabolism, obesity, 6MST

Procedia PDF Downloads 326
3389 Enhanced Weighted Centroid Localization Algorithm for Indoor Environments

Authors: I. Nižetić Kosović, T. Jagušt

Abstract:

Lately, with the increasing number of location-based applications, demand for highly accurate and reliable indoor localization became urgent. This is a challenging problem, due to the measurement variance which is the consequence of various factors like obstacles, equipment properties and environmental changes in complex nature of indoor environments. In this paper we propose low-cost custom-setup infrastructure solution and localization algorithm based on the Weighted Centroid Localization (WCL) method. Localization accuracy is increased by several enhancements: calibration of RSSI values gained from wireless nodes, repetitive measurements of RSSI to exclude deviating values from the position estimation, and by considering orientation of the device according to the wireless nodes. We conducted several experiments to evaluate the proposed algorithm. High accuracy of ~1m was achieved.

Keywords: indoor environment, received signal strength indicator, weighted centroid localization, wireless localization

Procedia PDF Downloads 212
3388 Grey Wolf Optimization Technique for Predictive Analysis of Products in E-Commerce: An Adaptive Approach

Authors: Shital Suresh Borse, Vijayalaxmi Kadroli

Abstract:

E-commerce industries nowadays implement the latest AI, ML Techniques to improve their own performance and prediction accuracy. This helps to gain a huge profit from the online market. Ant Colony Optimization, Genetic algorithm, Particle Swarm Optimization, Neural Network & GWO help many e-commerce industries for up-gradation of their predictive performance. These algorithms are providing optimum results in various applications, such as stock price prediction, prediction of drug-target interaction & user ratings of similar products in e-commerce sites, etc. In this study, customer reviews will play an important role in prediction analysis. People showing much interest in buying a lot of services& products suggested by other customers. This ultimately increases net profit. In this work, a convolution neural network (CNN) is proposed which further is useful to optimize the prediction accuracy of an e-commerce website. This method shows that CNN is used to optimize hyperparameters of GWO algorithm using an appropriate coding scheme. Accurate model results are verified by comparing them to PSO results whose hyperparameters have been optimized by CNN in Amazon's customer review dataset. Here, experimental outcome proves that this proposed system using the GWO algorithm achieves superior execution in terms of accuracy, precision, recovery, etc. in prediction analysis compared to the existing systems.

Keywords: prediction analysis, e-commerce, machine learning, grey wolf optimization, particle swarm optimization, CNN

Procedia PDF Downloads 88
3387 Assessing an Instrument Usability: Response Interpolation and Scale Sensitivity

Authors: Betsy Ng, Seng Chee Tan, Choon Lang Quek, Peter Looker, Jaime Koh

Abstract:

The purpose of the present study was to determine the particular scale rating that stands out for an instrument. The instrument was designed to assess student perceptions of various learning environments, namely face-to-face, online and blended. The original instrument had a 5-point Likert items (1 = strongly disagree and 5 = strongly agree). Alternate versions were modified with a 6-point Likert scale and a bar scale rating. Participants consisted of undergraduates in a local university were involved in the usability testing of the instrument in an electronic setting. They were presented with the 5-point, 6-point and percentage-bar (100-point) scale ratings, in response to their perceptions of learning environments. The 5-point and 6-point Likert scales were presented in the form of radio button controls for each number, while the percentage-bar scale was presented with a sliding selection. Among these responses, 6-point Likert scale emerged to be the best overall. When participants were confronted with the 5-point items, they either chose 3 or 4, suggesting that data loss could occur due to the insensitivity of instrument. The insensitivity of instrument could be due to the discreet options, as evidenced by response interpolation. To avoid the constraint of discreet options, the percentage-bar scale rating was tested, but the participant responses were not well-interpolated. The bar scale might have provided a variety of responses without a constraint of a set of categorical options, but it seemed to reflect a lack of perceived and objective accuracy. The 6-point Likert scale was more likely to reflect a respondent’s perceived and objective accuracy as well as higher sensitivity. This finding supported the conclusion that 6-point Likert items provided a more accurate measure of the participant’s evaluation. The 5-point and bar scale ratings might not be accurately measuring the participants’ responses. This study highlighted the importance of the respondent’s perception of accuracy, respondent’s true evaluation, and the scale’s ease of use. Implications and limitations of this study were also discussed.

Keywords: usability, interpolation, sensitivity, Likert scales, accuracy

Procedia PDF Downloads 390
3386 Dynamic Compensation for Environmental Temperature Variation in the Coolant Refrigeration Cycle as a Means of Increasing Machine-Tool Precision

Authors: Robbie C. Murchison, Ibrahim Küçükdemiral, Andrew Cowell

Abstract:

Thermal effects are the largest source of dimensional error in precision machining, and a major proportion is caused by ambient temperature variation. The use of coolant is a primary means of mitigating these effects, but there has been limited work on coolant temperature control. This research critically explored whether CNC-machine coolant refrigeration systems adapted to actively compensate for ambient temperature variation could increase machining accuracy. Accuracy data were collected from operators’ checklists for a CNC 5-axis mill and statistically reduced to bias and precision metrics for observations of one day over a sample period of 27 days. Temperature data were collected using three USB dataloggers in ambient air, the chiller inflow, and the chiller outflow. The accuracy and temperature data were analysed using Pearson correlation, then the thermodynamics of the system were described using system identification with MATLAB. It was found that 75% of thermal error is reflected in the hot coolant temperature but that this is negligibly dependent on ambient temperature. The effect of the coolant refrigeration process on hot coolant outflow temperature was also found to be negligible. Therefore, the evidence indicated that it would not be beneficial to adapt coolant chillers to compensate for ambient temperature variation. However, it is concluded that hot coolant outflow temperature is a robust and accessible source of thermal error data which could be used for prevention strategy evaluation or as the basis of other thermal error strategies.

Keywords: CNC manufacturing, machine-tool, precision machining, thermal error

Procedia PDF Downloads 62
3385 Predicting Options Prices Using Machine Learning

Authors: Krishang Surapaneni

Abstract:

The goal of this project is to determine how to predict important aspects of options, including the ask price. We want to compare different machine learning models to learn the best model and the best hyperparameters for that model for this purpose and data set. Option pricing is a relatively new field, and it can be very complicated and intimidating, especially to inexperienced people, so we want to create a machine learning model that can predict important aspects of an option stock, which can aid in future research. We tested multiple different models and experimented with hyperparameter tuning, trying to find some of the best parameters for a machine-learning model. We tested three different models: a Random Forest Regressor, a linear regressor, and an MLP (multi-layer perceptron) regressor. The most important feature in this experiment is the ask price; this is what we were trying to predict. In the field of stock pricing prediction, there is a large potential for error, so we are unable to determine the accuracy of the models based on if they predict the pricing perfectly. Due to this factor, we determined the accuracy of the model by finding the average percentage difference between the predicted and actual values. We tested the accuracy of the machine learning models by comparing the actual results in the testing data and the predictions made by the models. The linear regression model performed worst, with an average percentage error of 17.46%. The MLP regressor had an average percentage error of 11.45%, and the random forest regressor had an average percentage error of 7.42%

Keywords: finance, linear regression model, machine learning model, neural network, stock price

Procedia PDF Downloads 58
3384 Filter for the Measurement of Supraharmonics in Distribution Networks

Authors: Sivaraman Karthikeyan

Abstract:

Due to rapidly developing power electronics devices and technologies such as power line communication or self-commutating converters, voltage and current distortion, as well as interferences, have increased in the frequency range of 2 kHz to 150 kHz; there is an urgent need for regulation of electromagnetic compatibility (EMC) standards in this frequency range. Measuring or testing compliance with emission and immunity limitations necessitates the use of precise, repeatable measuring methods. Appropriate filters to minimize the fundamental component and its harmonics below 2 kHz in the measuring signal would improve the measurement accuracy in this frequency range leading to better analysis. This paper discusses filter suggestions in the current measurement standard and proposes an infinite impulse response (IIR) filter design that is optimized for a low number of poles, strong fundamental damping, and high accuracy above 2 kHz. The new filter’s transfer function is delivered as a result. An analog implementation is derived from the overall design.

Keywords: supraharmonics, 2 kHz, 150 kHz, filter, analog filter

Procedia PDF Downloads 116
3383 Deep learning with Noisy Labels : Learning True Labels as Discrete Latent Variable

Authors: Azeddine El-Hassouny, Chandrashekhar Meshram, Geraldin Nanfack

Abstract:

In recent years, learning from data with noisy labels (Label Noise) has been a major concern in supervised learning. This problem has become even more worrying in Deep Learning, where the generalization capabilities have been questioned lately. Indeed, deep learning requires a large amount of data that is generally collected by search engines, which frequently return data with unreliable labels. In this paper, we investigate the Label Noise in Deep Learning using variational inference. Our contributions are : (1) exploiting Label Noise concept where the true labels are learnt using reparameterization variational inference, while observed labels are learnt discriminatively. (2) the noise transition matrix is learnt during the training without any particular process, neither heuristic nor preliminary phases. The theoretical results shows how true label distribution can be learned by variational inference in any discriminate neural network, and the effectiveness of our approach is proved in several target datasets, such as MNIST and CIFAR32.

Keywords: label noise, deep learning, discrete latent variable, variational inference, MNIST, CIFAR32

Procedia PDF Downloads 96
3382 Modification of Newton Method in Two Point Block Backward Differentiation Formulas

Authors: Khairil I. Othman, Nur N. Kamal, Zarina B. Ibrahim

Abstract:

In this paper, we present modified Newton method as a new strategy for improving the efficiency of Two Point Block Backward Differentiation Formulas (BBDF) when solving stiff systems of ordinary differential equations (ODEs). These methods are constructed to produce two approximate solutions simultaneously at each iteration The detailed implementation of the predictor corrector BBDF with PE(CE)2 with modified Newton are discussed. The proposed modification of BBDF is validated through numerical results on some standard problems found in the literature and comparisons are made with the existing Block Backward Differentiation Formula. Numerical results show the advantage of using the new strategy for solving stiff ODEs in improving the accuracy of the solution.

Keywords: newton method, two point, block, accuracy

Procedia PDF Downloads 331
3381 The Identification of Combined Genomic Expressions as a Diagnostic Factor for Oral Squamous Cell Carcinoma

Authors: Ki-Yeo Kim

Abstract:

Trends in genetics are transforming in order to identify differential coexpressions of correlated gene expression rather than the significant individual gene. Moreover, it is known that a combined biomarker pattern improves the discrimination of a specific cancer. The identification of the combined biomarker is also necessary for the early detection of invasive oral squamous cell carcinoma (OSCC). To identify the combined biomarker that could improve the discrimination of OSCC, we explored an appropriate number of genes in a combined gene set in order to attain the highest level of accuracy. After detecting a significant gene set, including the pre-defined number of genes, a combined expression was identified using the weights of genes in a gene set. We used the Principal Component Analysis (PCA) for the weight calculation. In this process, we used three public microarray datasets. One dataset was used for identifying the combined biomarker, and the other two datasets were used for validation. The discrimination accuracy was measured by the out-of-bag (OOB) error. There was no relation between the significance and the discrimination accuracy in each individual gene. The identified gene set included both significant and insignificant genes. One of the most significant gene sets in the classification of normal and OSCC included MMP1, SOCS3 and ACOX1. Furthermore, in the case of oral dysplasia and OSCC discrimination, two combined biomarkers were identified. The combined genomic expression achieved better performance in the discrimination of different conditions than in a single significant gene. Therefore, it could be expected that accurate diagnosis for cancer could be possible with a combined biomarker.

Keywords: oral squamous cell carcinoma, combined biomarker, microarray dataset, correlated genes

Procedia PDF Downloads 395
3380 Diagnostic Performance of Mean Platelet Volume in the Diagnosis of Acute Myocardial Infarction: A Meta-Analysis

Authors: Kathrina Aseanne Acapulco-Gomez, Shayne Julieane Morales, Tzar Francis Verame

Abstract:

Mean platelet volume (MPV) is the most accurate measure of the size of platelets and is routinely measured by most automated hematological analyzers. Several studies have shown associations between MPV and cardiovascular risks and outcomes. Although its measurement may provide useful data, MPV remains to be a diagnostic tool that is yet to be included in routine clinical decision making. The aim of this systematic review and meta-analysis is to determine summary estimates of the diagnostic accuracy of mean platelet volume for the diagnosis of myocardial infarction among adult patients with angina and/or its equivalents in terms of sensitivity, specificity, diagnostic odds ratio, and likelihood ratios, and to determine the difference of the mean MPV values between those with MI and those in the non-MI controls. The primary search was done through search in electronic databases PubMed, Cochrane Review CENTRAL, HERDIN (Health Research and Development Information Network), Google Scholar, Philippine Journal of Pathology, and Philippine College of Physicians Philippine Journal of Internal Medicine. The reference list of original reports was also searched. Cross-sectional, cohort, and case-control articles studying the diagnostic performance of mean platelet volume in the diagnosis of acute myocardial infarction in adult patients were included in the study. Studies were included if: (1) CBC was taken upon presentation to the ER or upon admission (within 24 hours of symptom onset); (2) myocardial infarction was diagnosed with serum markers, ECG, or according to accepted guidelines by the Cardiology societies (American Heart Association (AHA), American College of Cardiology (ACC), European Society of Cardiology (ESC); and, (3) if outcomes were measured as significant difference AND/OR sensitivity and specificity. The authors independently screened for inclusion of all the identified potential studies as a result of the search. Eligible studies were appraised using well-defined criteria. Any disagreement between the reviewers was resolved through discussion and consensus. The overall mean MPV value of those with MI (9.702 fl; 95% CI 9.07 – 10.33) was higher than in those of the non-MI control group (8.85 fl; 95% CI 8.23 – 9.46). Interpretation of the calculated t-value of 2.0827 showed that there was a significant difference in the mean MPV values of those with MI and those of the non-MI controls. The summary sensitivity (Se) and specificity (Sp) for MPV were 0.66 (95% CI; 0.59 - 0.73) and 0.60 (95% CI; 0.43 – 0.75), respectively. The pooled diagnostic odds ratio (DOR) was 2.92 (95% CI; 1.90 – 4.50). The positive likelihood ratio of MPV in the diagnosis of myocardial infarction was 1.65 (95% CI; 1.20 – 22.27), and the negative likelihood ratio was 0.56 (95% CI; 0.50 – 0.64). The intended role for MPV in the diagnostic pathway of myocardial infarction would perhaps be best as a triage tool. With a DOR of 2.92, MPV values can discriminate between those who have MI and those without. For a patient with angina presenting with elevated MPV values, it is 1.65 times more likely that he has MI. Thus, it is implied that the decision to treat a patient with angina or its equivalents as a case of MI could be supported by an elevated MPV value.

Keywords: mean platelet volume, MPV, myocardial infarction, angina, chest pain

Procedia PDF Downloads 58
3379 U-Net Based Multi-Output Network for Lung Disease Segmentation and Classification Using Chest X-Ray Dataset

Authors: Jaiden X. Schraut

Abstract:

Medical Imaging Segmentation of Chest X-rays is used for the purpose of identification and differentiation of lung cancer, pneumonia, COVID-19, and similar respiratory diseases. Widespread application of computer-supported perception methods into the diagnostic pipeline has been demonstrated to increase prognostic accuracy and aid doctors in efficiently treating patients. Modern models attempt the task of segmentation and classification separately and improve diagnostic efficiency; however, to further enhance this process, this paper proposes a multi-output network that follows a U-Net architecture for image segmentation output and features an additional CNN module for auxiliary classification output. The proposed model achieves a final Jaccard Index of .9634 for image segmentation and a final accuracy of .9600 for classification on the COVID-19 radiography database.

Keywords: chest X-ray, deep learning, image segmentation, image classification

Procedia PDF Downloads 111
3378 Post-Earthquake Road Damage Detection by SVM Classification from Quickbird Satellite Images

Authors: Moein Izadi, Ali Mohammadzadeh

Abstract:

Detection of damaged parts of roads after earthquake is essential for coordinating rescuers. In this study, an approach is presented for the semi-automatic detection of damaged roads in a city using pre-event vector maps and both pre- and post-earthquake QuickBird satellite images. Damage is defined in this study as the debris of damaged buildings adjacent to the roads. Some spectral and texture features are considered for SVM classification step to detect damages. Finally, the proposed method is tested on QuickBird pan-sharpened images from the Bam City earthquake and the results show that an overall accuracy of 81% and a kappa coefficient of 0.71 are achieved for the damage detection. The obtained results indicate the efficiency and accuracy of the proposed approach.

Keywords: SVM classifier, disaster management, road damage detection, quickBird images

Procedia PDF Downloads 597
3377 Upon One Smoothing Problem in Project Management

Authors: Dimitri Golenko-Ginzburg

Abstract:

A CPM network project with deterministic activity durations, in which activities require homogenous resources with fixed capacities, is considered. The problem is to determine the optimal schedule of starting times for all network activities within their maximal allowable limits (in order not to exceed the network's critical time) to minimize the maximum required resources for the project at any point in time. In case when a non-critical activity may start only at discrete moments with the pregiven time span, the problem becomes NP-complete and an optimal solution may be obtained via a look-over algorithm. For the case when a look-over requires much computational time an approximate algorithm is suggested. The algorithm's performance ratio, i.e., the relative accuracy error, is determined. Experimentation has been undertaken to verify the suggested algorithm.

Keywords: resource smoothing problem, CPM network, lookover algorithm, lexicographical order, approximate algorithm, accuracy estimate

Procedia PDF Downloads 278