Search results for: measuring accuracy

Authors: Ghada S. Moussa

Abstract:

Vehicle classification is an important task in traffic surveillance and intelligent transportation systems. Classification of vehicle images is facing several problems such as: high intra-class vehicle variations, occlusion, shadow, illumination. These problems and others must be considered to develop a reliable vehicle classification system. In this study, a reliable multi-type vehicle classification system based on Bag-of-Words (BoW) paradigm is developed. Our proposed system used and compared four well-known classifiers; Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), k-Nearest Neighbour (KNN), and Decision Tree to classify vehicles into four categories: motorcycles, small, medium and large. Experiments on a large dataset show that our approach is efficient and reliable in classifying vehicles with accuracy of 95.7%. The SVM outperforms other classification algorithms in terms of both accuracy and robustness alongside considerable reduction in execution time. The innovativeness of developed system is it can serve as a framework for many vehicle classification systems.

Keywords: vehicle classification, bag-of-words technique, SVM classifier, LDA classifier, KNN classifier, decision tree classifier, SIFT algorithm

Procedia PDF Downloads 358

Authors: O. Behar, A. Khellaf, K. Mohammedi, S. Ait Kaci

Abstract:

Up to now, most validation studies have been based on the MBE and RMSE, and therefore, focused only on long and short terms performance to test and classify solar radiation models. This traditional analysis does not take into account the quality of modeling and linearity. In our analysis we have tested 22 solar radiation models that are capable to provide instantaneous direct and global radiation at any given location Worldwide. We introduce a new indicator, which we named Global Accuracy Indicator (GAI) to examine the linear relationship between the measured and predicted values and the quality of modeling in addition to long and short terms performance. Note that the quality of model has been represented by the T-Statistical test, the model linearity has been given by the correlation coefficient and the long and short term performance have been respectively known by the MBE and RMSE. An important founding of this research is that the use GAI allows avoiding default validation when using traditional methodology that might results in erroneous prediction of solar power conversion systems performances.

Keywords: solar radiation model, parametric model, performance analysis, Global Accuracy Indicator (GAI)

Procedia PDF Downloads 351

Authors: Su Nandar Tin, Wutjanun Muttitanon

Abstract:

The availability of free global and historical satellite imagery provides a valuable opportunity for mapping and monitoring the year by year for the built-up area, constantly and effectively. Land distribution guidelines and identification of changes are important in preparing and reviewing changes in the ground overview data. This study utilizes Landsat images for thirty years of information to acquire significant, and land spread data that are extremely valuable for urban arranging. This paper is mainly introducing to focus the basic of extracting built-up area for the city development area from the satellite images of LANDSAT 5,7,8 and Sentinel 2A from USGS in every five years. The purpose analyses the changing of the urban built-up area according to the year by year and to get the accuracy of mapping built-up and bare land areas in studying the trend of urban built-up changes the periods from 1990 to 2020. The GIS tools such as raster calculator and built-up area modelling are using in this study and then calculating the indices, which include enhanced built-up and bareness index (EBBI), Normalized difference Built-up index (NDBI), Urban index (UI), Built-up index (BUI) and Normalized difference bareness index (NDBAI) are used to get the high accuracy urban built-up area. Therefore, this study will point out a variable approach to automatically mapping typical enhanced built-up and bare land changes (EBBI) with simple indices and according to the outputs of indexes. Therefore, the percentage of the outputs of enhanced built-up and bareness index (EBBI) of the sentinel-2A can be realized with 48.4% of accuracy than the other index of Landsat images which are 15.6% in 1990 where there is increasing urban expansion area from 43.6% in 1990 to 92.5% in 2020 on the study area for last thirty years.

Keywords: built-up area, EBBI, NDBI, NDBAI, urban index

Procedia PDF Downloads 173

Authors: Hosein Falahaty, Hitoshi Gotoh, Abbas Khayyer

Abstract:

Performance of a Hamiltonian based particle method in simulation of nonlinear structural dynamics is subjected to investigation in terms of stability and accuracy. The governing equation of motion is derived based on Hamilton's principle of least action, while the deformation gradient is obtained according to Weighted Least Square method. The hyper-elasticity models of Saint Venant-Kirchhoff and a compressible version similar to Mooney- Rivlin are engaged for the calculation of second Piola-Kirchhoff stress tensor, respectively. Stability along with accuracy of numerical model is verified by reproducing critical stress fields in static and dynamic responses. As the results, although performance of Hamiltonian based model is evaluated as being acceptable in dealing with intense extensional stress fields, however kinds of instabilities reveal in the case of violent collision which can be most likely attributed to zero energy singular modes.

Keywords: Hamilton's principle of least action, particle-based method, hyper-elasticity, analysis of stability

Procedia PDF Downloads 341

Authors: Brindha Senthil Kumar, Payel Chakraborty, Senthil Kumar Nachimuthu, Arindam Maitra, Prem Nath

Abstract:

Gastric cancer is predominantly caused by demographic and diet factors as compared to other cancer types. The aim of the study is to predict Early Gastric Cancer (ECG) from diet and lifestyle factors using supervised machine learning algorithms. For this study, 160 healthy individual and 80 cases were selected who had been followed for 3 years (2016-2019), at Civil Hospital, Aizawl, Mizoram. A dataset containing 11 features that are core risk factors for the gastric cancer were extracted. Supervised machine algorithms: Logistic Regression, Naive Bayes, Support Vector Machine (SVM), Multilayer perceptron, and Random Forest were used to analyze the dataset using Python Jupyter Notebook Version 3. The obtained classified results had been evaluated using metrics parameters: minimum_false_positives, brier_score, accuracy, precision, recall, F1_score, and Receiver Operating Characteristics (ROC) curve. Data analysis results showed Naive Bayes - 88, 0.11; Random Forest - 83, 0.16; SVM - 77, 0.22; Logistic Regression - 75, 0.25 and Multilayer perceptron - 72, 0.27 with respect to accuracy and brier_score in percent. Naive Bayes algorithm out performs with very low false positive rates as well as brier_score and good accuracy. Naive Bayes algorithm classification results in predicting ECG showed very satisfactory results using only diet cum lifestyle factors which will be very helpful for the physicians to educate the patients and public, thereby mortality of gastric cancer can be reduced/avoided with this knowledge mining work.

Keywords: Early Gastric cancer, Machine Learning, Diet, Lifestyle Characteristics

Procedia PDF Downloads 161

Authors: Ronak Khosravi, Mahmood Abbasi Layegh, Siamak Haghipour, Avin Esmaili

Abstract:

In this paper, a study on classification of musical woodwind instruments using a small set of features selected from a broad range of extracted ones by the sequential forward selection method was carried out. Firstly, we extract 42 features for each record in the music database of 402 sound files belonging to five different groups of Flutes (end blown and internal duct), Single –reed, Double –reed (exposed and capped), Triple reed and Quadruple reed. Then, the sequential forward selection method is adopted to choose the best feature set in order to achieve very high classification accuracy. Two different classification techniques of support vector machines and relevance vector machines have been tested out and an accuracy of up to 96% can be achieved by using 21 time, frequency and coefficient features and relevance vector machine with the Gaussian kernel function.

Keywords: coefficient features, relevance vector machines, spectral features, support vector machines, temporal features

Procedia PDF Downloads 321

Authors: Bandhan Dey, Muhsina Bintoon Yiasha, Gulam Sulaman Choudhury

Abstract:

Chest disease is one of the most problematic ailments in our regular life. There are many known chest diseases out there. Diagnosing them correctly plays a vital role in the process of treatment. There are many methods available explicitly developed for different chest diseases. But the most common approach for diagnosing these diseases is through X-ray. In this paper, we proposed a multi-classification deep learning model for diagnosing COVID-19, lung cancer, pneumonia, tuberculosis, and atelectasis from chest X-rays. In the present work, we used the transfer learning method for better accuracy and fast training phase. The performance of three architectures is considered: InceptionV3, VGG-16, and VGG-19. We evaluated these deep learning architectures using public digital chest x-ray datasets with six classes (i.e., COVID-19, lung cancer, pneumonia, tuberculosis, atelectasis, and normal). The experiments are conducted on six-classification, and we found that VGG16 outperforms other proposed models with an accuracy of 95%.

Keywords: deep learning, image classification, X-ray images, Tensorflow, Keras, chest diseases, convolutional neural networks, multi-classification

Procedia PDF Downloads 92

Authors: Chhabi Nigam, S. Ramakrishnan

Abstract:

This paper brings out the analysis of the airborne Synthetic Aperture Radar (SAR) data to study the impact of Doppler centroid on Image quality and geocoding accuracy from the perspective of Stripmap mode of data acquisition. Although in Stripmap mode of data acquisition radar beam points at 90 degrees broad side (side looking), shift in the Doppler centroid is invariable due to platform motion. In-accurate estimation of Doppler centroid leads to poor image quality and image miss-registration. The effect of Doppler centroid is analyzed in this paper using multiple sets of data collected from airborne platform. Occurrences of ghost (ambiguous) targets and their power levels have been analyzed that impacts appropriate choice of PRF. Effect of aircraft attitudes (roll, pitch and yaw) on the Doppler centroid is also analyzed with the collected data sets. Various stages of the RDA (Range Doppler Algorithm) algorithm used for image formation in Stripmap mode, range compression, Doppler centroid estimation, azimuth compression, range cell migration correction are analyzed to find the performance limits and the dependence of the imaging geometry on the final image. The ability of Doppler centroid estimation to enhance the imaging accuracy for registration are also illustrated in this paper. The paper also tries to bring out the processing of low squint SAR data, the challenges and the performance limits imposed by the imaging geometry and the platform dynamics on the final image quality metrics. Finally, the effect on various terrain types, including land, water and bright scatters is also presented.

Keywords: ambiguous target, Doppler Centroid, image registration, Airborne SAR

Procedia PDF Downloads 218

Authors: Ayhan Kucukmanisa, Orhan Akbulut, Oguzhan Urhan

Abstract:

Nowadays, advanced driver assistance systems (ADAS) have become popular, since they enable safe driving. Lane detection is a vital step for ADAS. The performance of the lane detection process is critical to obtain a high accuracy lane departure warning system (LDWS). Challenging factors such as road cracks, erosion of lane markings, weather conditions might affect the performance of a lane detection system. In this paper, 1-D weighted filter based on row filtering to detect lane marking is proposed. 2-D input image is filtered by 1-D weighted filter considering four-pixel values located symmetrically around the center of candidate pixel. Performance evaluation is carried out by two metrics which are true positive rate (TPR) and false positive rate (FPR). Experimental results demonstrate that the proposed approach provides better lane marking detection accuracy compared to the previous methods while providing real-time processing performance.

Keywords: lane marking filter, lane detection, ADAS, LDWS

Procedia PDF Downloads 194

Authors: Yang Zhang, Jian He

Abstract:

Heart disease is one of the leading causes of death in the world, and coronary heart disease (CHD) is one of the major heart diseases. Electrocardiogram (ECG) is widely used in the detection of heart diseases, but the traditional manual method for CHD prediction by analyzing ECG requires lots of professional knowledge for doctors. This paper introduces sliding window and continuous wavelet transform (CWT) to transform ECG signals into images, and then ResNet and Bi-LSTM are introduced to build the ECG feature extraction network (namely ECGNet). At last, an auxiliary system for coronary heart disease prediction was developed based on modified ResNet18 and Bi-LSTM, and the public ECG dataset of CHD from MIMIC-3 was used to train and test the system. The experimental results show that the accuracy of the method is 83%, and the F1-score is 83%. Compared with the available methods for CHD prediction based on ECG, such as kNN, decision tree, VGGNet, etc., this method not only improves the prediction accuracy but also could avoid the degradation phenomenon of the deep learning network.

Keywords: Bi-LSTM, CHD, ECG, ResNet, sliding window

Procedia PDF Downloads 89

Authors: Okhee Woo

Abstract:

Purpose: With increasing concern of individual radiation exposure doses, studies analyzing radiation dosage in breast imaging modalities are required. Aim of this study is to compare radiation dosage and image quality between digital breast tomosynthesis (DBT) and full-field digital mammography (FFDM). Methods and Materials: 303 patients (mean age 52.1 years) who studied DBT and FFDM were retrospectively reviewed. Radiation dosage data were obtained by radiation dosage scoring and monitoring program: Radimetrics (Bayer HealthCare, Whippany, NJ). Entrance dose and mean glandular doses in each breast were obtained in both imaging modalities. To compare the image quality of DBT with two-dimensional synthesized mammogram (2DSM) and FFDM, 5-point scoring of lesion clarity was assessed and the better modality between the two was selected. Interobserver performance was compared with kappa values and diagnostic accuracy was compared using McNemar test. The parameters of radiation dosages (entrance dose, mean glandular dose) and image quality were compared between two modalities by using paired t-test and Wilcoxon rank sum test. Results: For entrance dose and mean glandular doses for each breasts, DBT had lower values compared with FFDM (p-value < 0.0001). Diagnostic accuracy did not have statistical difference, but lesion clarity score was higher in DBT with 2DSM and DBT was chosen as a better modality compared with FFDM. Conclusion: DBT showed lower radiation entrance dose and also lower mean glandular doses to both breasts compared with FFDM. Also, DBT with 2DSM had better image quality than FFDM with similar diagnostic accuracy, suggesting that DBT may have a potential to be performed as an alternative to FFDM.

Keywords: radiation dose, DBT, digital mammography, image quality

Procedia PDF Downloads 349

Authors: Ibrahim Khan, Waqas Khalid

Abstract:

The Healthcare sector is known to consume a higher proportion of total energy consumption in the HVAC market owing to an excessive cooling and heating requirement in maintaining human thermal comfort in indoor conditions, catering to patients undergoing treatment in hospital wards, rooms, and intensive care units. The indoor thermal comfort conditions in selected hospitals of Islamabad, Pakistan, were measured on a real-time basis with the collection of first-hand experimental data using calibrated sensors measuring Ambient Temperature, Wet Bulb Globe Temperature, Relative Humidity, Air Velocity, Light Intensity and CO2 levels. The Experimental data recorded was analyzed in conjunction with the Thermal Comfort Questionnaire Surveys, where the participants, including patients, doctors, nurses, and hospital staff, were assessed based on their thermal sensation, acceptability, preference, and comfort responses. The Recorded Dataset, including experimental and survey-based responses, was further analyzed in the development of a correlation between operative temperature, operative relative humidity, and other measured operative parameters with the predicted mean vote and adaptive predicted mean vote, with the adaptive temperature and adaptive relative humidity estimated using the seasonal data set gathered for both summer – hot and dry, and hot and humid as well as winter – cold and dry, and cold and humid climate conditions. The Machine Learning Logistic Regression Algorithm was incorporated to train the operative experimental data parameters and develop a correlation between patient sensations and the thermal environmental parameters for which a new ML-based adaptive thermal comfort model was proposed and developed in our study. Finally, the accuracy of our model was determined using the K-fold cross-validation.

Keywords: predicted mean vote, thermal comfort, energy management, logistic regression, machine learning

Procedia PDF Downloads 63

Authors: Kizito Ugochukwu Nwajeri

Abstract:

This paper explores the application of hybrid block methods for solving boundary value problems (BVPs), which are prevalent in various fields such as science, engineering, and applied mathematics. Traditionally, numerical approaches such as finite difference and shooting methods, often encounter challenges related to stability and convergence, particularly in the context of complex and nonlinear BVPs. To address these challenges, we propose a hybrid block method that integrates features from both single-step and multi-step techniques. This method allows for the simultaneous computation of multiple solution points while maintaining high accuracy. Specifically, we employ a combination of polynomial interpolation and collocation strategies to derive a system of equations that captures the behavior of the solution across the entire domain. By directly incorporating boundary conditions into the formulation, we enhance the stability and convergence properties of the numerical solution. Furthermore, we introduce an adaptive step-size mechanism to optimize performance based on the local behavior of the solution. This adjustment allows the method to respond effectively to variations in solution behavior, improving both accuracy and computational efficiency. Numerical tests on a variety of boundary value problems demonstrate the effectiveness of the hybrid block methods. These tests showcase significant improvements in accuracy and computational efficiency compared to conventional methods, indicating that our approach is robust and versatile. The results suggest that this hybrid block method is suitable for a wide range of applications in real-world problems, offering a promising alternative to existing numerical techniques.

Keywords: hybrid block methods, boundary value problem, polynomial interpolation, adaptive step-size control, collocation methods

Procedia PDF Downloads 31

Authors: Lu Yang, Meiyang Song, Xiang Yu, Wenhao Zhou, Chuntao Feng

Abstract:

To address the problem that the FM continuous-wave radar (FMCW) extracts human vital sign signals which are susceptible to noise interference and low reconstruction accuracy, a new detection scheme for the sign signals is proposed. Firstly, an improved complete ensemble empirical modal decomposition with adaptive noise (ICEEMDAN) algorithm is applied to decompose the radar-extracted thoracic signals to obtain several intrinsic modal functions (IMF) with different spatial scales, and then the IMF components are optimized by a BP neural network improved by immune genetic algorithm (IGA). The simulation results show that this scheme can effectively separate the noise and accurately extract the respiratory and heartbeat signals and improve the reconstruction accuracy and signal-to-noise ratio of the sign signals.

Keywords: frequency modulated continuous wave radar, ICEEMDAN, BP neural network, vital signs signal

Procedia PDF Downloads 165

Authors: Chaiyaporn Yuksen, Tapanawat Chaiwan

Abstract:

Introduction: Emergency medical service (EMS) care for trauma patients must be provided on-scene assessment and essential treatment and have appropriate transporting to the trauma center. The shock index (SI), reverse shock index Glasgow Coma Scale (rSIG), and National Early Warning Score (NEWS) triage tools are easy to use in a prehospital setting. There is no standardized on-scene triage protocol in prehospital care. The primary objective was to determine the accuracy of SI, rSIG, and NEWS to predict the severity of trauma patients in the emergency department (ED). Methods: This was a retrospective cross-sectional and diagnostic research conducted on trauma patients transported by EMS to the ED of Ramathibodi Hospital, a university-affiliated super tertiary care hospital in Bangkok, Thailand, from January 2015 to September 2022. We included the injured patients receiving prehospital care and transport to the ED of Ramathibodi Hospital by the EMS team from January 2015 to September 2022. We compared the on-scene parameter (SI, rSIG, and NEWS) and ED (Emergency Severity Index) with the area under ROC. Results: 218 patients were traumatic patients transported by EMS to the ED. 161 was ESI level 1-2, and 57 was level 3-5. NEWS was a more accurate triage tool to discriminate the severity of trauma patients than rSIG and SI. The area under the ROC was 0.743 (95%CI 0.70-0.79), 0.649 (95%CI 0.59-0.70), and 0.582 (95%CI 0.52-0.65), respectively (P-value <0.001). The cut point of NEWS to discriminate was 6 points. Conclusions: The NEWs was the most accurate triage tool in prehospital seeing in trauma patients.

Keywords: on-scene triage, trauma patient, ED triage, accuracy, NEWS

Procedia PDF Downloads 126

Authors: Agata Tomaszewska, Timothy Kamps, Stephan R. Turnock, Nicola Symonds

Abstract:

Bob skeleton is a highly competitive sport in which an athlete reaches speeds up to 40 m/s sliding, head first, down an ice track. It is believed that the friction between the runners and ice significantly contributes to the amount of the total energy loss during a bob skeleton descent. There is only limited available experimental data regarding the friction of bob skeleton runners or indeed steel on the ice at high sliding speeds ( > 20 m/s). Testing methods used to investigate the friction of steel on ice in winter sports have been outlined, and their accuracy and repeatability discussed. A system thinking approach was used to investigate the runner-ice interaction during sliding and create concept designs of three ice tribometers. The operational envelope of the bob skeleton system has been defined through mathematical modelling. Designs of a drum, linear and inertia pin-on-disk tribometers were developed specifically for bob skeleton runner testing with the requirement of reaching up to 40 m/s speed and facilitate fresh ice sliding. The design constraints have been outline and the proposed solutions compared based on the ease of operation, accuracy and the development cost.

Keywords: bob skeleton, ice friction, high-speed tribometers, sliding friction

Procedia PDF Downloads 261

Authors: R. B. Knudsen, O. T. Rasmussen, R. A. Alphinas

Abstract:

The reason for conducting this research is to develop an algorithm that is capable of classifying news articles from the automobile industry, according to the competitive actions that they entail, with the use of Text Mining (TM) methods. It is needed to test how to properly preprocess the data for this research by preparing pipelines which fits each algorithm the best. The pipelines are tested along with nine different classification algorithms in the realm of regression, support vector machines, and neural networks. Preliminary testing for identifying the optimal pipelines and algorithms resulted in the selection of two algorithms with two different pipelines. The two algorithms are Logistic Regression (LR) and Artificial Neural Network (ANN). These algorithms are optimized further, where several parameters of each algorithm are tested. The best result is achieved with the ANN. The final model yields an accuracy of 0.79, a precision of 0.80, a recall of 0.78, and an F1 score of 0.76. By removing three of the classes that created noise, the final algorithm is capable of reaching an accuracy of 94%.

Keywords: Artificial Neural network, Competitive dynamics, Logistic Regression, Text classification, Text mining

Procedia PDF Downloads 121

Authors: Jennifer Buz, Alvin Spivey

Abstract:

The most common greenhouse gas emitted through human activities, carbon dioxide (CO2), is naturally consumed by plants during photosynthesis. This process is actively being monetized by companies wishing to offset their carbon dioxide emissions. For example, companies are now able to purchase protections for vegetated land due-to-be clear cut or purchase barren land for reforestation. Therefore, by actively preventing the destruction/decay of plant matter or by introducing more plant matter (reforestation), a company can theoretically offset some of their emissions. One of the biggest issues in the carbon credit market is validating and verifying carbon offsets. There is a need for a system that can accurately and frequently ensure that the areas sold for carbon credits have the vegetation mass (and therefore for carbon offset capability) they claim. Traditional techniques for measuring vegetation mass and determining health are costly and require many person-hours. Orbital Sidekick offers an alternative approach that accurately quantifies carbon mass and assesses vegetation health through satellite hyperspectral imagery, a technique which enables us to remotely identify material composition (including plant species) and condition (e.g., health and growth stage). How much carbon a plant is capable of storing ultimately is tied to many factors, including material density (primarily species-dependent), plant size, and health (trees that are actively decaying are not effectively storing carbon). All of these factors are capable of being observed through satellite hyperspectral imagery. This abstract focuses on speciation. To build a species classification model, we matched pixels in our remote sensing imagery to plants on the ground for which we know the species. To accomplish this, we collaborated with the researchers at the Teakettle Experimental Forest. Our remote sensing data comes from our airborne “Kato” sensor, which flew over the study area and acquired hyperspectral imagery (400-2500 nm, 472 bands) at ~0.5 m/pixel resolution. Coverage of the entire teakettle experimental forest required capturing dozens of individual hyperspectral images. In order to combine these images into a mosaic, we accounted for potential variations of atmospheric conditions throughout the data collection. To do this, we ran an open source atmospheric correction routine called ISOFIT1 (Imaging Spectrometer Optiman FITting), which converted all of our remote sensing data from radiance to reflectance. A database of reflectance spectra for each of the tree species within the study area was acquired using the Teakettle stem map and the geo-referenced hyperspectral images. We found that a wide variety of machine learning classifiers were able to identify the species within our images with high (>95%) accuracy. For the most robust quantification of carbon mass and the best assessment of the health of a vegetated area, speciation is critical. Through the use of high resolution hyperspectral data, ground-truth databases, and complex analytical techniques, we are able to determine the species present within a pixel to a high degree of accuracy. These species identifications will feed directly into our carbon mass model.

Keywords: hyperspectral, satellite, carbon, imagery, python, machine learning, speciation

Procedia PDF Downloads 130

Authors: Chen-Yin Kuo, Yung-Hsin Lee

Abstract:

Previous studies applying residual income valuation (RIV) model generally use panel data and single-equation model to forecast stock prices. Unlike these, this paper uses Taiwan longitudinal data to estimate multi-equation time-series models such as Vector Autoregressive (VAR), Vector Error Correction Model (VECM), and conduct out-of-sample forecasting. Further, this work assesses their forecasting performance by two instruments. In favor of extant research, the major finding shows that VECM outperforms other three models in forecasting for three stock sectors over entire horizons. It implies that an error correction term containing long-run information contributes to improve forecasting accuracy. Moreover, the pattern of composite shows that at longer horizon, VECM produces the greater reduction in errors, and performs substantially better than VAR.

Keywords: residual income valuation model, vector error correction model, out of sample forecasting, forecasting accuracy

Procedia PDF Downloads 316

Authors: Misrak Assefa

Abstract:

The Amharic language is the second most widely spoken Semitic language in the world. There are several new overloaded on the web. Searching some useful documents from the web on a specific topic, which is written in the Amharic language, is a challenging task. Hence, document categorization is required for managing and filtering important information. In the classification of Amharic text news, there is still a gap in the domain of information that needs to be launch. This study attempts to design an automatic Amharic news classification using a supervised learning mechanism on four un-touch classes. To achieve this research, 4,182 news articles were used. Naive Bayes (NB) and Decision tree (j48) algorithms were used to classify the given Amharic dataset. In this paper, k-fold cross-validation is used to estimate the accuracy of the classifier. As a result, it shows those algorithms can be applicable in Amharic news categorization. The best average accuracy result is achieved by j48 decision tree and naïve Bayes is 95.2345 %, and 94.6245 % respectively using three categories. This research indicated that a typical decision tree algorithm is more applicable to Amharic news categorization.

Keywords: text categorization, supervised machine learning, naive Bayes, decision tree

Procedia PDF Downloads 211

Authors: Retno Supriyanti, Best Leader Nababan, Yogi Ramadhani, Wahyu Siswandari

Abstract:

Blood cell morphology is an important parameter in a hematology test. Currently, in developing countries, a lot of hematology is done manually, either by physicians or laboratory staff. According to the limitation of the human eye, examination based on manual method will result in a lower precision and accuracy. In addition, the hematology test by manual will further complicate the diagnosis in some areas that do not have competent medical personnel. This research aims to develop a simple tool in the detection of blood cell morphology-based computer. In this paper, we focus on the detection of the outer contour of leukocytes. The results show that the system that we developed is promising for detecting blood cell morphology automatically. It is expected, by implementing this method, the problem of accuracy, precision and limitations of the medical staff can be solved.

Keywords: morphology operation, developing countries, hematology test, limitation of medical personnel

Procedia PDF Downloads 338

Authors: Xiaohan Bookman, Xiaoyan Zhu

Abstract:

Margin-Based Principle has been proposed for a long time, it has been proved that this principle could reduce the structural risk and improve the performance in both theoretical and practical aspects. Meanwhile, feed-forward neural network is a traditional classifier, which is very hot at present with a deeper architecture. However, the training algorithm of feed-forward neural network is developed and generated from Widrow-Hoff Principle that means to minimize the squared error. In this paper, we propose a new training algorithm for feed-forward neural networks based on Margin-Based Principle, which could effectively promote the accuracy and generalization ability of neural network classifiers with less labeled samples and flexible network. We have conducted experiments on four UCI open data sets and achieved good results as expected. In conclusion, our model could handle more sparse labeled and more high-dimension data set in a high accuracy while modification from old ANN method to our method is easy and almost free of work.

Keywords: Max-Margin Principle, Feed-Forward Neural Network, classifier, structural risk

Procedia PDF Downloads 341

Authors: Yousef Reda

Abstract:

Pancreatic cancer has an overall dismal prognosis. CT, MRI and Endoscopic Ultrasound are most often used to establish the diagnosis. We present a case of a patient found on abdominal CT and MRI to have an 8 mm cystic lesion within the head of the pancreas which was thought to be a benign intraductal papillary mucinous neoplasm (IPMN). Further evaluation by EUS demonstrated a 1 cm predominantly solid mass that was proven to be an adenocarcinoma by EUS-guided FNA. The patient underwent a Whipple procedure. The final pathology confirmed a 1 cm pT1 N0 pancreatic ductal adenocarcinoma. Case: A 63-year-old male presented with left upper quadrant pain and an abdominal CT demonstrated an 8 mm lesion within the head of the pancreas that was thought to represent a side branch IPMN. An MRI also showed similar findings. Four months later due to ongoing symptoms an EUS was performed to re-evaluate the pancreatic lesion. EUS revealed a predominantly solid hypoechoic, homogeneous mass measuring 12 mm x 9 mm. EUS-guided FNA was performed and was positive for adenocarcinoma. The patient underwent a Whipple procedure that confirmed it to be a ductal adenocarcinoma, pT1N0. The solid mass was noted to be adjacent to a cystic dilation with no papillary architecture and scant epithelium. The differential diagnosis resided between cystic degeneration of a primary pancreatic adenocarcinoma versus malignant degeneration within a side-branch IPMN. Discussion: The reported sensitivity of CT for pancreatic cancer is approximately 90%. For pancreatic tumors, less than 3 cm the sensitivity of CT is reduced ranging from 67-77%. MRI does not significantly improve overall detection rates compared to CT. EUS, however is superior to CT in the detection of pancreatic cancer, in particular among lesions smaller than 3 cm. EUS also outperforms CT and MRI in distinguishing neoplastic from non-neoplastic cysts. In this case, both MRI and CT failed to detect a small pancreatic adenocarcinoma. The addition of EUS and FNA to abdominal imaging can increase overall accuracy for the diagnosis of neoplastic pancreatic lesions. It may be prudent that when small lesions although appearing as a benign IPMN should further be evaluated by EUS as this would lead to potentially identifying earlier stage pancreatic cancers and improve survival in a disease which has a dismal prognosis.

Keywords: IPMN, MRI, EUS, CT

Procedia PDF Downloads 264

Authors: Ahmed Abdulla Ashlam, Atta Badii, Frederic Stahl

Abstract:

In recent years, SQL injection attacks have been identified as being prevalent against web applications. They affect network security and user data, which leads to a considerable loss of money and data every year. This paper presents the use of classification algorithms in machine learning using a method to classify the login data filtering inputs into "SQLi" or "Non-SQLi,” thus increasing the reliability and accuracy of results in terms of deciding whether an operation is an attack or a valid operation. A method Web-App auto-generated twin data structure replication. Shielding against SQLi attacks (WebAppShield) that verifies all users and prevents attackers (SQLi attacks) from entering and or accessing the database, which the machine learning module predicts as "Non-SQLi" has been developed. A special login form has been developed with a special instance of data validation; this verification process secures the web application from its early stages. The system has been tested and validated, up to 99% of SQLi attacks have been prevented.

Keywords: SQL injection, attacks, web application, accuracy, database

Procedia PDF Downloads 151

Authors: Laid Fekih

Abstract:

Background: It is difficult to detect lying, deception, and misrepresentation just by looking at verbal or non-verbal expression during the criminal investigation process, as there is a common belief that it is possible to tell whether a person is lying or telling the truth just by looking at the way they act or behave. The process of detecting lies and deception during the criminal investigation process needs more studies and research to overcome the difficulties facing the investigators. Method: The present study aimed to identify the effectiveness of cognitive methods and techniques in detecting deception during the criminal investigation. It adopted the quasi-experimental method and covered a sample of (20) defendants distributed randomly into two homogeneous groups, an experimental group of (10) defendants be subject to criminal investigation by applying cognitive techniques to detect deception and a second experimental group of (10) defendants be subject to the direct investigation method. The tool that used is a guided interview based on models of investigative questions according to the cognitive deception detection approach, which consists of three techniques of Vrij: imposing the cognitive burden, encouragement to provide more information, and ask unexpected questions, and the Direct Investigation Method. Results: Results revealed a significant difference between the two groups in term of lie detection accuracy in favour of defendants be subject to criminal investigation by applying cognitive techniques, the cognitive deception detection approach produced superior total accuracy rates both with human observers and through an analysis of objective criteria. The cognitive deception detection approach produced superior accuracy results in truth detection: 71%, deception detection: 70% compared to a direct investigation method truth detection: 52%; deception detection: 49%. Conclusion: The study recommended if practitioners use a cognitive deception detection technique, they will correctly classify more individuals than when they use a direct investigation method.

Keywords: the cognitive lie detection approach, deception, criminal investigation, mental health

Procedia PDF Downloads 66

Authors: Habtamu Ayenew Asegie

Abstract:

Wealth, as opposed to income or consumption, implies a more stable and permanent status. Due to natural and human-made difficulties, households' economies will be diminished, and their well-being will fall into trouble. Hence, governments and humanitarian agencies offer considerable resources for poverty and malnutrition reduction efforts. One key factor in the effectiveness of such efforts is the accuracy with which low-income or poor populations can be identified. As a result, this study aims to predict a household’s wealth status using ensemble Machine learning (ML) algorithms. In this study, design science research methodology (DSRM) is employed, and four ML algorithms, Random Forest (RF), Adaptive Boosting (AdaBoost), Light Gradient Boosted Machine (LightGBM), and Extreme Gradient Boosting (XGBoost), have been used to train models. The Ethiopian Demographic and Health Survey (EDHS) dataset is accessed for this purpose from the Central Statistical Agency (CSA)'s database. Various data pre-processing techniques were employed, and the model training has been conducted using the scikit learn Python library functions. Model evaluation is executed using various metrics like Accuracy, Precision, Recall, F1-score, area under curve-the receiver operating characteristics (AUC-ROC), and subjective evaluations of domain experts. An optimal subset of hyper-parameters for the algorithms was selected through the grid search function for the best prediction. The RF model has performed better than the rest of the algorithms by achieving an accuracy of 96.06% and is better suited as a solution model for our purpose. Following RF, LightGBM, XGBoost, and AdaBoost algorithms have an accuracy of 91.53%, 88.44%, and 58.55%, respectively. The findings suggest that some of the features like ‘Age of household head’, ‘Total children ever born’ in a family, ‘Main roof material’ of their house, ‘Region’ they lived in, whether a household uses ‘Electricity’ or not, and ‘Type of toilet facility’ of a household are determinant factors to be a focal point for economic policymakers. The determinant risk factors, extracted rules, and designed artifact achieved 82.28% of the domain expert’s evaluation. Overall, the study shows ML techniques are effective in predicting the wealth status of households.

Keywords: ensemble machine learning, households wealth status, predictive model, wealth status prediction

Procedia PDF Downloads 39

Authors: Sultan Mahmud, Qamar Zaman, Travis Esau, Young Chang

Abstract:

Strawberry powdery mildew (PM) is a serious disease that has a significant impact on strawberry production. Field scouting is still a major way to find PM disease, which is not only labor intensive but also almost impossible to monitor disease severity. To reduce the loss caused by PM disease and achieve faster automatic detection of the disease, this paper proposes an approach for detection of the disease, based on image texture and classified with support vector machines (SVMs) and k-nearest neighbors (kNNs). The methodology of the proposed study is based on image processing which is composed of five main steps including image acquisition, pre-processing, segmentation, features extraction and classification. Two strawberry fields were used in this study. Images of healthy leaves and leaves infected with PM (Sphaerotheca macularis) disease under artificial cloud lighting condition. Colour thresholding was utilized to segment all images before textural analysis. Colour co-occurrence matrix (CCM) was introduced for extraction of textural features. Forty textural features, related to a physiological parameter of leaves were extracted from CCM of National television system committee (NTSC) luminance, hue, saturation and intensity (HSI) images. The normalized feature data were utilized for training and validation, respectively, using developed classifiers. The classifiers have experimented with internal, external and cross-validations. The best classifier was selected based on their performance and accuracy. Experimental results suggested that SVMs classifier showed 98.33%, 85.33%, 87.33%, 93.33% and 95.0% of accuracy on internal, external-I, external-II, 4-fold cross and 5-fold cross-validation, respectively. Whereas, kNNs results represented 90.0%, 72.00%, 74.66%, 89.33% and 90.3% of classification accuracy, respectively. The outcome of this study demonstrated that SVMs classified PM disease with a highest overall accuracy of 91.86% and 1.1211 seconds of processing time. Therefore, overall results concluded that the proposed study can significantly support an accurate and automatic identification and recognition of strawberry PM disease with SVMs classifier.

Keywords: powdery mildew, image processing, textural analysis, color co-occurrence matrix, support vector machines, k-nearest neighbors

Procedia PDF Downloads 120

Authors: M. Zaitoun, S. Cumming, A. Purcell

Abstract:

This study aims to determine if audiologists' experience characteristics in ABR (Auditory Brainstem Response) reading is associated with their performance in interpreting ABR results. Fifteen ABR traces with varying degrees of hearing level were presented twice, making a total of 30. Audiologists were asked to determine the hearing threshold for each of the cases after completing a brief survey regarding their experience and training in ABR administration. Sixty-one audiologists completed all tasks. Correlations between audiologists’ performance measures and experience variables suggested significant associations (p < 0.05) between training period in ABR testing and audiologists’ performance in terms of both sensitivity and accuracy. In addition, the number of years conducting ABR testing correlated with specificity. No other correlations approached significance. While there are relatively few significant correlations between ABR performance and experience, accuracy in ABR reading is associated with audiologists’ length of experience and period of training. To improve audiologists’ performance in reading ABR results, an emphasis on the importance of training should be raised and standardized levels and period for audiologists training in ABR testing should also be set.

Keywords: ABR, audiology, performance, training, experience

Procedia PDF Downloads 166

Authors: Muhammad Solikhudin Nafi, Wahyu Afif Mufida, Mita Erna Wati, Fitri Setyani Rokim, M. Al-Rizqi Dharma Fauzi

Abstract:

High dose activity without any pre-exercise will impact Delayed Onset Muscle Soreness (DOMS). DOMS known as delayed pain post-exercise and induce skeletal injury which will decrease athletes’ performances. From now on, post-exercise muscle damage can be detected by measuring skeletal troponin I (sTnI) concentration in serum using ELISA but this method needs more time and cost. To prevent decreased athletes performances, screening need to be done rapidly. We want to introduce our new prototype to detect DOMS acutely. Rapid detection tests are based on immunological reaction between skeletal troponin I antibodies and sTnI in human serum or whole blood. Chemical methods that are used in the manufacture of diagnostic test is lateral flow immunoassay. The material used is rat monoclonal antibody sTnI, colloidal gold, anti-mouse IgG, nitrocellulose membrane, conjugate pad, sample pad, wick and backing card. The procedure are made conjugate (colloidal gold and mAb sTnI) and insert into the conjugate pad, gives spray sTnI mAb and anti-mouse IgG into nitrocellulose membrane, and assemble RDT. RDT had been evaluated by measuring the sensitivity of positive human serum (n = 30) and negative human serum (n = 30). Overall sensitivity value was 93% and specificity value was 90%. ADCOR as the first rapid detection test qualitatively showed antigen-antibody reaction and showed good overall performances for screening of muscle damage. Furthermore, these finding still need more improvements to get best results.

Keywords: DOMS, sTnI, rapid detection test, ELISA

Procedia PDF Downloads 513

Authors: Adji Achmad Rinaldo Fernandes

Abstract:

The research was conducted to apply semiparametric SEM modeling to the timeliness of paying credit. Semiparametric SEM is structural modeling in which two combined approaches of parametric and nonparametric approaches are used. The analysis method in this research is semiparametric SEM with a nonparametric approach using a truncated spline. The data in the study were obtained through questionnaires distributed to Bank X mortgage debtors and are confidential. The study used 3 variables consisting of one exogenous variable, one intervening endogenous variable, and one endogenous variable. The results showed that (1) the effect of capacity and willingness to pay variables on timeliness of payment is significant, (2) modeling the capacity variable on willingness to pay also produces a significant estimate, (3) the effect of the capacity variable on the timeliness of payment variable is not influenced by the willingness to pay variable as an intervening variable, (4) the R^2 value of 0.763 or 76.33% indicates that the model has good predictive relevance.

Keywords: structural equation modeling semiparametric, credit bank, accuracy of payment time, willingness to pay

Procedia PDF Downloads 44