Search results for: slice position accuracy

Authors: Jonathan Gong

Abstract:

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

Keywords: artificial intelligence, convolutional neural networks, deep learning, image processing, machine learning

Procedia PDF Downloads 99

Authors: C. Rana, S. K. Jain

Abstract:

The enormous amount of Web data has challenged its usage in efficient manner in the past few years. As such, a range of techniques are applied to tackle this problem; prominent among them is personalization and recommender system. In fact, these are the tools that assist user in finding relevant information of web. Most of the e-commerce websites are applying such tools in one way or the other. In the past decade, a large number of recommendation algorithms have been proposed to tackle such problems. However, there have not been much research in the evaluation criteria for these algorithms. As such, the traditional accuracy and classification metrics are still used for the evaluation purpose that provides a static view. This paper studies how the evolution of user preference over a period of time can be mapped in a recommender system using a new evaluation methodology that explicitly using time dimension. We have also presented different types of experimental set up that are generally used for recommender system evaluation. Furthermore, an overview of major accuracy metrics and metrics that go beyond the scope of accuracy as researched in the past few years is also discussed in detail.

Keywords: collaborative filtering, data mining, evolutionary, clustering, algorithm, recommender systems

Procedia PDF Downloads 381

Authors: Huda Algharib, Amal Algharib, Hanan Algharib, Ali Mohammad Alqudah

Abstract:

Image registration is an important topic for many imaging systems and computer vision applications. The standard image registration techniques such as Mutual information/ Normalized mutual information -based methods have a limited performance because they do not consider the spatial information or the relationships between the neighbouring pixels or voxels. In addition, the amount of image noise may significantly affect the registration accuracy. Therefore, this paper proposes an efficient method that explicitly considers the relationships between the adjacent pixels, where the gradient information of the reference and scene images is extracted first, and then the cosine similarity of the extracted gradient information is computed and used to improve the accuracy of the standard normalized mutual information measure. Our experimental results on different data types (i.e. CT, MRI and thermal images) show that the proposed method outperforms a number of image registration techniques in terms of the accuracy.

Keywords: image registration, mutual information, image gradients, image transformations

Procedia PDF Downloads 218

Authors: David Tena-Gago, Jose M. Alcaraz Calero, Qi Wang

Abstract:

The evolution and integration of automated vehicles have become more and more tangible in recent years. State-of-the-art technological advances in the field of camera-based Artificial Intelligence (AI) and computer vision greatly favor the performance and reliability of the Advanced Driver Assistance System (ADAS), leading to a greater knowledge of vehicular operation and resembling human behavior. However, the exclusive use of this technology still seems insufficient to control vehicular operation at 100%. To reveal the degree of accuracy of the current camera-based automated driving AI modules, this paper studies the structure and behavior of one of the main solutions in a controlled testing environment. The results obtained clearly outline the lack of reliability when using exclusively the AI model in the perception stage, thereby entailing using additional complementary sensors to improve its safety and performance.

Keywords: accuracy assessment, AI-driven mobility, artificial intelligence, automated vehicles

Procedia PDF Downloads 85

Authors: Wenlong Feng, Zhenchun Du, Jianguo Yang

Abstract:

To decrease the grating scale thermal expansion error, a novel method which based on multiple temperature detections is proposed. Several temperature sensors are installed on the grating scale and the temperatures of these sensors are recorded. The temperatures of every point on the grating scale are calculated by interpolating between adjacent sensors. According to the thermal expansion principle, the grating scale thermal expansion error model can be established by doing the integral for the variations of position and temperature. A novel compensation method is proposed in this paper. By applying the established error model, the grating scale thermal expansion error is decreased by 90% compared with no compensation. The residual positioning error of the grating scale is less than 15um/10m and the accuracy of the machine tool is significant improved.

Keywords: thermal expansion error of grating scale, error compensation, machine tools, integral method

Procedia PDF Downloads 340

Authors: Ninomyslaw Jakubczyk, Anna Zwierzchowska, Adam Maszczyk

Abstract:

Background: Central stabilisation training aims to improve neuromuscular coordination. It is used in the form of injury prevention and completing the swimmers' process. The aim of the study was to access the impact of this training on the results by disabled swimmers at 50 and 100 meters’ freestyle. Material/Method: 20 competitors with similar dysfunctions of the musculoskeletal system, randomly assigned to the experimental and control group, participated in the study. Each group consisted of 7 swimmers started in competitions from the standing starting position, and 3 started from the water. The study included a 4-week set of stabilization exercises, 4 times a week instead of pulling by legs. Exercises were held under specialist swimming conditions and involved controlled circuit muscle movements while maintaining a floating stable position in the water. Results: All groups improved their 'best times' besides swimmers started from standing position in the control group. There were no significant differences between intergroup and intra-group results, both at distance 50 and 100 meters’ freestyle. Conclusions: Better improvements in the experimental group were noted, but this effect cannot be attributed to 4-week stabilisation training. However, this investigation might suggest that this type of training could be beneficial for junior disabled swimmers.

Keywords: athletes, swimming, trunk exercises, youth

Procedia PDF Downloads 135

Authors: Shiva Kumar, G. S. Vijay, Srinivas Pai P., Shrinivasa Rao B. R.

Abstract:

In the present study RBF neural networks were used for predicting the performance and emission parameters of a biodiesel engine. Engine experiments were carried out in a 4 stroke diesel engine using blends of diesel and Honge methyl ester as the fuel. Performance parameters like BTE, BSEC, Tech and emissions from the engine were measured. These experimental results were used for ANN modeling. RBF center initialization was done by random selection and by using Clustered techniques. Network was trained by using fixed and varying widths for the RBF units. It was observed that RBF results were having a good agreement with the experimental results. Networks trained by using clustering technique gave better results than using random selection of centers in terms of reduced MRE and increased prediction accuracy. The average MRE for the performance parameters was 3.25% with the prediction accuracy of 98% and for emissions it was 10.4% with a prediction accuracy of 80%.

Keywords: radial basis function networks, emissions, performance parameters, fuzzy c means

Procedia PDF Downloads 531

Authors: Burcu Oksuz, Volkan Altıintas, Zulfiye Acar Senturk

Abstract:

Though in the academic literature, it is emphasized that Public Relations (PR) should not be seen only as media relations, in practise, the media relations has a very dominant position at the communication studies carried out by many companies. There are many PR practitioners who have journalism background. However the number of the practitioners who have started to work in the sector after having PR education at the universities has been highly increasing. Therefore, it can be said that previous journalist dominance has diminished at the public relations sector in Turkey. However, by virtue of the fact that some companies and practitioners consider the media coverage the first priority of PR, this much is certain that the dominant position of media relations is ongoing. On the other hand, still many companies measure the success of their PR by how much place their companies have taken. This situation creates major pressure on the PR practitioners to have close relations with the media members and to make them write articles about their companies. Thereupon, PR practitioners have to take the time for the media relations and the media relations comes into prominence more than the other PR functions. The aim of this study is to reveal the PR functions at the companies and to evaluate the position of the media relations in the PR studies. Therefore, it is aimed to find out at what extend the discourse of “Public relations is not media relations” is accepted in practice and actualised. Accordingly, a research about 15 hotel enterprises which are located in the city of İzmir will be carried out. İzmir as one of the most important tourism destinations has many hotels. The PR/corporate communications managers will be interviewed profoundly within the scope of this study and PR functions performed by hotels will be discussed in details in consideration of the datum obtained.

Keywords: media relations, public relations, public relations practitioners, Turkey

Procedia PDF Downloads 358

Authors: Maysam Shahsavari, Seyed Jamalaldin Haddadi

Abstract:

There are several methods to localize a mobile robot such as relative, absolute and probabilistic. In this paper, particle filter due to its simple implementation and the fact that it does not need to know to the starting position will be used. This method estimates the position of the mobile robot using a probabilistic distribution, relying on a known map of the environment instead of predicting it. Afterwards, it updates this estimation by reading input sensors and control commands. To receive information from the surrounding world, distance to obstacles, for example, a Kinect is used which is much cheaper than a laser range finder. Finally, after explaining the Adaptive Particle Filter method and its implementation in detail, we will compare this method with the dead reckoning method and show that this method is much more suitable for situations in which we have a map of the environment.

Keywords: particle filter, localization, methods, odometry, kinect

Procedia PDF Downloads 240

Authors: Lakhdar Rahmani, Benhanifia Kada, Brahim Mebarki

Abstract:

The present paper aims to investigate the natural convection of nanofluid (water-cu) inside a hexagonal enclosure shape embedded with a square obstacle in the presence of hot and cold side walls. The governing equations were solved in a non-uniform unstructured grid by employing the Galerkin finite element method using the software COMSOL Multiphysics. The objective of this study is to analyze the influence of Rayleigh number (103 < Ra < 105), the position of the obstacle, which is located in three different positions (center, bottom, and top side ), and the effect of Nanoparticles volume concentration (0 < Ø < 0.2) on the thermal behavior inside the enclosure, The results are reported as contours of isotherms, streamlines, and average Nusselt numbers. The obtained results illustrate that the increase in the Rayleigh number (Ra) and the Nanoparticles concentration ( Ø ) leads to an increase in the Nusselt number (Nu average ) that signifies the rate of heat transfer in the studied enclosure, in addition to the best performance observed with the position of obstacle that is located at the middle of the enclosure, where has a high effect in improving the heat transfer along the enclosure comparatively with the rest different positions.

Keywords: natural convection, nanofluid (water-Cu), hexagonal enclosure, Nusselt numbers, Rayleigh number

Procedia PDF Downloads 68

Authors: Karim Adinehvand, Bakhtiar Azadbakht, Amin Sahebnasagh

Abstract:

Relation to high absorption fraction of Tc SESTAMIBI by internal organs in heart scan, and these organs are near to generation organs (Ovaries and uterus). In this study, Liver is specified as source organ. Method: we have set amount of absorbed fraction radiopharmaceutical in position of Liver in RANDO-phantom in form of elliptical surfaces, then absorbed dose to ovaries and uterus measured by TLD-100 that had set at position of these organs in RANDO-phantom. Calculation had done by MIRD method. Results from direct measurement and MIRD method are too similar. The absorbed dose to uterus and ovaries for Rest are 26.05µGyMBq-1, 17.23µGyMBq-1 and for Stress are 2.04µGyMBq-1, 1.35µGyMBq-1 respectively.

Keywords: absorbed dose, TLD, MIRD, RANDO-phantom, Tc-99m

Procedia PDF Downloads 536

Authors: Mahdi Bazarganigilani

Abstract:

Aortic enlargement, also known as an aortic aneurysm, can occur when the walls of the aorta become weak. This disease can become deadly if overlooked and undiagnosed. In this paper, a computer-aided diagnosis (CAD) system was introduced to accurately diagnose aortic enlargement from chest x-ray images. An enhanced convolutional neural network (CNN) was employed and then trained by transfer learning by using three different main areas from the original images. The areas included the left lung, heart, and right lung. The accuracy of the system was then evaluated on 1001 samples by using 4-fold cross-validation. A promising accuracy of 90% was achieved in terms of the F-measure indicator. The results showed using different areas from the original image in the training phase of CNN could increase the accuracy of predictions. This encouraged the author to evaluate this method on a larger dataset and even on different CAD systems for further enhancement of this methodology.

Keywords: computer-aided diagnosis systems, aortic enlargement, chest X-ray, image processing, convolutional neural networks

Procedia PDF Downloads 131

Authors: Naime Boudemagh, Zoheir Hammoudi

Abstract:

The parameters estimation of the K-distribution is an essential part in radar detection. In fact, presence of interfering targets in reference cells causes a decrease in detection performances. In such situation, the estimate of the shape and the scale parameters are far from the actual values. In the order to avoid interfering targets, we propose an Automatic Censoring (AC) algorithm of radar interfering targets in K-distribution. The censoring technique used in this work offers a good discrimination between homogeneous and non-homogeneous environments. The homogeneous population is then used to estimate the unknown parameters by the classical Method of Moment (MOM). The AC algorithm does not need any prior information about the clutter parameters nor does it require both the number and the position of interfering targets. The accuracy of the estimation parameters obtained by this algorithm are validated and compared to various actual values of the shape parameter, using Monte Carlo simulations, this latter show that the probability of censing in multiple target situations are in good agreement.

Keywords: parameters estimation, method of moments, automatic censoring, K distribution

Procedia PDF Downloads 353

Authors: Keivan Seyyedi, Leila Esmaeilpour, Seyed Jamal Sadeghi

Abstract:

Investigating the effectiveness of explicit focus on form on the written performance of the EFL learners was the aim of this study. To provide empirical support for this study, sixty male English learners were selected and randomly assigned into two groups of explicit focus on form and meaning focused. Narrative writing was employed for data collection. To measure writing performance, participants were required to narrate a story. They were given 20 minutes to finish the task and were asked to write at least 150 words. The participants’ output was coded then analyzed utilizing Independent t-test for grammatical accuracy and fluency of learners’ performance. Results indicated that learners in explicit focus on form group appear to benefit from error correction and rule explanation as two pedagogical techniques of explicit focus on form with respect to accuracy, but regarding fluency they did not yield any significant differences compared to the participants of meaning-focused group.

Keywords: explicit focus on form, rule explanation, accuracy, fluency

Procedia PDF Downloads 483

Authors: José E. Q. Souza, Marcio Fontana, Antonio C. C. Lima

Abstract:

This paper presents analysis and characterization of a piezoelectric micro-generator for energy harvesting application. A low-cost experimental prototype was designed to operate as piezoelectric micro-generator in the laboratory. An input acceleration of 9.8m/s2 using a sine signal (peak-to-peak voltage: 1V, offset voltage: 0V) at frequencies ranging from 10Hz to 160Hz generated a maximum average power of 432.4μW (linear mass position = 25mm) and an average power of 543.3μW (angular mass position = 35°). These promising results show that the prototype can be considered for low consumption load application as an energy harvesting micro-generator.

Keywords: piezoelectric, micro-generator, energy harvesting, cantilever beam

Procedia PDF Downloads 441

Authors: Jeong-Won Lee, Kyeong-Ok Yoon

Abstract:

The current study aimed to investigate the effects of topic familiarity and language proficiency on linguistic aspects (lexical complexity, syntactic complexity, accuracy, and fluency) in EFL learners’ argumentative essays. For the study 64 college students were asked to write an argumentative essay for the two different topics (Driving and Smoking) chosen by the consideration of topic familiarity. The students were divided into two language proficiency groups (high-level and intermediate) according to their English writing proficiency. The findings of the study are as follows: 1) the participants of this study exhibited lower levels of lexical and syntactic complexity as well as accuracy when performing writing tasks with unfamiliar topics; and 2) they demonstrated the use of a wider range of vocabulary, and longer and more complex structures, and produced accurate and lengthier texts compared to their intermediate peers. Discussion and pedagogical implications for instruction of writing classes in EFL contexts were addressed.

Keywords: topic familiarity, complexity, accuracy, fluency

Procedia PDF Downloads 24

Authors: André Smith, Amr Abdel-Dayem

Abstract:

This paper presents an overview of the history and development of stereo matching algorithms. Details from its inception, up to relatively recent techniques are described, noting challenges that have been surmounted across these past decades. Different components of these are explored, though focus is directed towards the local matching techniques. While global approaches have existed for some time, and demonstrated greater accuracy than their counterparts, they are generally quite slow. Many strides have been made more recently, allowing local methods to catch up in terms of accuracy, without sacrificing the overall performance.

Keywords: developmental survey, local stereo matching, rectification, stereo correspondence

Procedia PDF Downloads 266

Authors: Mohamed Hamada Abdelkader Fayed

Abstract:

Background: To evaluate the diagnostic accuracy of (ADD-RS) with D-dimer as a screening test to exclude AAS. Methods: We conducted research for the studies examining the diagnostic accuracy of (ADD- RS)+ D-dimer to exclude the diagnosis of AAS, We searched MEDLINE, Embase, and Cochrane of Trials up to 31 December 2020. Results: We identified 3 studies using (ADD-RS) with D-dimer as a diagnostic tool for AAS, involving 3261 patients were AAS was diagnosed in 559(17.14%) patients. Overall results showed that the pooled sensitivities were 97.6 (95% CI 0.95.6, 99.6) at (ADD-RS)≤1(low risk group) with D-dimer and 97.4(95% CI 0.95.4,, 99.4) at (ADD-RS)>1(High risk group) with D-dimer., the failure rate was 0.48% at low risk group and 4.3% at high risk group respectively. Conclusions: (ADD-RS) with D-dimer was a useful screening test with high sensitivity to exclude Acute Aortic Syndrome.

Keywords: aortic dissection detection risk score, D-dimer, acute aortic syndrome, diagnostic accuracy

Procedia PDF Downloads 190

Authors: Pengwei Qiao, Sucai Yang, Wenxia Wei

Abstract:

Soil pollution has become an important issue in China. Accurate spatial distribution prediction of pollutants with interpolation methods is the basis for soil remediation in the site. However, a relatively strong variability of pollutants would decrease the prediction accuracy. Theoretically, partition interpolation can result in accurate prediction results. In order to verify the applicability of partition interpolation for a site, benzo (b) fluoranthene (BbF) in four soil layers was adopted as the research object in this paper. IDW (inverse distance weighting)-, RBF (radial basis function)-and OK (ordinary kriging)-based partition interpolation accuracies were evaluated, and their influential factors were analyzed; then, the uncertainty and applicability of partition interpolation were determined. Three conclusions were drawn. (1) The prediction error of partitioned interpolation decreased by 70% compared to unpartitioned interpolation. (2) Partition interpolation reduced the impact of high CV (coefficient of variation) and high concentration value on the prediction accuracy. (3) The prediction accuracy of IDW-based partition interpolation was higher than that of RBF- and OK-based partition interpolation, and it was suitable for the identification of highly polluted areas at a contaminated site. These results provide a useful method to obtain relatively accurate spatial distribution information of pollutants and to identify highly polluted areas, which is important for soil pollution remediation in the site.

Keywords: accuracy, applicability, partition interpolation, site, soil pollution, uncertainty

Procedia PDF Downloads 119

Authors: Nikhil Yadav, Shubham Verma

Abstract:

Gas lift is a common technique used to optimize oil production in wells. Prosper software is a powerful tool for modeling and optimizing gas lift systems in oil wells. This review paper examines the effectiveness of Prosper software in optimizing gas lift systems in oil-producing wells. The literature review identified several studies that demonstrated the use of Prosper software to adjust injection rate, depth, and valve characteristics to optimize gas lift system performance. The results showed that Prosper software can significantly improve production rates and reduce operating costs in oil-producing wells. However, the accuracy of the model depends on the accuracy of the input data, and the cost of Prosper software can be high. Therefore, further research is needed to improve the accuracy of the model and evaluate the cost-effectiveness of using Prosper software in gas lift system optimization

Keywords: gas lift, prosper software, injection rate, operating costs, oil-producing wells

Procedia PDF Downloads 50

Authors: Faidon Kyriakou, William Dempster, David Nash

Abstract:

Abdominal Aortic Aneurysm (AAA) is a major life-threatening pathology for which modern approaches reduce the need for open surgery through the use of stenting. The success of stenting though is sometimes jeopardized by the final position of the stent graft inside the human artery which may result in migration, endoleaks or blood flow occlusion. Herein, a finite element (FE) model of the commercial medical device AnacondaTM (Vascutek, Terumo) has been developed and validated in order to create a numerical tool able to provide useful clinical insight before the surgical procedure takes place. The AnacondaTM device consists of a series of NiTi rings sewn onto woven polyester fabric, a structure that despite its column stiffness is flexible enough to be used in very tortuous geometries. For the purposes of this study, a FE model of the device was built in Abaqus® (version 6.13-2) with the combination of beam, shell and surface elements; the choice of these building blocks was made to keep the computational cost to a minimum. The validation of the numerical model was performed by comparing the deployed position of a full stent graft device inside a constructed AAA with a duplicate set-up in Abaqus®. Specifically, an AAA geometry was built in CAD software and included regions of both high and low tortuosity. Subsequently, the CAD model was 3D printed into a transparent aneurysm, and a stent was deployed in the lab following the steps of the clinical procedure. Images on the frontal and sagittal planes of the experiment allowed the comparison with the results of the numerical model. By overlapping the experimental and computational images, the mean and maximum distances between the rings of the two models were measured in the longitudinal, and the transverse direction and, a 5mm upper bound was set as a limit commonly used by clinicians when working with simulations. The two models showed very good agreement of their spatial positioning, especially in the less tortuous regions. As a result, and despite the inherent uncertainties of a surgical procedure, the FE model allows confidence that the final position of the stent graft, when deployed in vivo, can also be predicted with significant accuracy. Moreover, the numerical model run in just a few hours, an encouraging result for applications in the clinical routine. In conclusion, the efficient modelling of a complicated structure which combines thin scaffolding and fabric has been demonstrated to be feasible. Furthermore, the prediction capabilities of the location of each stent ring, as well as the global shape of the graft, has been shown. This can allow surgeons to better plan their procedures and medical device manufacturers to optimize their designs. The current model can further be used as a starting point for patient specific CFD analysis.

Keywords: AAA, efficiency, finite element analysis, stent deployment

Procedia PDF Downloads 168

Authors: I. Stathopoulos, V. Syrgiamiotis, E. Karavasilis, A. Ploussi, I. Nikas, C. Hatzigiorgi, K. Platoni, E. P. Efstathopoulos

Abstract:

Introduction: Brain and central nervous system (CNS) tumors form the second most common group of cancer in children, accounting for 30% of all childhood cancers. MRI is the key imaging technique used for the visualization and management of pediatric brain tumors. Initial characterization of tumors from MRI scans is usually performed via a radiologist’s visual assessment. However, different brain tumor types do not always demonstrate clear differences in visual appearance. Using only conventional MRI to provide a definite diagnosis could potentially lead to inaccurate results, and so histopathological examination of biopsy samples is currently considered to be the gold standard for obtaining definite diagnoses. Machine learning is defined as the study of computational algorithms that can use, complex or not, mathematical relationships and patterns from empirical and scientific data to make reliable decisions. Concerning the above, machine learning techniques could provide effective and accurate ways to automate and speed up the analysis and diagnosis for medical images. Machine learning applications in radiology are or could potentially be useful in practice for medical image segmentation and registration, computer-aided detection and diagnosis systems for CT, MR or radiography images and functional MR (fMRI) images for brain activity analysis and neurological disease diagnosis. Purpose: The objective of this study is to provide an automated tool, which may assist in the imaging evaluation and classification of brain neoplasms in pediatric patients by determining the glioma type, grade and differentiating between different brain tissue types. Moreover, a future purpose is to present an alternative way of quick and accurate diagnosis in order to save time and resources in the daily medical workflow. Materials and Methods: A cohort, of 80 pediatric patients with a diagnosis of posterior fossa tumor, was used: 20 ependymomas, 20 astrocytomas, 20 medulloblastomas and 20 healthy children. The MR sequences used, for every single patient, were the following: axial T1-weighted (T1), axial T2-weighted (T2), FluidAttenuated Inversion Recovery (FLAIR), axial diffusion weighted images (DWI), axial contrast-enhanced T1-weighted (T1ce). From every sequence only a principal slice was used that manually traced by two expert radiologists. Image acquisition was carried out on a GE HDxt 1.5-T scanner. The images were preprocessed following a number of steps including noise reduction, bias-field correction, thresholding, coregistration of all sequences (T1, T2, T1ce, FLAIR, DWI), skull stripping, and histogram matching. A large number of features for investigation were chosen, which included age, tumor shape characteristics, image intensity characteristics and texture features. After selecting the features for achieving the highest accuracy using the least number of variables, four machine learning classification algorithms were used: k-Nearest Neighbour, Support-Vector Machines, C4.5 Decision Tree and Convolutional Neural Network. The machine learning schemes and the image analysis are implemented in the WEKA platform and MatLab platform respectively. Results-Conclusions: The results and the accuracy of images classification for each type of glioma by the four different algorithms are still on process.

Keywords: image classification, machine learning algorithms, pediatric MRI, pediatric oncology

Procedia PDF Downloads 125

Authors: Ratun Rahman, Rafid Islam, Akin Ahmed, Kamrul Hasan, Hasan Mahmud

Abstract:

Malware is becoming more prevalent, and several threat categories have risen dramatically in recent years. This paper provides a bird's-eye view of the world of malware analysis. The efficiency of five different machine learning methods (Naive Bayes, K-Nearest Neighbor, Decision Tree, Random Forest, and TensorFlow Decision Forest) combined with features picked from the retrieval of Android permissions to categorize applications as harmful or benign is investigated in this study. The test set consists of 1,168 samples (among these android applications, 602 are malware and 566 are benign applications), each consisting of 948 features (permissions). Using the permission-based dataset, the machine learning algorithms then produce accuracy rates above 80%, except the Naive Bayes Algorithm with 65% accuracy. Of the considered algorithms TensorFlow Decision Forest performed the best with an accuracy of 90%.

Keywords: android malware detection, machine learning, malware, malware analysis

Procedia PDF Downloads 127

Authors: Jeremy Jenrette, Z. Y. C. Liu, Pranav Chimote, Edward Fox, Trevor Hastie, Francesco Ferretti

Abstract:

Suitable shark conservation depends on well-informed population assessments. Direct methods such as scientific surveys and fisheries monitoring are adequate for defining population statuses, but species-specific indices of abundance and distribution coming from these sources are rare for most shark species. We can rapidly fill these information gaps by boosting media-based remote monitoring efforts with machine learning and automation. We created a database of shark images by sourcing 24,546 images covering 219 species of sharks from the web application spark pulse and the social network Instagram. We used object detection to extract shark features and inflate this database to 53,345 images. We packaged object-detection and image classification models into a Shark Detector bundle. We developed the Shark Detector to recognize and classify sharks from videos and images using transfer learning and convolutional neural networks (CNNs). We applied these models to common data-generation approaches of sharks: boosting training datasets, processing baited remote camera footage and online videos, and data-mining Instagram. We examined the accuracy of each model and tested genus and species prediction correctness as a result of training data quantity. The Shark Detector located sharks in baited remote footage and YouTube videos with an average accuracy of 89\%, and classified located subjects to the species level with 69\% accuracy (n =\ eight species). The Shark Detector sorted heterogeneous datasets of images sourced from Instagram with 91\% accuracy and classified species with 70\% accuracy (n =\ 17 species). Data-mining Instagram can inflate training datasets and increase the Shark Detector’s accuracy as well as facilitate archiving of historical and novel shark observations. Base accuracy of genus prediction was 68\% across 25 genera. The average base accuracy of species prediction within each genus class was 85\%. The Shark Detector can classify 45 species. All data-generation methods were processed without manual interaction. As media-based remote monitoring strives to dominate methods for observing sharks in nature, we developed an open-source Shark Detector to facilitate common identification applications. Prediction accuracy of the software pipeline increases as more images are added to the training dataset. We provide public access to the software on our GitHub page.

Keywords: classification, data mining, Instagram, remote monitoring, sharks

Procedia PDF Downloads 91

Authors: Regina Chua

Abstract:

To reduce the costs of re-fielding a large survey, a Random Forest classifier was applied to measure the accuracy of classifying individuals into their assigned segments with the fewest possible questions. Given a long survey, one needed to determine the most predictive ten or fewer questions that would accurately assign new individuals to custom segments. Furthermore, the solution needed to be quick in its classification and usable in non-Python environments. In this paper, a supervised Random Forest classifier was modeled on a dataset with 7,000 individuals, 60 questions, and 254 features. The Random Forest consisted of an iterative collection of individual decision trees that result in a predicted segment with robust precision and recall scores compared to a single tree. A random 70-30 stratified sampling for training the algorithm was used, and accuracy trade-offs at different depths for each segment were identified. Ultimately, the Random Forest classifier performed at 87% accuracy at a depth of 10 with 20 instead of 254 features and 10 instead of 60 questions. With an acceptable accuracy in prioritizing feature selection, new tools were developed for non-Python environments: a worksheet with a formulaic version of the algorithm and an embedded function to predict the segment of an individual in real-time. Random Forest was determined to be an optimal classification model by its feature selection, performance, processing speed, and flexible application in other environments.

Keywords: machine learning, supervised learning, data science, random forest, classification, prediction, predictive modeling

Procedia PDF Downloads 72

Authors: Mohamed Hafid, Marcel Lacroix

Abstract:

This study presents an inverse analysis for predicting the thermal conductivities and the heat flux of a high-temperature metallurgical reactor simultaneously. Once these thermal parameters are predicted, the time-varying thickness of the protective phase-change bank that covers the inside surface of the brick walls of a metallurgical reactor can be calculated. The enthalpy method is used to solve the melting/solidification process of the protective bank. The inverse model rests on the Levenberg-Marquardt Method (LMM) combined with the Broyden method (BM). A statistical analysis for the thermal parameter estimation is carried out. The effect of the position of the temperature sensors, total number of measurements and measurement noise on the accuracy of inverse predictions is investigated. Recommendations are made concerning the location of temperature sensors.

Keywords: inverse heat transfer, phase change, metallurgical reactor, Levenberg–Marquardt method, Broyden method, bank thickness

Procedia PDF Downloads 309

Authors: Yan Cheng, Yijun Shao, James Rudolph, Charlene R. Weir, Beth Sahlmann, Qing Zeng-Treitler

Abstract:

Supervised predictive models require labeled data for training purposes. Complete and accurate labeled data, i.e., a ‘gold standard’, is not always available, and imperfectly labeled data may need to serve as an alternative. An important question is if the accuracy of the labeled data creates a performance ceiling for the trained model. In this study, we trained several models to recognize the presence of delirium in clinical documents using data with annotations that are not completely accurate (i.e., weakly-supervised learning). In the external evaluation, the support vector machine model with a linear kernel performed best, achieving an area under the curve of 89.3% and accuracy of 88%, surpassing the 80% accuracy of the training sample. We then generated a set of simulated data and carried out a series of experiments which demonstrated that models trained on imperfect data can (but do not always) outperform the accuracy of the training data, e.g., the area under the curve for some models is higher than 80% when trained on the data with an error rate of 40%. Our experiments also showed that the error resistance of linear modeling is associated with larger sample size, error type, and linearity of the data (all p-values < 0.001). In conclusion, this study sheds light on the usefulness of imperfect data in clinical research via weakly-supervised learning.

Keywords: weakly-supervised learning, support vector machine, prediction, delirium, simulation

Procedia PDF Downloads 169

Authors: Ali Mohammed Saleh Al-Hamzi

Abstract:

This study aims at finding out the most difficult position in pronouncing the bilabial plosive sounds at the fourth level of English foreign language students of the Faculty of Education, Mahweet, Sana’a University in Yemen. The subject of this study were 50 participants from English foreign language students aged 22-25. In describing sounds according to their place of articulation, sounds are classified as bilabial, labiodental, dental, alveolar, post-alveolar, palato-alveolar retroflex, palatal, velar, uvular, and glottal. In much the same way, sounds can be described in their manner of articulation as plosives, nasals, affricates, flaps, taps, rolls, fricatives, laterals, frictionless continuants, and semi-vowels. For English foreign language students in Yemen, there are some articulators that are difficult to pronounce. In this study, the researcher focuses on difficulties in pronouncing the English bilabial plosive sounds among English foreign language students. It can be in the initial, medial, and final positions. The problem discussed in this study was: which position is the most difficult in pronouncing the English bilabial plosive sounds? To solve the problem, a descriptive qualitative method was conducted in this study. The data were collected from each English bilabial plosive sounds produced by students. Finally, the researcher reached that the most difficult position in pronouncing the English bilabial plosive sounds is when English bilabial plosive /p/ and /b/ occur word-finally, where both are voiceless.

Keywords: difficulty, EFL students’ pronunciation, bilabial sounds, plosive sounds

Procedia PDF Downloads 124

Authors: Carine Kawakami

Abstract:

In French, as well as in English, there are two types of psychological predicate constructions depending on where the experiencer argument is realized; the first type is in the subject position (e.g. Je regrette d’être venu ici. ‘I regret coming here'), hereinafter called ES construction, and the second type is in the object position (e.g. Cette nouvelle m’a surpris. ‘This new surprised me.'), referred as EO construction. In the previous studies about psychological predicates, the syntactic position of the experiencer argument has been just a matter of its connection with the syntactic or semantic structure of the predicate. So that few attentions have been paid to how two types of realization of experiencer are related to the conceptualization of psychological event and to the function of the sentence describing the psychological event, in the sense of speech act theory. In this research, focusing on the French phenomena limited to the first personal pronoun and the present tense, the ES constructions and the EO constructions will be analyzed from cognitive and functional approach. It will be revealed that, due to the possibility to be used in soliloquy and the high co-occurrence with ça (‘it’), the EO constructions may have expressive function to betray what speaker feels in hic et nunc, like interjection. And in the expressive case, the experiencer is construed as a locus where a feeling appears spontaneously and is construed subjectively (e.g. Ah, ça m’énerve! ‘Oh, it irritates me!'). On the other hand, the ES constructions describe speaker’s mental state in an assertive manner rather than the expressive and spontaneously way. In other words, they describe what speaker feels to the interlocutor (e.g. Je suis énervé. ‘I am irritated.'). As a consequence, when the experiencer argument is realized in the subject position, it is construed objectively and have a participant feature in the sense of cognitive grammar. Finally, it will be concluded that the choice of construction type, at least in French, is correlated to the conceptualization of the psychological event and the discourse feature of its expression.

Keywords: french psychological verb, conceptualization, expressive function, assertive function, experiencer realization

Procedia PDF Downloads 103

Authors: Hooriya Sadr Dadras, Shiva Seyed Erfani

Abstract:

Speaking skills merit meticulous attention both on the side of the learners and the teachers. In particular, accuracy is a critical component to guarantee the messages to be conveyed through conversation because a wrongful change may adversely alter the content and purpose of the talk. Different types of tasks have served teachers to meet numerous educational objectives. Besides, negotiation of meaning and the use of different strategies have been areas of concern in socio-cultural theories of SLA. Negotiation of meaning is among the conversational processes which have a crucial role in facilitating the understanding and expression of meaning in a given second language. Conversational strategies are used during interaction when there is a breakdown in communication that leads to the interlocutor attempting to remedy the gap through talk. Therefore, this study was an attempt to investigate if there was any significant difference between the effect of reasoning gap tasks and information gap tasks on the frequency of conversational strategies used in negotiation of meaning in classrooms on one hand, and on the accuracy in speaking of Iranian intermediate EFL learners on the other. After a pilot study to check the practicality of the treatments, at the outset of the main study, the Preliminary English Test was administered to ensure the homogeneity of 87 out of 107 participants who attended the intact classes of a 15 session term in one control and two experimental groups. Also, speaking sections of PET were used as pretest and posttest to examine their speaking accuracy. The tests were recorded and transcribed to estimate the percentage of the number of the clauses with no grammatical errors in the total produced clauses to measure the speaking accuracy. In all groups, the grammatical points of accuracy were instructed and the use of conversational strategies was practiced. Then, different kinds of reasoning gap tasks (matchmaking, deciding on the course of action, and working out a time table) and information gap tasks (restoring an incomplete chart, spot the differences, arranging sentences into stories, and guessing game) were manipulated in experimental groups during treatment sessions, and the students were required to practice conversational strategies when doing speaking tasks. The conversations throughout the terms were recorded and transcribed to count the frequency of the conversational strategies used in all groups. The results of statistical analysis demonstrated that applying both the reasoning gap tasks and information gap tasks significantly affected the frequency of conversational strategies through negotiation. In the face of the improvements, the reasoning gap tasks had a more significant impact on encouraging the negotiation of meaning and increasing the number of conversational frequencies every session. The findings also indicated both task types could help learners significantly improve their speaking accuracy. Here, applying the reasoning gap tasks was more effective than the information gap tasks in improving the level of learners’ speaking accuracy.

Keywords: accuracy in speaking, conversational strategies, information gap tasks, reasoning gap tasks

Procedia PDF Downloads 286