Search results for: accuracy evaluation

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 96

Authors: Naruemon Phongaksorn

Abstract:

The biofuel consumption has increased significantly over the decade resulting in the increasing request on agricultural land for biofuel feedstocks. However, the biofuel feedstocks are already stressed of having low productivity owing to inappropriate agricultural practices without considering suitability of crop land. This research evaluates the land suitability using GIS-integrated Analytic Hierarchy Processing (AHP) of biofuel crops: cassava, at Chachoengsao province, in Thailand. AHP method that has been widely accepted for land use planning. The objective of this study is compared between AHP method and the most limiting group of land characteristics method (classical approach). The reliable results of the land evaluation were tested against the crop performance assessed by the field investigation in 2015. In addition to the socio-economic land suitability, the expected availability of raw materials for biofuel production to meet the local biofuel demand, are also estimated. The results showed that the AHP could classify and map the physical land suitability with 10% higher overall accuracy than the classical approach. The Chachoengsao province showed high and moderate socio-economic land suitability for cassava. Conditions in the Chachoengsao province were also favorable for cassava plantation, as the expected raw material needed to support ethanol production matched that of ethanol plant capacity of this province. The GIS integrated AHP for biofuel crops land suitability evaluation appears to be a practical way of sustainably meeting biofuel production demand.

Keywords: Analytic Hierarchy Processing (AHP), Cassava, Geographic Information Systems, Land suitability

Procedia PDF Downloads 166

Authors: Gulfam Haider, sana danish

Abstract:

Convolutional Neural Networks (CNNs) have emerged as powerful tools for image classification, and the choice of optimizers profoundly affects their performance. The study of optimizers and their adaptations remains a topic of significant importance in machine learning research. While numerous studies have explored and advocated for various optimizers, the efficacy of these optimization techniques is still subject to scrutiny. This work aims to address the challenges surrounding the effectiveness of optimizers by conducting a comprehensive analysis and evaluation. The primary focus of this investigation lies in examining the performance of different optimizers when employed in conjunction with the popular activation function, Rectified Linear Unit (ReLU). By incorporating ReLU, known for its favorable properties in prior research, the aim is to bolster the effectiveness of the optimizers under scrutiny. Specifically, we evaluate the adjustment of these optimizers with both the original Softmax activation function and the modified ReLU activation function, carefully assessing their impact on overall performance. To achieve this, a series of experiments are conducted using a well-established benchmark dataset for image classification tasks, namely the Canadian Institute for Advanced Research dataset (CIFAR-10). The selected optimizers for investigation encompass a range of prominent algorithms, including Adam, Root Mean Squared Propagation (RMSprop), Adaptive Learning Rate Method (Adadelta), Adaptive Gradient Algorithm (Adagrad), and Stochastic Gradient Descent (SGD). The performance analysis encompasses a comprehensive evaluation of the classification accuracy, convergence speed, and robustness of the CNN models trained with each optimizer. Through rigorous experimentation and meticulous assessment, we discern the strengths and weaknesses of the different optimization techniques, providing valuable insights into their suitability for image classification tasks. By conducting this in-depth study, we contribute to the existing body of knowledge surrounding optimizers in CNNs, shedding light on their performance characteristics for image classification. The findings gleaned from this research serve to guide researchers and practitioners in making informed decisions when selecting optimizers and activation functions, thus advancing the state-of-the-art in the field of image classification with convolutional neural networks.

Keywords: deep neural network, optimizers, RMsprop, ReLU, stochastic gradient descent

Procedia PDF Downloads 62

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 215

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 81

Authors: Reem AlKabbi, Hayat Ali, Mariam Yasser

Abstract:

Nowadays, eGovernment websites are becoming indispensable for public, business, personal efficiency or even improvement of livelihoods. Using these websites, citizens undertake number of tasks that would otherwise be difficult or impossible. However, many of these websites are not accessible to all people' types including People with Disabilities (PWDs). Through Web Accessibility Guidelines, Web developers can develop Web applications that are accessible to PWDs. This research is to investigate the Accessibility of eGovernment websites in Kingdom of Bahrain. The accessibility was measured using Web Content Accessibility Guidelines (WCAG) and section 508. For the evaluation purpose, some automatic tools were used. Samples of 43 eGovernment websites were selected. The accessibility of the websites was analyzed by using several automatic evaluation tools such as Total Validator and Functional Accessibility Evaluator (FAE). The evaluation process revealed several errors according to the accessibility guidelines. This research provides few recommendations for further improvement of accessibility features of eGovernment websites based on the highlighted issues and key findings reported in this research.

Keywords: website accessibility, W3C, PWD, e-government

Procedia PDF Downloads 412

Authors: Lina Feng

Abstract:

The study aimed at establishing quality evaluation indicators of an early education center for 0~3 years old, and defining the weight system of it. Expert questionnaire and Fuzzy Delphi method were applied. Firstly, in order to ensure the indicators in accordance with the practice of early education, 16 experts were invited as respondents to a preliminary Expert Questionnaire about Quality Evaluation Indicators of Early Education Center for 0~3 Years Old. The indicators were based on relevant studies on quality evaluation indicators of early education centers in China and abroad. Secondly, 20 scholars, kindergarten principals, and educational administrators were invited to form a fuzzy Delphi expert team. The experts’ opinions on the importance of indicators were calculated through triangle fuzzy numbers in order to select appropriate indicators and calculate indicator weights. This procedure resulted in the final Quality Evaluation Indicators of Early education Center for 0~3 Years Old. The Indicators contained three major levels, including 6 first-level indicators, 30 second-level indicators, and 147 third-level indicators. The 6 first-level indicators were health and safety; educational and cultivating activities; development of babies; conditions of the center; management of the center; and collaboration between family and the community. The indicators established by this study could provide suggestions for the high-quality environment for promoting the development of early year children.

Keywords: early education center for 0~3 years old, educational management, fuzzy delphi method, quality evaluation indicator

Procedia PDF Downloads 231

Authors: Chengfang Wang, Zichao Wu, Jianying Zhou

Abstract:

At present, much attention is paid to the development of new industrial parks in the era of inventory planning. Generally speaking, there are two types of development models: incremental development models and stock development models. The former relies on key projects to build a value innovation park, and the latter relies on the iterative update of the park to build a value innovation park. Take the Baiyun Western Digital Park as an example, considering the growth model of value units, determine the evaluation target. Based on a GIS platform, comprehensive land-use status, regulatory detailed planning, land use planning, blue-green ecological base, rail transit system, road network system, industrial park distribution, public service facilities, and other factors are used to carry out the land use within the planning multi-factor superimposed comprehensive evaluation, constructing a value unit evaluation system, and delineating value units based on implementation orientation and combining two different development models. The research hopes to provide a reference for the planning and construction of new domestic industrial parks.

Keywords: value units, GIS, multi-factor evaluation, implementation orientation

Procedia PDF Downloads 151

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 528

Authors: Soha A. Bahanshal, Vaibhav Verdhan, Bayong Kim

Abstract:

Graduation rates at six-year colleges are becoming a more essential indicator for incoming fresh students and for university rankings. Predicting student graduation is extremely beneficial to schools and has a huge potential for targeted intervention. It is important for educational institutions since it enables the development of strategic plans that will assist or improve students' performance in achieving their degrees on time (GOT). A first step and a helping hand in extracting useful information from these data and gaining insights into the prediction of students' progress and performance is offered by machine learning techniques. Data analysis and visualization techniques are applied to understand and interpret the data. The data used for the analysis contains students who have graduated in 6 years in the academic year 2017-2018 for science majors. This analysis can be used to predict the graduation of students in the next academic year. Different Predictive modelings such as logistic regression, decision trees, support vector machines, Random Forest, Naïve Bayes, and KNeighborsClassifier are applied to predict whether a student will graduate. These classifiers were evaluated with k folds of 5. The performance of these classifiers was compared based on accuracy measurement. The results indicated that Ensemble Classifier achieves better accuracy, about 91.12%. This GOT prediction model would hopefully be useful to university administration and academics in developing measures for assisting and boosting students' academic performance and ensuring they graduate on time.

Keywords: prediction, decision trees, machine learning, support vector machine, ensemble model, student graduation, GOT graduate on time

Procedia PDF Downloads 48

Authors: Tom D. Gedeon, Ujala Rampaul

Abstract:

The evaluation of electronic consumer goods are most often done from the perspective of analysing the latest models, comparing their advantages and disadvantages with respect to price. This style of evaluation is often performed by one or a few product experts on a wide range of features that may not be applicable to each user. We instead used a scenario-based approach to evaluate a number of e-readers. The setting is similar to a user who is interested in a new product or technology and has allocated a limited budget. We evaluate the quality and usability of e-readers available within that budget range. This is based on the assumption of a rational market which prices older second hand devices the same as functionally equivalent new devices. We describe our evaluation and comparison of four branded eReaders, as the initial stage of a larger project. The scenario has a range of tasks approximating a busy person who does not bother to read the manual. We found that navigation within books to be the most significant differentiator between the eReaders in our scenario based evaluation process.

Keywords: eReader, scenario based, price comparison, Kindle, Kobo, Nook, Sony, technology adoption

Procedia PDF Downloads 488

Authors: Jennifer Leach, Umashanger Thayasivam

Abstract:

The use of technology has benefited society in more ways than one ever thought possible. Unfortunately, though, as society’s knowledge of technology has advanced, so has its knowledge of ways to use technology to manipulate people. This has led to a simultaneous advancement in the world of fraud. Machine learning techniques can offer a possible solution to help decrease this advancement. This research explores how the use of various machine learning techniques can aid in detecting fraudulent activity across two different types of fraudulent data, and the accuracy, precision, recall, and F1 were recorded for each method. Each machine learning model was also tested across five different training and testing splits in order to discover which testing split and technique would lead to the most optimal results.

Keywords: data science, fraud detection, machine learning, supervised learning

Procedia PDF Downloads 157

Authors: Somayyeh Karimiyan

Abstract:

To evaluate the seismic vulnerability of vital offshore structures with the highest possible precision, Nonlinear Time History Analyses (NLTHA), is the most reliable method. However, since it is very time-consuming, a quick procedure is greatly desired. This paper presents a quick method by combining the Push Over Analysis (POA) and the NLTHA. The POA is preformed first to recognize the more critical members, and then the NLTHA is performed to evaluate more precisely the critical members’ vulnerability. The proposed method has been applied to jacket type structure. Results show that combining POA and NLTHA is a reliable seismic evaluation method, and also that none of the earthquake characteristics alone, can be a dominant factor in vulnerability evaluation.

Keywords: jacket structure, seismic evaluation, push-over and nonlinear time history analyses, critical members

Procedia PDF Downloads 260

Authors: Hamzat Shittu Atunnise

Abstract:

This study on Assessment of the Implementation of Recommended Teaching and Evaluation Methods of the Nigeria Certificate in Education (NCE) Arabic Language Curriculum in Colleges of Education in North Western Nigeria was conducted with four objectives, four research questions and four null hypotheses. Descriptive survey design was used and the multistage sampling procedure adopted. Frequency count and percentage were used to answer research questions and chi-square was used to test all the null hypotheses at an Alpha 0.05 level of significance. Two hundred and ninety one subjects were drawn as sample. Questionnaires were used for data collection. The Context, Input, Process and Product (CIPP) model of evaluation was employed. The study findings indicated that: there were no significant difference in the perceptions of lecturers and students from Federal and State Colleges of Education on the following: extent of which lecturers employ appropriate methods in teaching the language and extent of which recommended evaluation methods are utilized for the implementation of Arabic Curriculum. Based on these findings, it was recommended among other things that: lecturers should adopt teaching methodologies that promote interactive learning; Governments should ensure that information and communication technology facilities are made available and usable in all Colleges of Education; Lecturers should vary their evaluation methods because other methods of evaluation can meet and surpass the level of learning and understanding which essay type questions are believed to create and that language labs should be used in teaching Arabic in Colleges of Education because comprehensive language learning is possible through both classroom and language lab teaching.

Keywords: assessment, arabic language, curriculum, methods of teaching, evaluation methods, NCE

Procedia PDF Downloads 24

Authors: Zahra Karimi

Abstract:

The purpose of this paper is to investigate the role and importance of accounting for the implementation of the VAT system in the country. For this purpose, after the evaluation of specifications and important advantages of the VAT and the experience of other countries, important role of accounting in the precise determination of taxes, strategies to prevent escape of tax and realization of tax revenues of government, necessary control to increase the efficiency and accuracy of the calculations discussed. High-dependence of government to borrowing from the banking system and inflation tax and a low general ratio of tax revenues to GDP, indicating the inadequacy of the country's tax system. It can be said that being of a proper accounting system consider as a prerequisite for successful implementation of VAT in the country. So it's crucial for accountants with responsibility announce its full fitness to meet the requirements. For successful implementation of VAT as such a multi-stage sales tax and the tax on the price.

Keywords: accounting, tax reform in Iran, Value Added Tax (VAT), economic

Procedia PDF Downloads 357

Authors: Adeniran K. Ademuwagun, Alastair Allen

Abstract:

The relationship dependence between RSS and distance in an enclosed environment is an important consideration because it is a factor that can influence the reliability of any localization algorithm founded on RSS. Several algorithms effectively reduce the variance of RSS to improve localization or accuracy performance. Our proposed algorithm essentially avoids this pitfall and consequently, its high adaptability in the face of erratic radio signal. Using 3 anchors in close proximity of each other, we are able to establish that RSS can be used as reliable indicator for localization with an acceptable degree of accuracy. Inherent in this concept, is the ability for each prospective anchor to validate (guarantee) the position or the proximity of the other 2 anchors involved in the localization and vice versa. This procedure ensures that the uncertainties of radio signals due to multipath effects in enclosed environments are minimized. A major driver of this idea is the implicit topological relationship among sensors due to raw radio signal strength. The algorithm is an area based algorithm; however, it does not trade accuracy for precision (i.e the size of the returned area).

Keywords: anchor nodes, centroid algorithm, communication graph, radio signal strength

Procedia PDF Downloads 473

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 126

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 480

Authors: Chen Bo, Wen Zengping

Abstract:

Based on the results of previous studies, we focus on the research of real ground motion selection and scaling method for structural performance-based seismic evaluation using nonlinear dynamic analysis. The input of earthquake ground motion should be determined appropriately to make them compatible with the site-specific hazard level considered. Thus, an optimized selection and scaling method are established including the use of not only Monte Carlo simulation method to create the stochastic simulation spectrum considering the multivariate lognormal distribution of target spectrum, but also a spectral shape parameter. Its applications in structural fragility analysis are demonstrated through case studies. Compared to the previous scheme with no consideration of the uncertainty of target spectrum, the method shown here can make sure that the selected records are in good agreement with the median value, standard deviation and spectral correction of the target spectrum, and greatly reveal the uncertainty feature of site-specific hazard level. Meanwhile, it can help improve computational efficiency and matching accuracy. Given the important infection of target spectrum’s uncertainty on structural seismic fragility analysis, this work can provide the reasonable and reliable basis for structural seismic evaluation under scenario earthquake environment.

Keywords: ground motion selection, scaling method, seismic fragility analysis, spectral shape

Procedia PDF Downloads 265

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 22

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 264

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 186

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 44

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 122

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 89

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 68

Authors: M. Zielina, W. Dabrowski, E. Radziszewska-Zielina

Abstract:

Several different cements have been tested to evaluate their potential to leach calcium, chromium and aluminum ions in soft water environment. The research allows comparing some different cements in order to the potential risk of water contamination. This can be done only in the same environment. To reach the results in reasonable short time intervals and to make heavy metals measurements with high accuracy, demineralized water was used. In this case the conditions of experiments are far away from the water supply practice, but short time experiments and measurably high concentrations of elements in the water solution are an important advantage. Moreover leaching mechanisms can be recognized, our experiments reported here refer to this kind of cements evaluation.

Keywords: concrete corrosion, hydrogen sulfide, odors, reinforced concrete sewers, sewerage

Procedia PDF Downloads 181

Authors: F.Sadoughi, A. Sarsarshahi, L, Eerfannia, S.M.A. Khatami

Abstract:

Hospital information systems with lots of ability would lead to health care quality improvement. Evaluation of this system has done according different method and criteria. The main goal of present study is to prioritize the most important factors which are influence these systems evaluation. At the first step, according relevant literature, three main factor and 29 subfactors extracted. Then, study framework was designed. Based on analytical hierarchical process (AHP), 28 paired comparisons with Saaty range, in a questionnaire format obtained. Questionnaires were filled by 10 experts in health information management and medical informatics field. Human factors with weight of 0.55 were ranked as the most important. Organization (0.25) and technology (0.14) were in next place. It seems MADM methods such as AHP have enough potential to use in health research and provide positive opportunities for health domain decision makers.

Keywords: Analytical hierarchy process, Multiple criteria decision-making (MCDM), Hospital information system, Evaluation factors

Procedia PDF Downloads 421

Authors: Vaclav Sadilek, Miroslav Vorechovsky

Abstract:

The paper deals with the classical fiber bundle model of equal load sharing, sometimes referred to as the Daniels' bundle or the democratic bundle. Daniels formulated a multidimensional integral and also a recursive formula for evaluation of the strength cumulative distribution function. This paper describes three algorithms for evaluation of the recursive formula and also their implementations with source codes in high-level programming language Python. A comparison of the algorithms are provided with respect to execution time. Analysis of orders of magnitudes of addends in the recursion is also provided.

Keywords: equal load sharing, mpmath, python, strength of Daniels' bundle

Procedia PDF Downloads 375

Authors: Kaiping Xu, Aiju You, Lei Hua

Abstract:

In view of the ecological environmental problems and protection needs of mountainous rivers in Zhejiang province, a suitable ecological water demand evaluation system was established based on investigation and monitoring. Taking the Kaihua river as an example, the research on ecological water demand and the current situation evaluation were carried out. The main types of ecological water demand in Majin River are basic ecological flow and lake wetland outside the river, and instream flow and water demands for water quality in Zhongcun river. In the wet season, each ecological water demand is 18.05m3/s and 2.56m3 / s, and in the dry season is 3.00m3/s and 0.61m3/s. Three indexes of flow, duration and occurrence time are used to evaluate the ecological water demand. The degree of ecological water demand in the past three years is low level of satisfaction. Meanwhile, the existing problems are analyzed, and put forward reasonable and operable safeguards and suggestions.

Keywords: Zhejiang province, mountainous river, ecological water demand, Kaihua river, evaluation

Procedia PDF Downloads 194