Search results for: deep neural image models

Authors: Zekang Lan, Yan Xu, Yingkun Huang, Dian Huang, Shengzhong Feng

Abstract:

Jobs on high-performance computing (HPC) clusters can suffer significant performance degradation due to inter-job network interference. Topology-aware job allocation problem (TJAP) is such a problem that decides how to dedicate nodes to specific applications to mitigate inter-job network interference. In this paper, we study the window-based TJAP on a fat-tree network aiming at minimizing the cost of communication hop, a defined inter-job interference metric. The window-based approach for scheduling repeats periodically, taking the jobs in the queue and solving an assignment problem that maps jobs to the available nodes. Two special allocation strategies are considered, i.e., static continuity assignment strategy (SCAS) and dynamic continuity assignment strategy (DCAS). For the SCAS, a 0-1 integer programming is developed. For the DCAS, an approach called neural simulated algorithm (NSA), which is an extension to simulated algorithm (SA) that learns a repair operator and employs them in a guided heuristic search, is proposed. The efficacy of NSA is demonstrated with a computational study against SA and SCIP. The results of numerical experiments indicate that both the model and algorithm proposed in this paper are effective.

Keywords: high-performance computing, job allocation, neural simulated annealing, topology-aware

Procedia PDF Downloads 90

Authors: Pooja Rani, G. S. Mahapatra, S. K. Pandey

Abstract:

In this paper, we propose a novel approach of Neural Network and Particle Swarm Optimization methods for software reliability prediction. We first explain how to apply compound function in neural network so that we can derive a Flexible Logistic (S-shaped) Growth Curve (FLGC) model. This model mathematically represents software failure as a random process and can be used to evaluate software development status during testing. To avoid trapping in local minima, we have applied Particle Swarm Optimization method to train proposed model using failure test data sets. We drive our proposed model using computational based intelligence modeling. Thus, proposed model becomes Neuro-Particle Swarm Optimization (NPSO) model. We do test result with different inertia weight to update particle and update velocity. We obtain result based on best inertia weight compare along with Personal based oriented PSO (pPSO) help to choose local best in network neighborhood. The applicability of proposed model is demonstrated through real time test data failure set. The results obtained from experiments show that the proposed model has a fairly accurate prediction capability in software reliability.

Keywords: software reliability, flexible logistic growth curve model, software cumulative failure prediction, neural network, particle swarm optimization

Procedia PDF Downloads 333

Authors: Touila Ahmed, Elie Louis, Hamza Gharbi

Abstract:

State of the art question answering models have recently shown impressive performance especially in a zero-shot setting. This approach is particularly useful when confronted with a highly diverse domain such as the legal field, in which it is increasingly difficult to have a dataset covering every notion and concept. In this work, we propose a flexible generative question answering approach to contract analysis as well as a weakly supervised procedure to leverage unannotated data and boost our models’ performance in general, and their zero-shot performance in particular.

Keywords: question answering, contract analysis, zero-shot, natural language processing, generative models, self-supervision

Procedia PDF Downloads 165

Authors: Wendy Flory, Kazi Czarnecki, Matthijs Mercy, Mark Joswiak, Mary Beth Seasholtz

Abstract:

Polyurethane Materials are present in a wide range of industrial segments such as Furniture, Building and Construction, Composites, Automotive, Electronics, and more. Dow is one of the leaders for the manufacture of the two main raw materials, Isocyanates and Polyols used to produce polyurethane products. Dow is also a key player for the manufacture of Polyurethane Systems/Formulations designed for targeted applications. In 1990, the first analytical chemometric models were developed and deployed for use in the Dow QC labs of the polyols business for the quantification of OH, water, cloud point, and viscosity. Over the years many models have been added; there are now over 140 models for quantification and hundreds for product identification, too many to be reasonable for support. There are 29 global models alone for the quantification of OH across > 70 products at many sites. An attempt was made to consolidate these into a single model. While the consolidated model proved good statistics across the entire range of OH, several products had a bias by ASTM E1655 with individual product validation. This project summary will show the strategy for global model updates for OH, to reduce the number of models for quantification from over 140 to 5 or less using chemometric methods. In order to gain an understanding of the best product groupings, we identify clusters by reducing spectra to a few dimensions via Principal Component Analysis (PCA) and Uniform Manifold Approximation and Projection (UMAP). Results from these cluster analyses and a separate validation set allowed dow to reduce the number of models for predicting OH from 29 to 3 without loss of accuracy.

Keywords: hydroxyl, global model, model maintenance, near infrared, polyol

Procedia PDF Downloads 120

Authors: Anuruddha Jagoda, Samiddhi Samarakoon, Anil Jasinghe

Abstract:

In an emergency department ‘where every second count for patient’s management’ timely availability of X- rays play a vital role in early diagnosis and management of patients. Trauma care centers rely heavily on timely radiologic imaging for patient care and radiology plays a crucial role in the emergency department (ED) operations. A research study was carried out to assess timeliness of availability of X-rays and total turnaround time at the Accident Service of National Hospital of Sri Lanka which is the premier trauma center in the country. Digital Radiology system was implemented as an intervention to improve the timeliness of availability of X-rays. Post-implementation assessment was carried out to assess the effectiveness of the intervention. Reduction in all three aspects of waiting times namely waiting for initial examination by doctors, waiting until X –ray is performed and waiting for image availability was observed after implementation of the intervention. However, the most significant improvement was seen in waiting time for image availability and reduction in time for image availability had indirect impact on reducing waiting time for initial examination by doctors and waiting until X –ray is performed. The most significant reduction in time for image availability was observed when performing 4-5 X rays with DR system. The least improvement in timeliness was seen in patients who are categorized as critical.

Keywords: emergency department, digital radilogy, timeliness, trauma care

Procedia PDF Downloads 250

Authors: S. Mohamed, D. Gonzalez, C. Sayada, P. Halfon

Abstract:

Drug resistance mutations are routinely detected using standard Sanger sequencing, which does not detect minor variants with a frequency below 20%. The impact of detecting minor variants generated by ultra-deep sequencing (UDS) on HIV drug-resistance (DR) interpretations has not yet been studied. Fifty HIV-1 patients who experienced virological failure were included in this retrospective study. The HIV-1 UDS protocol allowed the detection and quantification of HIV-1 protease and reverse transcriptase variants related to genotypes A, B, C, E, F, and G. DeepChek®-HIV simplified DR interpretation software was used to compare Sanger sequencing and UDS. The total time required for the UDS protocol was found to be approximately three times longer than Sanger sequencing with equivalent reagent costs. UDS detected all of the mutations found by population sequencing and identified additional resistance variants in all patients. An analysis of DR revealed a total of 643 and 224 clinically relevant mutations by UDS and Sanger sequencing, respectively. Three resistance mutations with > 20% prevalence were detected solely by UDS: A98S (23%), E138A (21%) and V179I (25%). A significant difference in the DR interpretations for 19 antiretroviral drugs was observed between the UDS and Sanger sequencing methods. Y181C and T215Y were the most frequent mutations associated with interpretation differences. A combination of UDS and DeepChek® software for the interpretation of DR results would help clinicians provide suitable treatments. A cut-off of 1% allowed a better characterisation of the viral population by identifying additional resistance mutations and improving the DR interpretation.

Keywords: HIV-1, ultra-deep sequencing, Sanger sequencing, drug resistance

Procedia PDF Downloads 318

Authors: Haya Salah, Srinivas Sharan

Abstract:

Healthcare facilities use appointment systems to schedule their appointments and to manage access to their medical services. With the growing demand for outpatient care, it is now imperative to manage physician's time effectively. However, high variation in consultation duration affects the clinical scheduler's ability to estimate the appointment duration and allocate provider time appropriately. Underestimating consultation times can lead to physician's burnout, misdiagnosis, and patient dissatisfaction. On the other hand, appointment durations that are longer than required lead to doctor idle time and fewer patient visits. Therefore, a good estimation of consultation duration has the potential to improve timely access to care, resource utilization, quality of care, and patient satisfaction. Although the literature on factors influencing consultation length abound, little work has done to predict it using based data-driven approaches. Therefore, this study aims to predict consultation duration using supervised machine learning algorithms (ML), which predicts an outcome variable (e.g., consultation) based on potential features that influence the outcome. In particular, ML algorithms learn from a historical dataset without explicitly being programmed and uncover the relationship between the features and outcome variable. A subset of the data used in this study has been obtained from the electronic medical records (EMR) of four different outpatient clinics located in central Pennsylvania, USA. Also, publicly available information on doctor's characteristics such as gender and experience has been extracted from online sources. This research develops three popular ML algorithms (deep learning, random forest, gradient boosting machine) to predict the treatment time required for a patient and conducts a comparative analysis of these algorithms with respect to predictive performance. The findings of this study indicate that ML algorithms have the potential to predict the provider service time with superior accuracy. While the current approach of experience-based appointment duration estimation adopted by the clinic resulted in a mean absolute percentage error of 25.8%, the Deep learning algorithm developed in this study yielded the best performance with a MAPE of 12.24%, followed by gradient boosting machine (13.26%) and random forests (14.71%). Besides, this research also identified the critical variables affecting consultation duration to be patient type (new vs. established), doctor's experience, zip code, appointment day, and doctor's specialty. Moreover, several practical insights are obtained based on the comparative analysis of the ML algorithms. The machine learning approach presented in this study can serve as a decision support tool and could be integrated into the appointment system for effectively managing patient scheduling.

Keywords: clinical decision support system, machine learning algorithms, patient scheduling, prediction models, provider service time

Procedia PDF Downloads 108

Authors: Radoslaw Domke

Abstract:

The social history of Poland in the years 1945-1990 has already been thoroughly researched based on the so-called Classical sources. Many types of archival and press sources, diaries, memoirs, and literature on the subject were analyzed. It turns out, however, that the fictional film material remains an unknown source. In the paper, the author intends to focus on the image of Polish society that emerges from the analysis of cinematography produced by the Polish People's Republic. The conclusions presented in the paper can be the basis for further research on the visual history of post-war societies.

Keywords: visual history, history of Poland, social history, cinematography

Procedia PDF Downloads 80

Authors: Ali Almadan, Anoop Krishnan, Ajita Rattani

Abstract:

Facial recognition is a widely adopted technology in surveillance, border control, healthcare, banking services, and lately, in mobile user authentication with Apple introducing “Face ID” moniker with iPhone X. A lot of research has been conducted in the area of face recognition on datasets captured by surveillance cameras, DSLR, and mobile devices. Recently, face recognition technology has also been deployed on body-worn cameras to keep officers safe, enabling situational awareness and providing evidence for trial. However, limited academic research has been conducted on this topic so far, without the availability of any publicly available datasets with a sufficient sample size. This paper aims to advance research in the area of face recognition using body-worn cameras. To this aim, the contribution of this work is two-fold: (1) collection of a dataset consisting of a total of 136,939 facial images of 102 subjects captured using body-worn cameras in in-door and daylight conditions and (2) evaluation of various deep-learning architectures for face identification on the collected dataset. Experimental results suggest a maximum True Positive Rate(TPR) of 99.86% at False Positive Rate(FPR) of 0.000 obtained by SphereFace based deep learning architecture in daylight condition. The collected dataset and the baseline algorithms will promote further research and development. A downloadable link of the dataset and the algorithms is available by contacting the authors.

Keywords: face recognition, body-worn cameras, deep learning, person identification

Procedia PDF Downloads 151

Authors: Eiji Nakamachi, Tsuyoshi Eguchi, Sayo Yamamoto, Yusuke Morita, H. Sakamoto

Abstract:

In this study, we aim to reveal the relationship between the meniscal tearing and the articular cartilage injury of knee joint by using the dynamic explicit finite element (FE) method. Meniscal injuries reduce its functional ability and consequently increase the load on the articular cartilage of knee joint. In order to prevent the induction of osteoarthritis (OA) caused by meniscal injuries, many medical treatment techniques, such as artificial meniscus replacement and meniscal regeneration, have been developed. However, it is reported that these treatments are not the comprehensive methods. In order to reveal the fundamental mechanism of OA induction, the mechanical characterization of meniscus under the condition of normal and injured states is carried out by using FE analyses. At first, a FE model of the human knee joint in the case of normal state – ‘intact’ - was constructed by using the magnetron resonance (MR) tomography images and the image construction code, Materialize Mimics. Next, two types of meniscal injury models with the radial tears of medial and lateral menisci were constructed. In FE analyses, the linear elastic constitutive law was adopted for the femur and tibia bones, the visco-hyperelastic constitutive law for the articular cartilage, and the visco-anisotropic hyperelastic constitutive law for the meniscus, respectively. Material properties of articular cartilage and meniscus were identified using the stress-strain curves obtained by our compressive and the tensile tests. The numerical results under the normal walking condition revealed how and where the maximum compressive stress occurred on the articular cartilage. The maximum compressive stress and its occurrence point were varied in the intact and two meniscal tear models. These compressive stress values can be used to establish the threshold value to cause the pathological change for the diagnosis. In this study, FE analyses of knee joint were carried out to reveal the influence of meniscal injuries on the cartilage injury. The following conclusions are obtained. 1. 3D FE model, which consists femur, tibia, articular cartilage and meniscus was constructed based on MR images of human knee joint. The image processing code, Materialize Mimics was used by using the tetrahedral FE elements. 2. Visco-anisotropic hyperelastic constitutive equation was formulated by adopting the generalized Kelvin model. The material properties of meniscus and articular cartilage were determined by curve fitting with experimental results. 3. Stresses on the articular cartilage and menisci were obtained in cases of the intact and two radial tears of medial and lateral menisci. Through comparison with the case of intact knee joint, two tear models show almost same stress value and higher value than the intact one. It was shown that both meniscal tears induce the stress localization in both medial and lateral regions. It is confirmed that our newly developed FE analysis code has a potential to be a new diagnostic system to evaluate the meniscal damage on the articular cartilage through the mechanical functional assessment.

Keywords: finite element analysis, hyperelastic constitutive law, knee joint injury, meniscal tear, stress concentration

Procedia PDF Downloads 229

Authors: Janusz Bobulski, Kamila Pasternak

Abstract:

Despite many years of effort and research, the problem of waste management is still current. So far, no fully effective waste management system has been developed. Many programs and projects improve statistics on the percentage of waste recycled every year. In these efforts, it is worth using modern Computer Vision techniques supported by artificial intelligence. In the article, we present a method of identifying plastic waste based on the asymmetry analysis of the histogram of the image containing the waste. The method is simple but effective (94%), which allows it to be implemented on devices with low computing power, in particular on microcomputers. Such de-vices will be used both at home and in waste sorting plants.

Keywords: waste management, environmental protection, image processing, computer vision

Procedia PDF Downloads 101

Authors: Saumya Srivastava, Rina Maiti

Abstract:

In order to achieve a better performance of vehicle detection in a complex environment, we present an efficient approach for a multi-vehicle detection system using an adaptive sliding window technique. For a given frame, image segmentation is carried out to establish the region of interest. Gradient computation followed by thresholding, denoising, and morphological operations is performed to extract the binary search image. Near-region field and far-region field are defined to generate hypotheses using the adaptive sliding window technique on the resultant binary search image. For each vehicle candidate, features are extracted using a histogram of oriented gradients, and a pre-trained support vector machine is applied for hypothesis verification. Later, the Kalman filter is used for tracking the vanishing point. The experimental results show that the method is robust and effective on various roads and driving scenarios. The algorithm was tested on highways and urban roads in India.

Keywords: gradient, vehicle detection, histograms of oriented gradients, support vector machine

Procedia PDF Downloads 107

Authors: Muhammad Naveed Tahir, Wang Yingkuan, Huang Wenjiang, Raheel Osman

Abstract:

Numerous models used in prediction and decision-making process but most of them are linear in natural environment, and linear models reach their limitations with non-linearity in data. Therefore accurate estimation is difficult. Artificial Neural Networks (ANN) found extensive acceptance to address the modeling of the complex real world for the non-linear environment. ANN’s have more general and flexible functional forms than traditional statistical methods can effectively deal with. The link between information technology and agriculture will become more firm in the near future. Monitoring crop biophysical properties non-destructively can provide a rapid and accurate understanding of its response to various environmental influences. Crop chlorophyll content is an important indicator of crop health and therefore the estimation of crop yield. In recent years, remote sensing has been accepted as a robust tool for site-specific management by detecting crop parameters at both local and large scales. The present research combined the ANN model with satellite-derived chlorophyll indices from LANDSAT 8 imagery for predicting real-time wheat chlorophyll estimation. The cloud-free scenes of LANDSAT 8 were acquired (Feb-March 2016-17) at the same time when ground-truthing campaign was performed for chlorophyll estimation by using SPAD-502. Different vegetation indices were derived from LANDSAT 8 imagery using ERADAS Imagine (v.2014) software for chlorophyll determination. The vegetation indices were including Normalized Difference Vegetation Index (NDVI), Green Normalized Difference Vegetation Index (GNDVI), Chlorophyll Absorbed Ratio Index (CARI), Modified Chlorophyll Absorbed Ratio Index (MCARI) and Transformed Chlorophyll Absorbed Ratio index (TCARI). For ANN modeling, MATLAB and SPSS (ANN) tools were used. Multilayer Perceptron (MLP) in MATLAB provided very satisfactory results. For training purpose of MLP 61.7% of the data, for validation purpose 28.3% of data and rest 10% of data were used to evaluate and validate the ANN model results. For error evaluation, sum of squares error and relative error were used. ANN model summery showed that sum of squares error of 10.786, the average overall relative error was .099. The MCARI and NDVI were revealed to be more sensitive indices for assessing wheat chlorophyll content with the highest coefficient of determination R²=0.93 and 0.90 respectively. The results suggested that use of high spatial resolution satellite imagery for the retrieval of crop chlorophyll content by using ANN model provides accurate, reliable assessment of crop health status at a larger scale which can help in managing crop nutrition requirement in real time.

Keywords: ANN, chlorophyll content, chlorophyll indices, satellite images, wheat

Procedia PDF Downloads 136

Authors: Yousif Mohamed Y. Abdallah, Razan Manofely, Rajab M. Ben Yousef

Abstract:

X-Ray images are very popular as a first tool for diagnosis. Automating the process of analysis of such images is important in order to help physician procedures. In this practice, teeth segmentation from the radiographic images and feature extraction are essential steps. The main objective of this study was to study correction preprocessing of x-rays images using local adaptive filters in order to evaluate contrast enhancement pattern in different x-rays images such as grey color and to evaluate the usage of new nonlinear approach for contrast enhancement of soft tissues in x-rays images. The data analyzed by using MatLab program to enhance the contrast within the soft tissues, the gray levels in both enhanced and unenhanced images and noise variance. The main techniques of enhancement used in this study were contrast enhancement filtering and deblurring images using the blind deconvolution algorithm. In this paper, prominent constraints are firstly preservation of image's overall look; secondly, preservation of the diagnostic content in the image and thirdly detection of small low contrast details in diagnostic content of the image.

Keywords: enhancement, x-rays, pixel intensity values, MatLab

Procedia PDF Downloads 463

Authors: Filip Rusak, Yulia Arzhaeva, Dadong Wang

Abstract:

Machine learning based Computer-Aided Diagnosis (CAD) is gaining much popularity in medical imaging and diagnostic radiology. However, it requires a large amount of high quality and labeled training image datasets. The training images may come from different sources and be acquired from different radiography machines produced by different manufacturers, digital or digitized copies of film radiographs, with various sizes as well as different pixel intensity distributions. In this paper, a content-aware image augmentation method is presented to deal with these variations. The results of the proposed method have been validated graphically by plotting the removed and added seams of pixels on original images. Two different chest X-ray (CXR) datasets are used in the experiments. The CXRs in the datasets defer in size, some are digital CXRs while the others are digitized from analog CXR films. With the proposed content-aware augmentation method, the Seam Carving algorithm is employed to resize CXRs and the corresponding labels in the form of image masks, followed by histogram matching used to normalize the pixel intensities of digital radiography, based on the pixel intensity values of digitized radiographs. We implemented the algorithms, resized the well-known Montgomery dataset, to the size of the most frequently used Japanese Society of Radiological Technology (JSRT) dataset and normalized our digital CXRs for testing. This work resulted in the unified off-the-shelf CXR dataset composed of radiographs included in both, Montgomery and JSRT datasets. The experimental results show that even though the amount of augmentation is large, our algorithm can preserve the important information in lung fields, local structures, and global visual effect adequately. The proposed method can be used to augment training and testing image data sets so that the trained machine learning model can be used to process CXRs from various sources, and it can be potentially used broadly in any medical imaging applications.

Keywords: computer-aided diagnosis, image augmentation, lung segmentation, medical imaging, seam carving

Procedia PDF Downloads 197

Authors: Shri Krishna Mishra

Abstract:

In an educational context, technology can prompt interactive plight only when it is used in conjunction with interactive plight methods. This study, therefore, examines the relationships among components that contribute to higher levels of interactive plight and execution, such as interactive Plight methods, technology, intrinsic motivation and deep learning. 526 students participated in this study. With structural equation modelling, the authors test the conceptual model and identify satisfactory model fit. The results indicate that interactive Plight methods, technology and intrinsic motivation have significant relationship with interactive Plight; deep learning mediates the relationships of the other variables with Execution.

Keywords: searching the relationship among components, contribute to interactive plight, educational execution, intrinsic motivation

Procedia PDF Downloads 437

Authors: Avichal Malhotra, Jerome Frisch, Christoph van Treeck

Abstract:

The utilization of semantic, cadastral and topological data from geographic information systems (GIS) has exponentially increased for building and urban-scale energy performance simulations. Urban planners, simulation scientists, and researchers use virtual 3D city models for energy analysis, algorithms and simulation tools. For dynamic energy simulations at city and district level, this paper provides an overview of the available GIS data models and their levels of detail. Adhering to different norms and standards, these models also intend to describe building and construction industry data. For further investigations, CityGML data models are considered for simulations. Though geographical information modelling has considerably many different implementations, extensions of virtual city data can also be made for domain specific applications. Highlighting the use of the extended CityGML models for energy researches, a brief introduction to the Energy Application Domain Extension (ADE) along with its significance is made. Consequently, addressing specific input simulation data, a workflow using Modelica underlining the usage of GIS information and the quantification of its significance over annual heating energy demand is presented in this paper.

Keywords: CityGML, EnergyADE, energy performance simulation, GIS

Procedia PDF Downloads 153

Authors: Thomas Monahan, Nicolas Gorius, Thanh Nguyen

Abstract:

Exoplanet atmospheric parameters retrieval is a complex, computationally intensive, inverse modeling problem in which an exoplanet’s atmospheric composition is extracted from an observed spectrum. Traditional Bayesian sampling methods require extensive time and computation, involving algorithms that compare large numbers of known atmospheric models to the input spectral data. Runtimes are directly proportional to the number of parameters under consideration. These increased power and runtime requirements are difficult to accommodate in space missions where model size, speed, and power consumption are of particular importance. The use of traditional Bayesian sampling methods, therefore, compromise model complexity or sampling accuracy. The Atmospheric Retrievals conditional Generative Adversarial Network (ARcGAN) is a deep convolutional generative adversarial network that improves on the previous model’s speed and accuracy. We demonstrate the efficacy of artificial intelligence to quickly and reliably predict atmospheric parameters and present it as a viable alternative to slow and computationally heavy Bayesian methods. In addition to its broad applicability across instruments and planetary types, ARcGAN has been designed to function on low power application-specific integrated circuits. The application of edge computing to atmospheric retrievals allows for real or near-real-time quantification of atmospheric constituents at the instrument level. Additionally, edge computing provides both high-performance and power-efficient computing for AI applications, both of which are critical for space missions. With the edge computing chip implementation, ArcGAN serves as a strong basis for the development of a similar machine-learning algorithm to reduce the downlinked data volume from the Compact Ultraviolet to Visible Imaging Spectrometer (CUVIS) onboard the DAVINCI mission to Venus.

Keywords: deep learning, generative adversarial network, edge computing, atmospheric parameters retrieval

Procedia PDF Downloads 155

Authors: Payel Datta, Abhishek Das, Abhishek Roychoudhury, Dhiman Chattopadhyay, Tanushyam Chattopadhyay

Abstract:

Machine learning (ML) and deep learning (DL) is most predominantly used in image/video processing, natural language processing (NLP), audio and speech recognition but not that much used in system performance evaluation. In this paper, authors are going to describe the architecture of an abstraction layer constructed using ML/DL to detect the system failure. This proposed system is used to detect the system failure by evaluating the performance metrics of an IoT service deployment under constrained infrastructure environment. This system has been tested on the manually annotated data set containing different metrics of the system, like number of threads, throughput, average response time, CPU usage, memory usage, network input/output captured in different hardware environments like edge (atom based gateway) and cloud (AWS EC2). The main challenge of developing such system is that the accuracy of classification should be 100% as the error in the system has an impact on the degradation of the service performance and thus consequently affect the reliability and high availability which is mandatory for an IoT system. Proposed ML/DL classifiers work with 100% accuracy for the data set of nearly 4,000 samples captured within the organization.

Keywords: machine learning, system performance, performance metrics, IoT, edge

Procedia PDF Downloads 182

Authors: Edward K. Boahen, Brunel E. Bouya-Moko, Changda Wang

Abstract:

The major threat to online social network (OSN) users is account compromisation. Spammers now spread malicious messages by exploiting the trust relationship established between account owners and their friends. The challenge in detecting a compromised account by service providers is validating the trusted relationship established between the account owners, their friends, and the spammers. Another challenge is the increase in required human interaction with the feature selection. Research available on supervised learning (machine learning) has limitations with the feature selection and accounts that cannot be profiled, like application programming interface (API). Therefore, this paper discusses the various behaviours of the OSN users and the current approaches in detecting a compromised OSN account, emphasizing its limitations and challenges. We propose a deep learning approach that addresses and resolve the constraints faced by the previous schemes. We detailed our proposed optimized nonsymmetric deep auto-encoder (OPT_NDAE) for unsupervised feature learning, which reduces the required human interaction levels in the selection and extraction of features. We evaluated our proposed classifier using the NSL-KDD and KDDCUP'99 datasets in a graphical user interface enabled Weka application. The results obtained indicate that our proposed approach outperformed most of the traditional schemes in OSN compromised account detection with an accuracy rate of 99.86%.

Keywords: computer security, network security, online social network, account compromisation

Procedia PDF Downloads 100

Authors: Shaan Khosla, Jon Krohn

Abstract:

In a recruiting context, machine learning models are valuable for recommendations: to predict the best candidates for a vacancy, to match the best vacancies for a candidate, and compile a set of similar candidates for any given candidate. While useful to create these models, validating their accuracy in a recommendation context is difficult due to a sparsity of data. In this report, we use network graph data to generate useful representations for candidates and vacancies. We use candidates and vacancies as network nodes and designate a bi-directional link between them based on the candidate interviewing for the vacancy. After using node2vec, the embeddings are used to construct a validation dataset with a ranked order, which will help validate new recommender systems.

Keywords: AI, machine learning, NLP, recruiting

Procedia PDF Downloads 75

Authors: Katalina Grigorova, Kaloyan Mironov

Abstract:

The paper focuses on the benefits of business process modeling. Although this discipline is developing for many years, there is still necessity of creating new opportunities to meet the ever-increasing users’ needs. Because one of these needs is related to the conversion of business process models from one standard to another, the authors have developed a converter between BPMN and EPC standards using workflow patterns as intermediate tool. Nowadays there are too many systems for business process modeling. The variety of output formats is almost the same as the systems themselves. This diversity additionally hampers the conversion of the models. The presented study is aimed at discussing problems due to differences in the output formats of various modeling environments.

Keywords: business process modeling, business process modeling standards, workflow patterns, converting models

Procedia PDF Downloads 566

Authors: Faraz Tahir, M. Usman Akram, Albab Ahmad Khan, Mujahid Abbass, Ahmad Tariq, Nuzhat Qaiser

Abstract:

The objective of this study was to evaluate the Degree of anemia by taking the picture of the palpebral conjunctiva using Smartphone Camera. We have first localized the region of interest from the image and then extracted certain features from that Region of interest and trained SVM classifier on those features and then, as a result, our system classifies the image in real-time on their level of hemoglobin. The proposed system has given an accuracy of 70%. We have trained our classifier on a locally gathered dataset of 30 patients.

Keywords: anemia, palpebral conjunctiva, SVM, smartphone

Procedia PDF Downloads 486

Authors: Saifalarab A. Mohmmed, Morgana E. Vianna, Jonathan C. Knowles

Abstract:

The issue of apical periodontitis has received considerable critical attention. Bacteria is integrated into communities, attached to surfaces and consequently form biofilm. The biofilm structure provides bacteria with a series protection skills against, antimicrobial agents and enhances pathogenicity (e.g. apical periodontitis). Sodium hypochlorite (NaOCl) has become the irrigant of choice for elimination of bacteria from the root canal system based on its antimicrobial findings. The aim of the study was to investigate the effect of different agitation techniques on the efficacy of 2.5% NaOCl to eliminate the biofilm from the surface of the lateral canal using the residual biofilm, and removal rate of biofilm as outcome measures. The effect of canal complexity (lateral canal) on the efficacy of the irrigation procedure was also assessed. Forty root canal models (n = 10 per group) were manufactured using 3D printing and resin materials. Each model consisted of two halves of an 18 mm length root canal with apical size 30 and taper 0.06, and a lateral canal of 3 mm length, 0.3 mm diameter located at 3 mm from the apical terminus. E. faecalis biofilms were grown on the apical 3 mm and lateral canal of the models for 10 days in Brain Heart Infusion broth. Biofilms were stained using crystal violet for visualisation. The model halves were reassembled, attached to an apparatus and tested under a fluorescence microscope. Syringe and needle irrigation protocol was performed using 9 mL of 2.5% NaOCl irrigant for 60 seconds. The irrigant was either left stagnant in the canal or activated for 30 seconds using manual (gutta-percha), sonic and ultrasonic methods. Images were then captured every second using an external camera. The percentages of residual biofilm were measured using image analysis software. The data were analysed using generalised linear mixed models. The greatest removal was associated with the ultrasonic group (66.76%) followed by sonic (45.49%), manual (43.97%), and passive irrigation group (control) (38.67%) respectively. No marked reduction in the efficiency of NaOCl to remove biofilm was found between the simple and complex anatomy models (p = 0.098). The removal efficacy of NaOCl on the biofilm was limited to the 1 mm level of the lateral canal. The agitation of NaOCl results in better penetration of the irrigant into the lateral canals. Ultrasonic agitation of NaOCl improved the removal of bacterial biofilm.

Keywords: 3D printing, biofilm, root canal irrigation, sodium hypochlorite

Procedia PDF Downloads 213

Authors: Fatima-Zahra Eddoug, Jamal Benhra, Rajaa Benabbou

Abstract:

Several project management models exist in the literature and the most used ones are the hybrids for their multiple advantages. Our objective in this paper is to analyze the existing models, which are based on the Lean and Agile approaches and to propose a novel framework with the convenient tools that will allow efficient management of a general project. To create the desired framework, we were based essentially on 7 existing models. Only the Scrum tool among the agile tools was identified by several authors to be appropriate for project management. In contrast, multiple lean tools were proposed in different phases of the project.

Keywords: agility, hybrid project management, lean, scrum

Procedia PDF Downloads 118

Authors: Sule Yucelbas, Gulay Tezel, Cuneyt Yucelbas, Seral Ozsen

Abstract:

In this study, it was tried to identify some heart rhythm disorders by electrocardiography (ECG) data that is taken from MIT-BIH arrhythmia database by subtracting the required features, presenting to artificial neural networks (ANN), artificial immune systems (AIS), artificial neural network based on artificial immune system (AIS-ANN) and particle swarm optimization based artificial neural network (PSO-NN) classifier systems. The main purpose of this study is to evaluate the performance of hybrid AIS-ANN and PSO-ANN classifiers with regard to the ANN and AIS. For this purpose, the normal sinus rhythm (NSR), atrial premature contraction (APC), sinus arrhythmia (SA), ventricular trigeminy (VTI), ventricular tachycardia (VTK) and atrial fibrillation (AF) data for each of the RR intervals were found. Then these data in the form of pairs (NSR-APC, NSR-SA, NSR-VTI, NSR-VTK and NSR-AF) is created by combining discrete wavelet transform which is applied to each of these two groups of data and two different data sets with 9 and 27 features were obtained from each of them after data reduction. Afterwards, the data randomly was firstly mixed within themselves, and then 4-fold cross validation method was applied to create the training and testing data. The training and testing accuracy rates and training time are compared with each other. As a result, performances of the hybrid classification systems, AIS-ANN and PSO-ANN were seen to be close to the performance of the ANN system. Also, the results of the hybrid systems were much better than AIS, too. However, ANN had much shorter period of training time than other systems. In terms of training times, ANN was followed by PSO-ANN, AIS-ANN and AIS systems respectively. Also, the features that extracted from the data affected the classification results significantly.

Keywords: AIS, ANN, ECG, hybrid classifiers, PSO

Procedia PDF Downloads 426

Authors: Mohammadjavad Yaghoubi, Arul Arulrajah, Mahdi M. Disfani, Suksun Horpibulsuk, Myint W. Bo, Stephen P. Darmawan

Abstract:

Utilising waste materials, such as fly ash (FA) and slag (S) stockpiled in landfills, has drawn the attention of researchers and engineers in the recent years. There is a great potential for usage of these wastes in ground improvement projects, especially where deep deposits of soft compressible soils exist. This paper investigates the changes in the strength development of a high water content soft soil stabilised with alkaline activated FA and S, termed as geopolymer binder, to use in deep soil mixing technology. The strength improvement and the changes in the microstructure of the mixtures have been studied. The results show that using FA and S-based geopolymers can increases the strength significantly. Furthermore, utilising FA and S in ground improvement projects, where large amounts of binders are required, can be a solution to the disposal of these wastes.

Keywords: alkaline activation, fly ash, geopolymer, slag, strength development

Procedia PDF Downloads 250

Authors: Jesús A. Pérez, Sam Coppieters, Dimitri Debruyne

Abstract:

In the past decade, the use of digital image correlation (DIC) techniques has increased significantly in the area of experimental mechanics, especially for materials behavior characterization. This non-contact tool enables full field displacement and strain measurements over a complete region of interest. The DIC algorithm requires a random contrast pattern on the surface of the specimen in order to perform properly. To create this pattern, the specimen is usually first coated using a white matt paint. Next, a black random speckle pattern is applied using any suitable method. If the applied paint coating is too thick, its top surface may not be able to exactly follow the deformation of the specimen, and consequently, the strain measurement might be underestimated. In the present article, a study of the influence of the paint thickness on the strain underestimation is performed for different strain levels. The results are then compared to typical paint coating thicknesses applied by experienced DIC users. A slight strain underestimation was observed for paint coatings thicker than about 30μm. On the other hand, this value was found to be uncommonly high compared to coating thicknesses applied by DIC users.

Keywords: digital image correlation, paint coating thickness, strain

Procedia PDF Downloads 499

Authors: Seyed Sadegh Naseralavi, Najmeh Bemani

Abstract:

In this paper, different concrete codes including America, New Zealand, Mexico, Italy, India, Canada, Hong Kong, Euro Code and Britain are compared with the Iranian concrete design code. First, by using Adaptive Neuro Fuzzy Inference System (ANFIS), the codes having the most correlation with the Iranian ninth issue of the national regulation are determined. Consequently, two anticipated methods are used for comparing the codes: Artificial Neural Network (ANN) and Multi-variable regression. The results show that ANN performs better. Predicting is done by using only tensile steel ratio and with ignoring the compression steel ratio.

Keywords: adaptive neuro fuzzy inference system, anticipate method, artificial neural network, concrete design code, multi-variable regression

Procedia PDF Downloads 269

Authors: M. Saiful Islam, M. Mohandes, S. Rehman, S. Badran

Abstract:

Increasing necessity of wind power is directing us to have precise knowledge on wind resources. Methodical investigation of potential locations is required for wind power deployment. High penetration of wind energy to the grid is leading multi megawatt installations with huge investment cost. This fact appeals to determine appropriate places for wind farm operation. For accurate assessment, detailed examination of wind speed profile, relative humidity, temperature and other geological or atmospheric parameters are required. Among all of these uncertainty factors influencing wind power estimation, vertical extrapolation of wind speed is perhaps the most difficult and critical one. Different approaches have been used for the extrapolation of wind speed to hub height which are mainly based on Log law, Power law and various modifications of the two. This paper proposes a Artificial Neural Network (ANN) and Genetic Algorithm (GA) based hybrid model, namely GA-NN for vertical extrapolation of wind speed. This model is very simple in a sense that it does not require any parametric estimations like wind shear coefficient, roughness length or atmospheric stability and also reliable compared to other methods. This model uses available measured wind speeds at 10m, 20m and 30m heights to estimate wind speeds up to 100m. A good comparison is found between measured and estimated wind speeds at 30m and 40m with approximately 3% mean absolute percentage error. Comparisons with ANN and power law, further prove the feasibility of the proposed method.

Keywords: wind profile, vertical extrapolation of wind, genetic algorithm, artificial neural network, hybrid machine learning

Procedia PDF Downloads 478