Search results for: data mining techniques

Authors: Lethola Tshikose, Munyaradzi Katurura

Abstract:

Information and Communication Technology (ICT) plays a critical role in improving daily healthcare processes. The South African healthcare organizations have adopted Information Systems to integrate their patient records. This has made it much easier for healthcare organizations because patient information can now be accessible at any time. The primary purpose of this research study was to investigate the best practices that can be applied to enhance patient security and confidentiality when using e-health systems in South Africa. Security and confidentiality are critical in healthcare organizations as they ensure safety in EHRs. The research study used an inductive research approach that included a thorough literature review; therefore, no data was collected. The research paper’s scope included patient data and possible security threats associated with healthcare systems. According to the study, South African healthcare organizations discovered various patient data security and confidentiality issues. The study also revealed that when it comes to handling patient data, health professionals sometimes make mistakes. Some may not be computer literate, which posed issues and caused data to be tempered with. The research paper recommends that healthcare organizations ensure that security measures are adequately supported and promoted by their IT department. This will ensure that adequate resources are distributed to keep patient data secure and confidential. Healthcare organizations must correctly use standards set up by IT specialists to solve patient data security and confidentiality issues. Healthcare organizations must make sure that their organizational structures are adaptable to improve security and confidentiality.

Keywords: E-health, EHR, security, confidentiality, healthcare

Procedia PDF Downloads 48

Authors: Vhahangwele Belemu, Isaac Busayo Oluwatayo

Abstract:

Post-harvest losses pose a serious challenge to smallholder fruit crop farmers, especially in the rural communities of South Africa, affecting their economic livelihoods and food security. This study investigated the post-harvest handling practices and technologies harnessed by smallholder fruit crop farmers in the Vhembe district of Limpopo province, South Africa. Data were collected on a random sample of 224 smallholder fruit crop farmers selected from the four municipalities of the district using a multistage sampling technique. Analytical tools employed include descriptive statistics and the tobit regression model. A descriptive analysis of farmers’ socioeconomic characteristics showed that a sizeable number of these farmers are still in their active working age (mean = 52 years) with more males (63.8%) than their female (36.2%) counterparts. Respondents’ distribution by educational status revealed that only a few of these had no formal education (2.2%), with the majority having secondary education (48.7%). Results of data analysis further revealed that the prominent post-harvest technologies and handling practices harnessed by these farmers include using appropriate harvesting techniques (20.5%), selling at a reduced price (19.6%), transportation consideration (18.3%), cleaning and disinfecting (17.9%), sorting and grading (16.5%), manual cleaning (15.6%) and packaging technique (11.6%) among others. The result of the Tobit regression analysis conducted to examine the determinants of post-harvest technologies and handling practices harnessed showed that age, educational status of respondents, awareness of technology/handling practices, farm size, access to credit, extension contact, and membership of association were the significant factors. The study suggests enhanced awareness creation, access to credit facility and improved access to market as important factors to consider by relevant stakeholders to assist smallholder fruit crop farmers in the study area.

Keywords: fruit crop farmers, handling practices, post harvest losses, smallholder, Vhembe District, South Africa

Procedia PDF Downloads 54

Authors: Pranjali Avinash Yadav-Deshmukh

Abstract:

Remarkable development of the Internet along with the new technological innovation, such as high-speed systems and affordable large storage space have led to a tremendous increase in the amount and accessibility to digital records. For any person, studying of all these data is tremendously time intensive, so there is a great need to access effective multi-document summarization (MDS) systems, which can successfully reduce details found in several records into a short, understandable summary or conclusion. For semantic representation of textual details in ontology area, as a theoretical design, our system provides a significant structure. The stability of using the ontology in fixing multi-document summarization problems in the sector of catastrophe control is finding its recommended design. Saliency ranking is usually allocated to each phrase and phrases are rated according to the ranking, then the top rated phrases are chosen as the conclusion. With regards to the conclusion quality, wide tests on a selection of media announcements are appropriate for “Jammu Kashmir Overflow in 2014” records. Ontology centered multi-document summarization methods using “NLP centered extraction” outshine other baselines. Our participation in recommended component is to implement the details removal methods (NLP) to enhance the results.

Keywords: disaster management, extraction technique, k-means, multi-document summarization, NLP, ontology, sentence extraction

Procedia PDF Downloads 379

Authors: Issam Lakdhar, Akram Alhussein, Juan Creus

Abstract:

With the huge increase in world energy consumption, researchers are working to find other alternative sources of energy instead of fossil fuel one causing many environmental problems as the production of greenhouse effect gases. Hydrogen is considered a green energy source, which its combustion does not cause environmental pollution. The transport and the storage of the gas molecules or the other products containing this smallest chemical element in metallic structures (pipelines, tanks) are crucial issues. The dissolve and the permeation of hydrogen into the metal lattice lead to the formation of hydride phases and the embrittlement of structures. To protect the metallic structures, a surface treatment could be a good solution. Among the different techniques, magnetron sputtering is used to elaborate micrometric coatings capable of slowing down or stop hydrogen permeation. In the plasma environment, the deposition parameters of new thin-film metallic glasses Al-Ti-W were optimized and controlled in order to obtain, hydrogen barrier. Many characterizations were carried out (SEM, XRD and Nano-indentation…) to control the composition and understand the influence of film microstructure and chemical composition on the hydrogen permeation through the coatings. The coating performance was evaluated under two hydrogen production methods: chemical and electrochemical (cathodic protection) techniques. The hydrogen quantity absorbed was experimentally determined using the Thermal-Desorption Spectroscopy method (TDS)). An ideal ATW thin film was developed and showed excellent behavior against the diffusion of hydrogen.

Keywords: thin films, hydrogen, PVD, plasma technology, electrochemical properties

Procedia PDF Downloads 180

Authors: Girish J. Showkatramani, Arthi M. Krishna, Sashi Nareddi, Naresh Nula, Aaron Pepe, Glen Brown, Greg Gabel, Chris Doninger

Abstract:

Trademark examination and approval is a complex process that involves analysis and review of the design components of the marks such as the visual representation as well as the textual data associated with marks such as marks' description. Currently, the process of identifying marks with similar visual representation is done manually in United States Patent and Trademark Office (USPTO) and takes a considerable amount of time. Moreover, the accuracy of these searches depends heavily on the experts determining the trademark design codes used to catalog the visual design codes in the mark. In this study, we explore several methods to automate trademark design code classification. Based on recent successes of convolutional neural networks in image classification, we have used several different convolutional neural networks such as Google’s Inception v3, Inception-ResNet-v2, and Xception net. The study also looks into other techniques to augment the results from CNNs such as using Open Source Computer Vision Library (OpenCV) to pre-process the images. This paper reports the results of the various models trained on year of annotated trademark images.

Keywords: trademark design code, convolutional neural networks, trademark image classification, trademark image search, Inception-ResNet-v2

Procedia PDF Downloads 226

Authors: Elia Favarelli, Enrico Testi, Andrea Giorgetti

Abstract:

Autonomous structural health monitoring (SHM) of many structures and bridges became a topic of paramount importance for maintenance purposes and safety reasons. This paper proposes a set of machine learning (ML) tools to perform automatic feature selection and detection of anomalies in a bridge from vibrational data and compare different feature extraction schemes to increase the accuracy and reduce the amount of data collected. As a case study, the Z-24 bridge is considered because of the extensive database of accelerometric data in both standard and damaged conditions. The proposed framework starts from the first four fundamental frequencies extracted through operational modal analysis (OMA) and clustering, followed by density-based time-domain filtering (tracking). The fundamental frequencies extracted are then fed to a dimensionality reduction block implemented through two different approaches: feature selection (intelligent multiplexer) that tries to estimate the most reliable frequencies based on the evaluation of some statistical features (i.e., mean value, variance, kurtosis), and feature extraction (auto-associative neural network (ANN)) that combine the fundamental frequencies to extract new damage sensitive features in a low dimensional feature space. Finally, one class classifier (OCC) algorithms perform anomaly detection, trained with standard condition points, and tested with normal and anomaly ones. In particular, a new anomaly detector strategy is proposed, namely one class classifier neural network two (OCCNN2), which exploit the classification capability of standard classifiers in an anomaly detection problem, finding the standard class (the boundary of the features space in normal operating conditions) through a two-step approach: coarse and fine boundary estimation. The coarse estimation uses classics OCC techniques, while the fine estimation is performed through a feedforward neural network (NN) trained that exploits the boundaries estimated in the coarse step. The detection algorithms vare then compared with known methods based on principal component analysis (PCA), kernel principal component analysis (KPCA), and auto-associative neural network (ANN). In many cases, the proposed solution increases the performance with respect to the standard OCC algorithms in terms of F1 score and accuracy. In particular, by evaluating the correct features, the anomaly can be detected with accuracy and an F1 score greater than 96% with the proposed method.

Keywords: anomaly detection, frequencies selection, modal analysis, neural network, sensor network, structural health monitoring, vibration measurement

Procedia PDF Downloads 120

Authors: Richard Byrne, Emma Mulliner

Abstract:

Smart cities are a vision for the future that is increasingly becoming a reality. While a key concept of the smart city is the ability to capture, communicate, and process data that has long been produced through day-to-day activities of the city, much of the assessment models in place neglect this fact to focus on ‘smartness’ concepts. Although it is true technology often provides the opportunity to capture and communicate data in more effective ways, there are also human processes involved that are just as important. The growing importance with regards to the use and ownership of data in society can be seen by all with companies such as Facebook and Google increasingly coming under the microscope, however, why is the same scrutiny not applied to cities? The research area is therefore of great importance to the future of our cities here and now, while the findings will be of just as great importance to our children in the future. This research aims to understand the influence data is having on organisations operating throughout the smart cities sector and employs a mixed-method research approach in order to best answer the following question: Would a data-based evaluation model for smart cities be more appropriate than a smart-based model in assessing the development of the smart city? A fully comprehensive literature review concluded that there was a requirement for a data-driven assessment model for smart cities. This was followed by a documentary analysis to understand the root source of data integration to the smart city. A content analysis of city data platforms enquired as to the alternative approaches employed by cities throughout the UK and draws on best practice from New York to compare and contrast. Grounded in theory, the research findings to this point formulated a qualitative analysis framework comprised of: the changing environment influenced by data, the value of data in the smart city, the data ecosystem of the smart city and organisational response to the data orientated environment. The framework was applied to analyse primary data collected through the form of interviews with both public and private organisations operating throughout the smart cities sector. The work to date represents the first stage of data collection that will be built upon by a quantitative research investigation into the feasibility of data network effects in the smart city. An analysis into the benefits of data interoperability supporting services to the smart city in the areas of health and transport will conclude the research to achieve the aim of inductively forming a framework that can be applied to future smart city policy. To conclude, the research recognises the influence of technological perspectives in the development of smart cities to date and highlights this as a challenge to introduce theory applied with a planning dimension. The primary researcher has utilised their experience working in the public sector throughout the investigation to reflect upon what is perceived as a gap in practice of where we are today, to where we need to be tomorrow.

Keywords: data, planning, policy development, smart cities

Procedia PDF Downloads 308

Authors: Anurag Sharma, Dinesh Kumar, Rahul Malhotra, Manoj Kumar

Abstract:

Fiber based access networks can deliver performance that can support the increasing demands for high speed connections. One of the new technologies that have emerged in recent years is Passive Optical Networks. This paper is targeted to show the simultaneous delivery of triple play service (data, voice and video). The comparative investigation and suitability of various data rates is presented. It is demonstrated that as we increase the data rate, number of users to be accommodated decreases due to increase in bit error rate.

Keywords: BER, PON, TDMPON, GPON, CWDM, OLT, ONT

Procedia PDF Downloads 727

Authors: Nouha Khediri, Mohammed Ben Ammar, Monji Kherallah

Abstract:

Recently, facial emotion recognition (FER) has become increasingly essential to understand the state of the human mind. Accurately classifying emotion from the face is a challenging task. In this paper, we present a facial emotion recognition approach named CV-FER, benefiting from deep learning, especially CNN and VGG16. First, the data is pre-processed with data cleaning and data rotation. Then, we augment the data and proceed to our FER model, which contains five convolutions layers and five pooling layers. Finally, a softmax classifier is used in the output layer to recognize emotions. Based on the above contents, this paper reviews the works of facial emotion recognition based on deep learning. Experiments show that our model outperforms the other methods using the same FER2013 database and yields a recognition rate of 92%. We also put forward some suggestions for future work.

Keywords: CNN, deep-learning, facial emotion recognition, machine learning

Procedia PDF Downloads 87

Authors: Ayten Ekin Meşe, Selahattin Şentürk, Melike Duvanoğlu

Abstract:

Petroleum refineries are a highly complex process industry with continuous production and high operating costs. Physical separation of crude oil starts with the crude oil distillation unit, continues with various conversion and purification units, and passes through many stages until obtaining the final product. To meet the desired product specification, process parameters are strictly followed. To be able to ensure the quality of distillates, routine analyses are performed in quality control laboratories based on appropriate international standards such as American Society for Testing and Materials (ASTM) standard methods and European Standard (EN) methods. The cut point of distillates in the crude distillation unit is very crucial for the efficiency of the upcoming processes. In order to maximize the process efficiency, the determination of the quality of distillates should be as fast as possible, reliable, and cost-effective. In this sense, an alternative study was carried out on the crude oil distillation unit that serves the entire refinery process. In this work, studies were conducted with three different crude oil distillates which are Light Straight Run Naphtha (LSRN), Heavy Straight Run Naphtha (HSRN), and Kerosene. These products are named after separation by the number of carbons it contains. LSRN consists of five to six carbon-containing hydrocarbons, HSRN consist of six to ten, and kerosene consists of sixteen to twenty-two carbon-containing hydrocarbons. Physical properties of three different crude distillation unit products (LSRN, HSRN, and Kerosene) were determined using Near-Infrared Spectroscopy with multivariate calibration. The absorbance spectra of the petroleum samples were obtained in the range from 10000 cm⁻¹ to 4000 cm⁻¹, employing a quartz transmittance flow through cell with a 2 mm light path and a resolution of 2 cm⁻¹. A total of 400 samples were collected for each petroleum sample for almost four years. Several different crude oil grades were processed during sample collection times. Extended Multiplicative Signal Correction (EMSC) and Savitzky-Golay (SG) preprocessing techniques were applied to FT-NIR spectra of samples to eliminate baseline shifts and suppress unwanted variation. Two different multivariate calibration approaches (Partial Least Squares Regression, PLS and Genetic Inverse Least Squares, GILS) and an ensemble model were applied to preprocessed FT-NIR spectra. Predictive performance of each multivariate calibration technique and preprocessing techniques were compared, and the best models were chosen according to the reproducibility of ASTM reference methods. This work demonstrates the developed models can be used for routine analysis instead of conventional analytical methods with over 90% accuracy.

Keywords: crude distillation unit, multivariate calibration, near infrared spectroscopy, data preprocessing, refinery

Procedia PDF Downloads 115

Authors: Zahreddine Hafsi, Manoranjan Mishra , Sami Elaoud

Abstract:

Ensuring the maximum recovery rate of oil from reservoir rocks is a challenging task that requires preliminary numerical analysis of different techniques used to enhance the recovery process. After conventional oil recovery processes and in order to retrieve oil left behind after the primary recovery phase, water flooding in one of several techniques used for enhanced oil recovery (EOR). In this research work, EOR via water flooding is numerically modeled, and hydrodynamic instabilities resulted from immiscible oil-water flow in reservoir rocks are investigated. An oil reservoir is a porous medium consisted of many fractures of tiny dimensions. For modeling purposes, the oil reservoir is considered as a collection of capillary tubes which provides useful insights into how fluids behave in the reservoir pore spaces. Equations governing oil-water flow in oil reservoir rocks are developed and numerically solved following a finite element scheme. Numerical results are obtained using Comsol Multiphysics software. The two phase Darcy module of COMSOL Multiphysics allows modelling the imbibition process by the injection of water (as wetting phase) into an oil reservoir. Van Genuchten, Brooks Corey and Levrett models were considered as retention models and obtained flow configurations are compared, and the governing parameters are discussed. For the considered retention models it was found that onset of instabilities viz. fingering phenomenon is highly dependent on the capillary pressure as well as the boundary conditions, i.e., the inlet pressure and the injection velocity.

Keywords: capillary pressure, EOR process, immiscible flow, numerical modelling

Procedia PDF Downloads 124

Authors: Vivian Isaac, A. T. Joteeshwaran, Craig McLachlan

Abstract:

The University of New South Wales (UNSW) Rural Clinical School has a strategic collaborative focus on chronic disease and public health. Our objectives are to understand rural environmental and biological interactions in vulnerable community populations. The UNSW Rural Clinical School translational model is a spoke and hub network. This spoke and hub model connects rural data and biological specimens with city based collaborative public health research networks. Similar spoke and hub models are prevalent across research centers in India. The Australia-India Council grant was awarded so we could establish sustainable public health and community research collaborations. As part of the collaborative network we are developing strategies around data and biological sharing platforms between Indian Institute of Public Health, Public Health Foundation of India (PHFI), Hyderabad and Rural Clinical School UNSW. The key objective is to understand how research collaborations are conducted in India and also how data can shared and tracked with external collaborators such as ourselves. A framework to improve data sharing for research collaborations, including DNA was proposed as a project outcome. The complexities of sharing biological data has been investigated via a visit to India. A flagship sustainable project between Rural Clinical School UNSW and PHFI would illustrate a model of data sharing platforms.

Keywords: data sharing, collaboration, public health research, chronic disease

Procedia PDF Downloads 445

Authors: Iman Abu-Rub

Abstract:

This research paper examines if Artificial Intelligence is, in fact, racist or not. Different studies from all around the world, and covering different communities were analyzed to further understand AI’s true implications over different communities. The black community, Asian community, and Muslim community were all analyzed and discussed in the paper to figure out if AI is biased or unbiased towards these specific communities. It was found that the biggest problem AI faces is the biased distribution of data collection. Most of the data inserted and coded into AI are of a white male, which significantly affects the other communities in terms of reliable cultural, political, or medical research. Nonetheless, there are various research was done that help increase awareness of this issue, but also solve it completely if done correctly. Governments and big corporations are able to implement different strategies into their AI inventions to avoid any racist results, which could cause hatred culturally but also unreliable data, medically, for example. Overall, Artificial Intelligence is not racist per se, but the data implementation and current racist culture online manipulate AI to become racist.

Keywords: social media, artificial intelligence, racism, discrimination

Procedia PDF Downloads 111

Authors: Vabya Kumar Pandit, Mudit Mittal, N. Prahlad Rao, Ramnath Babu

Abstract:

TeamIndus is the only Indian team competing for the Google Lunar XPRIZE(GLXP). The GLXP is a global competition to challenge the private entities to soft land a rover on the moon, travel minimum 500 meters and transmit high definition images and videos to Earth. Towards this goal, the TeamIndus strategy is to design and developed lunar lander that will deliver a rover onto the surface of the moon which will accomplish GLXP mission objectives. This paper showcases the various system level noise control techniques adopted by Electrical Distribution System (EDS), to achieve the required Electromagnetic Compatibility (EMC) of the spacecraft. The design guidelines followed to control Electromagnetic Interference by proper electronic package design, grounding, shielding, filtering, and cable routing within the stipulated mass budget, are explained. The paper also deals with the challenges of achieving Electromagnetic Cleanliness in presence of various Commercial Off-The-Shelf (COTS) and In-House developed components. The methods of minimizing Electrostatic Discharge (ESD) by identifying the potential noise sources, susceptible areas for charge accumulation and the methodology to prevent arcing inside spacecraft are explained. The paper then provides the EMC requirements matrix derived from the mission requirements to meet the overall Electromagnetic compatibility of the Spacecraft.

Keywords: electromagnetic compatibility, electrostatic discharge, electrical distribution systems, grounding schemes, light weight harnessing

Procedia PDF Downloads 289

Authors: Salihah Alghamdi, Surajit Ray

Abstract:

Space-time data can be observed over irregularly shaped manifolds, which might have complex boundaries or interior gaps. Most of the existing methods do not consider the shape of the data, and as a result, it is difficult to model irregularly shaped data accommodating the complex domain. We used a method that can deal with space-time data that are distributed over non-planner shaped regions. The method is based on partial differential equations and finite element analysis. The model can be estimated using a penalized least squares approach with a regularization term that controls the over-fitting. The model is regularized using two roughness penalties, which consider the spatial and temporal regularities separately. The integrated square of the second derivative of the basis function is used as temporal penalty. While the spatial penalty consists of the integrated square of Laplace operator, which is integrated exclusively over the domain of interest that is determined using finite element technique. In this paper, we applied a spatio-temporal regression model with partial differential equations regularization (ST-PDE) approach to analyze a remote sensing data measuring the greenness of vegetation, measure by an index called enhanced vegetation index (EVI). The EVI data consist of measurements that take values between -1 and 1 reflecting the level of greenness of some region over a period of time. We applied (ST-PDE) approach to irregular shaped region of the EVI data. The approach efficiently accommodates the irregular shaped regions taking into account the complex boundaries rather than smoothing across the boundaries. Furthermore, the approach succeeds in capturing the temporal variation in the data.

Keywords: irregularly shaped domain, partial differential equations, finite element analysis, complex boundray

Procedia PDF Downloads 136

Authors: P. Daniels, T. Adonis, P. September-Brown, R. Comalie

Abstract:

The community engagement unit at the University of the Western Cape was tasked with establishing a community engagement database. The database would store information of all community engagement projects related to the university. The wealth of knowledge obtained from the various disciplines would be used to facilitate interdisciplinary collaboration within the university, as well as facilitating community university partnership opportunities. The purpose of this qualitative study was to explore electronic data collection through the development of a database. Two types of electronic data collection platforms were used, namely online questionnaire and email. The semi structured questionnaire was used to collect data related to community engagement projects from different faculties and departments at the university. There are many benefits for using an electronic data collection platform, such as reduction of costs and time, ease in reaching large numbers of potential respondents, and the possibility of providing anonymity to participants. Despite all the advantages of using the electronic platform, there were as many challenges, as depicted in our findings. The findings suggest that certain barriers existed by using an electronic platform for data collection, even though it was in an academic environment, where knowledge and resources were in abundance. One of the challenges experienced in this process was the lack of dissemination of information via email to staff within faculties. The actual online software used for the questionnaire had its own limitations, such as only being able to access the questionnaire from the same electronic device. In a few cases, academics only completed the questionnaire after a telephonic prompt or face to face meeting about "Is higher education in South Africa ready to embrace electronic platform in data collection?"

Keywords: community engagement, database, data collection, electronic platform, electronic tools, knowledge sharing, university

Procedia PDF Downloads 258

Authors: Muhammad Bahrul Ilmi

Abstract:

The purpose of this research is to analyze the influence of Islamic financing and work relation founding simultaneously and partially towards non-performing financing in Islamic banks. This research was regression quantitative field research, and had been done in Muammalat Indonesia Bank and Islamic Danamon Bank in 3 months. The populations of this research were 15 account officers of Muammalat Indonesia Bank and Islamic Danamon Bank in Surakarta, Indonesia. The techniques of collecting data used in this research were documentation, questionnaire, literary study and interview. Regression analysis result shows that Islamic financing and work relation founding simultaneously has positive and significant effect towards non performing financing of two Islamic Banks. It is obtained with probability value 0.003 which is less than 0.05 and F value 9.584. The analysis result of Islamic financing regression towards non performing financing shows the significant effect. It is supported by double linear regression analysis with probability value 0.001 which is less than 0.05. The regression analysis of work relation founding effect towards non-performing financing shows insignificant effect. This is shown in the double linear regression analysis with probability value 0.161 which is bigger than 0.05.

Keywords: Syariah financing, work relation founding, non-performing financing (NPF), Islamic Bank

Procedia PDF Downloads 426

Authors: Divya Juneja, Sukhjeet Kaur Matharu

Abstract:

Purpose: The paper is aimed at identifying the challenging factors experienced by the women entrepreneurs in India in operating their enterprises amidst the challenges posed by the COVID-19 pandemic. Methodology: The sample for the study comprised 396 women entrepreneurs from different regions of India. A purposive sampling technique was adopted for data collection. Data was collected through a self-administered questionnaire. Analysis was performed using the SPSS package for quantitative data analysis. Findings: The results of the study state that entrepreneurial characteristics, resourcefulness, networking, adaptability, and continuity have a positive influence on the resiliency of women entrepreneurs when faced with a crisis situation. Practical Implications: The findings of the study have some important implications for women entrepreneurs, organizations, government, and other institutions extending support to entrepreneurs.

Keywords: women entrepreneurs, analysis, data analysis, positive influence, resiliency

Procedia PDF Downloads 107

Authors: Mohammed Abdullah Alshahrani

Abstract:

The research focuses on investigating the use of partial least squares (PLS) methodology for addressing challenges associated with high-dimensional correlated data. Recent technological advancements have led to experiments producing data characterized by a large number of variables compared to observations, with substantial inter-variable correlations. Such data patterns are common in chemometrics, where near-infrared (NIR) spectrometer calibrations record chemical absorbance levels across hundreds of wavelengths, and in genomics, where thousands of genomic regions' copy number alterations (CNA) are recorded from cancer patients. PLS serves as a widely used method for analyzing high-dimensional data, functioning as a regression tool in chemometrics and a classification method in genomics. It handles data complexity by creating latent variables (components) from original variables. However, applying PLS can present challenges. The study investigates key areas to address these challenges, including unifying interpretations across three main PLS algorithms and exploring unusual negative shrinkage factors encountered during model fitting. The research presents an alternative approach to addressing the interpretation challenge of predictor weights associated with PLS. Sparse estimation of predictor weights is employed using a penalty function combining a lasso penalty for sparsity and a Cauchy distribution-based penalty to account for variable dependencies. The results demonstrate sparse and grouped weight estimates, aiding interpretation and prediction tasks in genomic data analysis. High-dimensional data scenarios, where predictors outnumber observations, are common in regression analysis applications. Ordinary least squares regression (OLS), the standard method, performs inadequately with high-dimensional and highly correlated data. Copy number alterations (CNA) in key genes have been linked to disease phenotypes, highlighting the importance of accurate classification of gene expression data in bioinformatics and biology using regularized methods like PLS for regression and classification.

Keywords: partial least square regression, genetics data, negative filter factors, high dimensional data, high correlated data

Procedia PDF Downloads 45

Authors: Maisyatus Suadaa Irfana, Nove Eka Variant Anna, Dyah Puspitasari Sri Rahayu

Abstract:

Technological developments provide convenience to all the people. Nowadays, the communication of human with the computer is done via text. With the development of technology, human and computer communications have been conducted with a voice like communication between human beings. It provides an easy facility for many people, especially those who have special needs. Voice search technology is applied in the search of book collections in the OPAC (Online Public Access Catalog), so library visitors will find it faster and easier to find books that they need. Integration with Google is needed to convert the voice into text. To optimize the time and the results of searching, Server will download all the book data that is available in the server database. Then, the data will be converted into JSON format. In addition, the incorporation of some algorithms is conducted including Decomposition (parse) in the form of array of JSON format, the index making, analyzer to the result. It aims to make the process of searching much faster than the usual searching in OPAC because the data are directly taken to the database for every search warrant. Data Update Menu is provided with the purpose to enable users perform their own data updates and get the latest data information.

Keywords: OPAC, voice, searching, faster

Procedia PDF Downloads 340

Authors: Sophia Shi

Abstract:

Acute kidney injury (AKI) is the sudden onset of kidney damage in which the kidneys cannot filter waste from the blood, requiring emergency hospitalization. AKI patient mortality rate is high in the ICU and is virtually impossible for doctors to predict because it is so unexpected. Currently, there is no hybrid model predicting AKI that takes advantage of two types of data. De-identified patient data from the MIMIC-III database and de-identified kidney images and corresponding patient records from the Beijing Hospital of the Ministry of Health were collected. Using data features including serum creatinine among others, two numeric models using MIMIC and Beijing Hospital data were built, and with the hospital ultrasounds, an image-only model was built. Convolutional neural networks (CNN) were used, VGG and Resnet for numeric data and Resnet for image data, and they were combined into a hybrid model by concatenating feature maps of both types of models to create a new input. This input enters another CNN block and then two fully connected layers, ending in a binary output after running through Softmax and additional code. The hybrid model successfully predicted AKI and the highest AUROC of the model was 0.953, achieving an accuracy of 90% and F1-score of 0.91. This model can be implemented into urgent clinical settings such as the ICU and aid doctors by assessing the risk of AKI shortly after the patient’s admission to the ICU, so that doctors can take preventative measures and diminish mortality risks and severe kidney damage.

Keywords: Acute kidney injury, Convolutional neural network, Hybrid deep learning, Patient record data, ResNet, Ultrasound kidney images, VGG

Procedia PDF Downloads 126

Authors: S. Saju, G. Thirugnanam

Abstract:

In this paper, a medical image watermarking algorithm based on contourlet is proposed. Medical image watermarking is a special subcategory of image watermarking in the sense that images have special requirements. Watermarked medical images should not differ perceptually from their original counterparts because clinical reading of images must not be affected. Watermarking techniques based on wavelet transform are reported in many literatures but robustness and security using contourlet are better when compared to wavelet transform. The main challenge in exploring geometry in images comes from the discrete nature of the data. In this paper, original image is decomposed to two level using contourlet and the watermark is embedded in the resultant sub-bands. Sub-band selection is based on the value of Peak Signal to Noise Ratio (PSNR) that is calculated between watermarked and original image. To extract the watermark, Kernel ICA is used and it has a novel characteristic is that it does not require the transformation process to extract the watermark. Simulation results show that proposed scheme is robust against attacks such as Salt and Pepper noise, Median filtering and rotation. The performance measures like PSNR and Similarity measure are evaluated and compared with Discrete Wavelet Transform (DWT) to prove the robustness of the scheme. Simulations are carried out using Matlab Software.

Keywords: digital watermarking, independent component analysis, wavelet transform, contourlet

Procedia PDF Downloads 521

Authors: Taner Ersoz, Filiz Ersoz

Abstract:

This study was designed enable application of multivariate technique in the interpretation of categorical data for measuring health care services satisfaction in Turkey. The data was collected from a total of 17726 respondents. The establishment of the sample group and collection of the data were carried out by a joint team from The Ministry of Health and Turkish Statistical Institute (Turk Stat) of Turkey. The multiple correspondence analysis (MCA) was used on the data of 2882 respondents who answered the questionnaire in full. The multiple correspondence analysis indicated that, in the evaluation of health services females, public employees, younger and more highly educated individuals were more concerned and complainant than males, private sector employees, older and less educated individuals. Overall 53 % of the respondents were pleased with the improvements in health care services in the past three years. This study demonstrates the public consciousness in health services and health care satisfaction in Turkey. It was found that most the respondents were pleased with the improvements in health care services over the past three years. Awareness of health service quality increases with education levels. Older individuals and males would appear to have lower expectancies in health services.

Keywords: multiple correspondence analysis, multivariate categorical data, health care services, health satisfaction survey

Procedia PDF Downloads 237

Authors: Bharti Garg, Ashleigh Cousins, Pauline Pearson, Vincent Verheyen, Paul Feron

Abstract:

The presence of SO₂ in power plant flue gases makes flue gas desulfurization (FGD) an essential requirement prior to post combustion CO₂ (PCC) removal facilities. Although most of the power plants worldwide deploy FGD in order to comply with environmental regulations, generally the achieved SO₂ levels are not sufficiently low for the flue gases to enter the PCC unit. The SO₂ level in the flue gases needs to be less than 10 ppm to effectively operate the PCC installation. The existing FGD units alone cannot bring down the SO₂ levels to or below 10 ppm as required for CO₂ capture. It might require an additional scrubber along with the existing FGD unit to bring the SO₂ to the desired levels. The absence of FGD units in Australian power plants brings an additional challenge. SO₂ concentrations in Australian power station flue gas emissions are in the range of 100-600 ppm. This imposes a serious barrier on the implementation of standard PCC technologies in Australia. CSIRO’s developed CS-Cap process is a unique solution to capture SO₂ and CO₂ in a single column with single absorbent which can potentially bring cost-effectiveness to the commercial deployment of carbon capture in Australia, by removing the need for FGD. Estimated savings of removing SO₂ through a similar process as CS-Cap is around 200 MMUSD for a 500 MW Australian power plant. Pilot plant trials conducted to generate the proof of concept resulted in 100% removal of SO₂ from flue gas without utilising standard limestone-based FGD. In this work, removal of absorbed sulfur from aqueous amine absorbents generated in the pilot plant trials has been investigated by reactive crystallisation and thermal reclamation. More than 95% of the aqueous amines can be reclaimed back from the sulfur loaded absorbent via reactive crystallisation. However, the recovery of amines through thermal reclamation is limited and depends on the sulfur loading on the spent absorbent. The initial experimental work revealed that reactive crystallisation is a better fit for CS-Cap’s sulfur-rich absorbent especially when it is also capable of generating K₂SO₄ crystals of highly saleable quality ~ 99%. Initial cost estimation carried on both the technologies resulted in almost similar capital expenditure; however, the operating cost is considerably higher in thermal reclaimer than that in crystalliser. The experimental data generated in the laboratory from both the regeneration techniques have been used to generate the simulation model in Aspen Plus. The simulation model illustrates the economic benefits which could be gained by removing flue gas desulfurization prior to standard PCC unit and replacing it with a CS-Cap absorber column co-capturing CO₂ and SO₂, and it's absorbent regeneration system which would be either reactive crystallisation or thermal reclamation.

Keywords: combined capture, cost analysis, crystallisation, CS-Cap, flue gas desulfurisation, regeneration, sulfur, thermal reclamation

Procedia PDF Downloads 119

Authors: Andrés C. Cuervo Pinilla, Christian G. Quintero M., Chinthaka Premachandra

Abstract:

This paper considers people’s driving skills diagnosis under real driving conditions. In that sense, this research presents an approach that uses GPS signals which have a direct correlation with driving maneuvers. Besides, it is presented a novel expert-driving-criteria approximation using fuzzy logic which seeks to analyze GPS signals in order to issue an intelligent driving diagnosis. Based on above, this works presents in the first section the intelligent driving diagnosis system approach in terms of its own characteristics properties, explaining in detail significant considerations about how an expert-driving-criteria approximation must be developed. In the next section, the implementation of our developed system based on the proposed fuzzy logic approach is explained. Here, a proposed set of rules which corresponds to a quantitative abstraction of some traffics laws and driving secure techniques seeking to approach an expert-driving- criteria approximation is presented. Experimental testing has been performed in real driving conditions. The testing results show that the intelligent driving diagnosis system qualifies driver’s performance quantitatively with a high degree of reliability.

Keywords: driver support systems, intelligent transportation systems, fuzzy logic, real time data processing

Procedia PDF Downloads 512

Authors: Katawut Kaewbanjong

Abstract:

We analyzed a volume of data and found significant user satisfaction in software project factors. A statistical significance analysis (logistic regression) and collinearity analysis determined the significance factors from a group of 71 pre-defined factors from 191 software projects in ISBSG Release 12. The eight prediction models used for testing the prediction potential of these factors were Neural network, k-NN, Naïve Bayes, Random forest, Decision tree, Gradient boosted tree, linear regression and logistic regression prediction model. Fifteen pre-defined factors were truly significant in predicting user satisfaction, and they provided 82.71% prediction accuracy when used with a neural network prediction model. These factors were client-server, personnel changes, total defects delivered, project inactive time, industry sector, application type, development type, how methodology was acquired, development techniques, decision making process, intended market, size estimate approach, size estimate method, cost recording method, and effort estimate method. These findings may benefit software development managers considerably.

Keywords: prediction model, statistical analysis, software project, user satisfaction factor

Procedia PDF Downloads 118

Authors: Ashok Tejankar, Rohan K. Pathrikar

Abstract:

Maharashtra is covered by heterogeneous flows of Deccan basaltic terrains of upper cretaceous to lower Eocene age. It consist mainly different types of basalt flow, having heterogeneous Geohydrological characters. The study area Aurangabad dist. lies in the central part of Maharashtra. The study area is typically covered by Deccan traps formation mainly basalt type of igneous volcanic rock. The area is located in the survey of India toposheet No. 47M and laying between 19° to 20° north latitudes and 74° to 76° east longitudes. Groundwater is the primary source for fresh water in the study area. There has been a growing demand for fresh water in domestic & agriculture sectors. Due to over exploitation and rainfall failure has been created an irrecoverable stress on groundwater in study area. In an effort to maintain the water table condition in balance, artificial recharge is being implemented. The selection of site for artificial recharge is a very important task in recharge basalt. The present study aims at sitting artificial recharge structure at village Pachod in basaltic terrain of the Godavari-Purna river basin in Aurangabad district of Maharashtra, India. where the average annual rainfall is 650mm. In this investigation, integrated remote sensing and GIS techniques were used and various parameters like lithology, structure, etc. aspect of drainage basins, landforms and other parameters were extracted from visual interpretation of IRS P6 Satellite data and Survey of India (SIO) topographical sheets, aided by field checks by carrying well inventory survey. The depth of weathered material, water table conditions, and rainfall data were been considered. All the thematic information layers were digitized and analyzed in Arc-GIS environment and the composite maps produced show suitable site, depth of bed rock flows for successful artificial recharge in village Pachod to increase groundwater potential of low laying area.

Keywords: hard rock, artificial recharge, remote sensing, GIS

Procedia PDF Downloads 288

Authors: Paul Dallyn, Ashraf El-Hamalawi, Alessandro Palmeri, Bob Knight

Abstract:

In order to better understand the long term implications of the grout wear failure mode in large-diameter plain-sided grouted connections, a numerical model has been developed and calibrated that can take advantage of existing operational plant data to predict the wear accumulation for the actual load conditions experienced over a given period, thus limiting the need for expensive monitoring systems. This model has been derived and calibrated based on site structural condition monitoring (SCM) data and supervisory control and data acquisition systems (SCADA) data for two operational wind turbine generator substructures afflicted with this challenge, along with experimentally derived wear rates.

Keywords: grouted connection, numerical model, offshore structure, wear, wind energy

Procedia PDF Downloads 448

Authors: Ons Slimene, Aroua Taamallah, Maha Khemaja

Abstract:

In recent years, human activity recognition (HAR) has been a key area of research due to its diverse applications. It has garnered increasing attention in the field of computer vision. HAR plays an important role in people’s daily lives as it has the ability to learn advanced knowledge about human activities from data. In HAR, activities are usually represented by exploiting different types of sensors, such as embedded sensors or visual sensors. However, these sensors have limitations, such as local obstacles, image-related obstacles, sensor unreliability, and consumer concerns. Recently, several deep learning-based approaches have been proposed for HAR and these approaches are classified into two categories based on the type of data used: vision-based approaches and sensor-based approaches. This research paper highlights the importance of multimodal data fusion from skeleton data obtained from videos and data generated by embedded sensors using deep neural networks for achieving HAR. We propose a deep multimodal fusion network based on a twostream architecture. These two streams use the Convolutional Neural Network combined with the Bidirectional LSTM (CNN BILSTM) to process skeleton data and data generated by embedded sensors and the fusion at the feature level is considered. The proposed model was evaluated on a public OPPORTUNITY++ dataset and produced a accuracy of 96.77%.

Keywords: human activity recognition, action recognition, sensors, vision, human-centric sensing, deep learning, context-awareness

Procedia PDF Downloads 96

Authors: Waqar Ahmad Butt, Gholamreza Vakili Nezhaad, Ali Soud Al Bemani, Yahya Al Wahaibi

Abstract:

Minimum miscibility pressure (MMP) plays a great role in determining the displacement efficiency of different gas injection processes. Experimental techniques for MMP determination include industrially recommended slim tube, vanishing interfacial tension (VIT) and rising bubble apparatus (RBA). In this paper, MMP measurement study using slim tube and VIT experimental techniques for two different crude oil samples (M and N) both in live and stock tank oil forms is being presented. VIT measured MMP values for both 'M' and 'N' live crude oils were close to slim tube determined MMP values with 6.4 and 5 % deviation respectively. Whereas for both oil samples in stock tank oil form, VIT measured MMP showed a higher unacceptable deviation from slim tube determined MMP. This higher difference appears to be related to high stabilized crude oil heavier fraction and lack of multiple contacts miscibility. None of the different nine deployed crude oil and CO2 MMP computing correlations could result in reliable MMP, close to slim tube determined MMP. Since VIT determined MMP values for both considered live crude oils are in close match with slim tube determined MMP values, it confirms reliable, reproducible, rapid and cheap alternative for live crude oil MMP determination. Whereas VIT MMP determination for stock tank oil case needed further investigation about stabilization / destabilization mechanism of oil heavier ends and multiple contacts miscibility development issues.

Keywords: minimum miscibility pressure, interfacial tension, multiple contacts miscibility, heavier ends

Procedia PDF Downloads 265