Search results for: data driven diagnosis
26299 Features of Normative and Pathological Realizations of Sibilant Sounds for Computer-Aided Pronunciation Evaluation in Children
Authors: Zuzanna Miodonska, Michal Krecichwost, Pawel Badura
Abstract:
Sigmatism (lisping) is a speech disorder in which sibilant consonants are mispronounced. The diagnosis of this phenomenon is usually based on the auditory assessment. However, the progress in speech analysis techniques creates a possibility of developing computer-aided sigmatism diagnosis tools. The aim of the study is to statistically verify whether specific acoustic features of sibilant sounds may be related to pronunciation correctness. Such knowledge can be of great importance while implementing classifiers and designing novel tools for automatic sibilants pronunciation evaluation. The study covers analysis of various speech signal measures, including features proposed in the literature for the description of normative sibilants realization. Amplitudes and frequencies of three fricative formants (FF) are extracted based on local spectral maxima of the friction noise. Skewness, kurtosis, four normalized spectral moments (SM) and 13 mel-frequency cepstral coefficients (MFCC) with their 1st and 2nd derivatives (13 Delta and 13 Delta-Delta MFCC) are included in the analysis as well. The resulting feature vector contains 51 measures. The experiments are performed on the speech corpus containing words with selected sibilant sounds (/ʃ, ʒ/) pronounced by 60 preschool children with proper pronunciation or with natural pathologies. In total, 224 /ʃ/ segments and 191 /ʒ/ segments are employed in the study. The Mann-Whitney U test is employed for the analysis of stigmatism and normative pronunciation. Statistically, significant differences are obtained in most of the proposed features in children divided into these two groups at p < 0.05. All spectral moments and fricative formants appear to be distinctive between pathology and proper pronunciation. These metrics describe the friction noise characteristic for sibilants, which makes them particularly promising for the use in sibilants evaluation tools. Correspondences found between phoneme feature values and an expert evaluation of the pronunciation correctness encourage to involve speech analysis tools in diagnosis and therapy of sigmatism. Proposed feature extraction methods could be used in a computer-assisted stigmatism diagnosis or therapy systems.Keywords: computer-aided pronunciation evaluation, sigmatism diagnosis, speech signal analysis, statistical verification
Procedia PDF Downloads 29426298 Influences of Separation of the Boundary Layer in the Reservoir Pressure in the Shock Tube
Authors: Bruno Coelho Lima, Joao F.A. Martos, Paulo G. P. Toro, Israel S. Rego
Abstract:
The shock tube is a ground-facility widely used in aerospace and aeronautics science and technology for studies on gas dynamic and chemical-physical processes in gases at high-temperature, explosions and dynamic calibration of pressure sensors. A shock tube in its simplest form is comprised of two separate tubes of equal cross-section by a diaphragm. The diaphragm function is to separate the two reservoirs at different pressures. The reservoir containing high pressure is called the Driver, the low pressure reservoir is called Driven. When the diaphragm is broken by pressure difference, a normal shock wave and non-stationary (named Incident Shock Wave) will be formed in the same place of diaphragm and will get around toward the closed end of Driven. When this shock wave reaches the closer end of the Driven section will be completely reflected. Now, the shock wave will interact with the boundary layer that was created by the induced flow by incident shock wave passage. The interaction between boundary layer and shock wave force the separation of the boundary layer. The aim of this paper is to make an analysis of influences of separation of the boundary layer in the reservoir pressure in the shock tube. A comparison among CDF (Computational Fluids Dynamics), experiments test and analytical analysis were performed. For the analytical analysis, some routines in Python was created, in the numerical simulations (Computational Fluids Dynamics) was used the Ansys Fluent, and the experimental tests were used T1 shock tube located in IEAv (Institute of Advanced Studies).Keywords: boundary layer separation, moving shock wave, shock tube, transient simulation
Procedia PDF Downloads 31026297 A Case of Generalized Anxiety Disorder (GAD)
Authors: Muhammad Zeeshan
Abstract:
This case study is about a 54 years man named Mr. U, referred to Capital Hospital, Islamabad, with the presenting complaints of Generalized Anxiety Disorder (GAD). Contrary to his complaints, the client reported psychological symptoms such as restlessness, low mood and fear of darkness and fear from closed places from the last 30 days. He also had a fear of death and his existence in the grave. His sleep was also disturbed due to excessive urination due to diabetes. He was also suffering from semantic symptoms such as headache, numbness of feet and pain in the chest and blockage of the nose. A complete history was taken and informal assessment (clinical interview and MSE) and formal testing (BAI) was applied that showed the clear diagnosis of Generalized Anxiety Disorder. CBT, relaxation techniques, prayer chart and behavioural techniques were applied for the treatment purposes.Keywords: generalized anxiety disorder, presenting complaints, formal and informal assessment, diagnosis
Procedia PDF Downloads 28026296 First Experimental Evidence on Feasibility of Molecular Magnetic Particle Imaging of Tumor Marker Alpha-1-Fetoprotein Using Antibody Conjugated Nanoparticles
Authors: Kolja Them, Priyal Chikhaliwala, Sudeshna Chandra
Abstract:
Purpose: The purpose of this work is to examine possibilities for noninvasive imaging and identification of tumor markers for cancer diagnosis. The proposed method uses antibody conjugated iron oxide nanoparticles and multicolor Magnetic Particle Imaging (mMPI). The method has the potential for radiation exposure free real-time estimation of local tumor marker concentrations in vivo. In this study, the method is applied to human Alpha-1-Fetoprotein. Materials and Methods: As tracer material AFP antibody-conjugated Dendrimer-Fe3O4 nanoparticles were used. The nanoparticle bioconjugates were then incubated with bovine serum albumin (BSA) to block any possible nonspecific binding sites. Parts of the resulting solution were then incubated with AFP antigen. MPI measurements were done using the preclinical MPI scanner (Bruker Biospin MRI GmbH) and the multicolor method was used for image reconstruction. Results: In multicolor MPI images the nanoparticles incubated only with BSA were clearly distinguished from nanoparticles incubated with BSA and AFP antigens. Conclusion: Tomographic imaging of human tumor marker Alpha-1-Fetoprotein is possible using AFP antibody conjugated iron oxide nanoparticles in presence of BSA. This opens interesting perspectives for cancer diagnosis.Keywords: noninvasive imaging, tumor antigens, antibody conjugated iron oxide nanoparticles, multicolor magnetic particle imaging, cancer diagnosis
Procedia PDF Downloads 29726295 Different Data-Driven Bivariate Statistical Approaches to Landslide Susceptibility Mapping (Uzundere, Erzurum, Turkey)
Authors: Azimollah Aleshzadeh, Enver Vural Yavuz
Abstract:
The main goal of this study is to produce landslide susceptibility maps using different data-driven bivariate statistical approaches; namely, entropy weight method (EWM), evidence belief function (EBF), and information content model (ICM), at Uzundere county, Erzurum province, in the north-eastern part of Turkey. Past landslide occurrences were identified and mapped from an interpretation of high-resolution satellite images, and earlier reports as well as by carrying out field surveys. In total, 42 landslide incidence polygons were mapped using ArcGIS 10.4.1 software and randomly split into a construction dataset 70 % (30 landslide incidences) for building the EWM, EBF, and ICM models and the remaining 30 % (12 landslides incidences) were used for verification purposes. Twelve layers of landslide-predisposing parameters were prepared, including total surface radiation, maximum relief, soil groups, standard curvature, distance to stream/river sites, distance to the road network, surface roughness, land use pattern, engineering geological rock group, topographical elevation, the orientation of slope, and terrain slope gradient. The relationships between the landslide-predisposing parameters and the landslide inventory map were determined using different statistical models (EWM, EBF, and ICM). The model results were validated with landslide incidences, which were not used during the model construction. In addition, receiver operating characteristic curves were applied, and the area under the curve (AUC) was determined for the different susceptibility maps using the success (construction data) and prediction (verification data) rate curves. The results revealed that the AUC for success rates are 0.7055, 0.7221, and 0.7368, while the prediction rates are 0.6811, 0.6997, and 0.7105 for EWM, EBF, and ICM models, respectively. Consequently, landslide susceptibility maps were classified into five susceptibility classes, including very low, low, moderate, high, and very high. Additionally, the portion of construction and verification landslides incidences in high and very high landslide susceptibility classes in each map was determined. The results showed that the EWM, EBF, and ICM models produced satisfactory accuracy. The obtained landslide susceptibility maps may be useful for future natural hazard mitigation studies and planning purposes for environmental protection.Keywords: entropy weight method, evidence belief function, information content model, landslide susceptibility mapping
Procedia PDF Downloads 12726294 Two Cases of VACTERL Association in Pregnancy with Lymphocyte Therapy
Authors: Seyed Mazyar Mortazavi, Masod Memari, Hasan Ali Ahmadi, Zhaleh Abed
Abstract:
Introduction: VACTERL association is a rare disorder with various congenital malformations. The aetiology remains unknown. Combination of at least three congenital anomalies of the following criteria is required for diagnosis: vertebral defects, anal atresia, cardiac anomalies, tracheo-esophageal fistula, renal anomalies, and limb defects. Case presentation: The first case was 1-day old male neonate with multiple congenital anomalies was bore from 28 years old mother. The mother had history of pregnancy with lymphocyte therapy. His anomalies included: defects in thoracic and lumbar vertebral, anal atresia, bilateral hydronephrosis, atrial septal defect, and lower limb abnormality. Other anomalies were cryptorchidism and nasal canal narrowing. The second case was born with 32 weeks gestational age from mother with history of pregnancy with lymphocyte therapy. He had thoracic vertebral defect, cardiac anomalies and renal defect. Conclusion: diagnosis based on clinical finding is VACTERL association. Early diagnosis is very important to investigation and treatment of other coexistence anomalies. VACTERL association in mothers with history of pregnancy with lymphocyte therapy has suggested possibly of relationship between VACTERL association and this method of pregnancy.Keywords: anal atresia, tracheo-esophageal fistula, atrial septal defect, lymphocyte therapy
Procedia PDF Downloads 44626293 An Audit on the Role of Sentinel Node Biopsy in High-Risk Ductal Carcinoma in Situ and Intracystic Papillary Carcinoma
Authors: M. Sulieman, H. Arabiyat, H. Ali, K. Potiszil, I. Abbas, R. English, P. King, I. Brown, P. Drew
Abstract:
Introduction: The incidence of breast ductal Carcinoma in Situ (DCIS) has been increasing; it currently represents up 20-25% of all breast carcinomas. Some aspects of DCIS management are still controversial, mainly due to the heterogeneity of its clinical presentation and of its biological and pathological characteristics. In DCIS, histological diagnosis obtained preoperatively, carries the risk of sampling error if the presence of invasive cancer is subsequently diagnosed. The mammographic extent over than 4–5 cm and the presence of architectural distortion, focal asymmetric density or mass on mammography are proven important risk factors of preoperative histological under staging. Intracystic papillary cancer (IPC) is a rare form of breast carcinoma. Despite being previously compared to DCIS it has been shown to present histologically with invasion of the basement membrane and even metastasis. SLNB – Carries the risk of associated comorbidity that should be considered when planning surgery for DCIS and IPC. Objectives: The aim of this Audit was to better define a ‘high risk’ group of patients with pre-op diagnosis of non-invasive cancer undergoing breast conserving surgery, who would benefit from sentinel node biopsy. Method: Retrospective data collection of all patients with ductal carcinoma in situ over 5 years. 636 patients identified, and after exclusion criteria applied: 394 patients were included. High risk defined as: Extensive micro-calcification >40mm OR any mass forming DCIS. IPC: Winpath search from for the term ‘papillary carcinoma’ in any breast specimen for 5 years duration;.29 patients were included in this group. Results: DCIS: 188 deemed high risk due to >40mm calcification or a mass forming (radiological or palpable) 61% of those had a mastectomy and 32% BCS. Overall, in that high-risk group - the number with invasive disease was 38%. Of those high-risk DCIS pts 85% had a SLN - 80% at the time of surgery and 5% at a second operation. For the BCS patients - 42% had SLN at time of surgery and 13% (8 patients) at a second operation. 15 (7.9%) pts in the high-risk group had a positive SLNB, 11 having a mastectomy and 4 having BCS. IPC: The provisional diagnosis of encysted papillary carcinoma is upgraded to an invasive carcinoma on final histology in around a third of cases. This has may have implications when deciding whether to offer sentinel node removal at the time of therapeutic surgery. Conclusions: We have defined a ‘high risk’ group of pts with pre-op diagnosis of non-invasive cancer undergoing BCS, who would benefit from SLNB at the time of the surgery. In patients with high-risk features; the risk of invasive disease is up to 40% but the risk of nodal involvement is approximately 8%. The risk of morbidity from SLN is up to about 5% especially the risk of lymphedema.Keywords: breast ductal carcinoma in Situ (DCIS), intracystic papillary carcinoma (IPC), sentinel node biopsy (SLNB), high-risk, non-invasive, cancer disease
Procedia PDF Downloads 10426292 Multiple Fault Detection and Classification in a Coupled Motor with Rotor Using Artificial Neural Network
Authors: Mehrdad Nouri Khajavi, Gollamhassan Payganeh, Mohsen Fallah Tafti
Abstract:
Fault diagnosis is an important aspect of maintaining rotating machinery health and increasing productivity. Many researches has been done in this regards. Many faults such as unbalance, misalignment, looseness, bearing faults, etc. have been considered and diagnosed with different techniques. Most of the researches in fault diagnosis of rotating machinery deal with single fault. Where as in reality faults usually occur simultaneously and it is, therefore, necessary to recognize them at the same time. In this research, two of the most common faults namely unbalance and misalignment have been considered simultaneously with different intensity and then identified and classified with the use of Multi-Layer Perception Neural Network (MLPNN). Processed Vibration signals are used as the input to the MLPNN, and the class of mixed unbalancy, and misalignment is the output of the NN.Keywords: unbalance, parallel misalignment, combined faults, vibration signals
Procedia PDF Downloads 34526291 Modelling High-Frequency Crude Oil Dynamics Using Affine and Non-Affine Jump-Diffusion Models
Authors: Katja Ignatieva, Patrick Wong
Abstract:
We investigated the dynamics of high frequency energy prices, including crude oil and electricity prices. The returns of underlying quantities are modelled using various parametric models such as stochastic framework with jumps and stochastic volatility (SVCJ) as well as non-parametric alternatives, which are purely data driven and do not require specification of the drift or the diffusion coefficient function. Using different statistical criteria, we investigate the performance of considered parametric and nonparametric models in their ability to forecast price series and volatilities. Our models incorporate possible seasonalities in the underlying dynamics and utilise advanced estimation techniques for the dynamics of energy prices.Keywords: stochastic volatility, affine jump-diffusion models, high frequency data, model specification, markov chain monte carlo
Procedia PDF Downloads 9326290 The Types of Collaboration Models Driven by Public Art Establishment–Case Study of Taichung City
Authors: Cheng-Lung Yu, Ying-His Liao
Abstract:
Some evidence show that public art accelerates local economic growth. Even local governments award the collaboration of public-private partnership to sustain the creation of public art for urban economic development. Through the public-private partnership of public art establishment it is obvious that public construction projects have been led by the governmental policy yet the private developers have played crucial roles to drive the innovative business models such as tourism investment, real estate value up and community participation. This study shows that the types of collaboration have been driven by Taichung city governmental policy from the regulation of public art establishment in the past three years. Through some cases empirical analyzes the authors discover the trends concerning the public art development to support local economic growth in Taiwan.Keywords: public art, public art establishment regulation, construction management, urban governance
Procedia PDF Downloads 1926289 Vision-Based Daily Routine Recognition for Healthcare with Transfer Learning
Authors: Bruce X. B. Yu, Yan Liu, Keith C. C. Chan
Abstract:
We propose to record Activities of Daily Living (ADLs) of elderly people using a vision-based system so as to provide better assistive and personalization technologies. Current ADL-related research is based on data collected with help from non-elderly subjects in laboratory environments and the activities performed are predetermined for the sole purpose of data collection. To obtain more realistic datasets for the application, we recorded ADLs for the elderly with data collected from real-world environment involving real elderly subjects. Motivated by the need to collect data for more effective research related to elderly care, we chose to collect data in the room of an elderly person. Specifically, we installed Kinect, a vision-based sensor on the ceiling, to capture the activities that the elderly subject performs in the morning every day. Based on the data, we identified 12 morning activities that the elderly person performs daily. To recognize these activities, we created a HARELCARE framework to investigate into the effectiveness of existing Human Activity Recognition (HAR) algorithms and propose the use of a transfer learning algorithm for HAR. We compared the performance, in terms of accuracy, and training progress. Although the collected dataset is relatively small, the proposed algorithm has a good potential to be applied to all daily routine activities for healthcare purposes such as evidence-based diagnosis and treatment.Keywords: daily activity recognition, healthcare, IoT sensors, transfer learning
Procedia PDF Downloads 12626288 Theoretical and ML-Driven Identification of a Mispriced Credit Risk
Authors: Yuri Katz, Kun Liu, Arunram Atmacharan
Abstract:
Due to illiquidity, mispricing on Credit Markets is inevitable. This creates huge challenges to banks and investors as they seek to find new ways of risk valuation and portfolio management in a post-credit crisis world. Here, we analyze the difference in behavior of the spread-to-maturity in investment and high-yield categories of US corporate bonds between 2014 and 2023. Deviation from the theoretical dependency of this measure in the universe under study allows to identify multiple cases of mispriced credit risk. Remarkably, we observe mispriced bonds in both categories of credit ratings. This identification is supported by the application of the state-of-the-art machine learning model in more than 90% of cases. Noticeably, the ML-driven model-based forecasting of a category of bond’s credit ratings demonstrate an excellent out-of-sample accuracy (AUC = 98%). We believe that these results can augment conventional valuations of credit portfolios.Keywords: credit risk, credit ratings, bond pricing, spread-to-maturity, machine learning
Procedia PDF Downloads 7126287 Information Visualization Methods Applied to Nanostructured Biosensors
Authors: Osvaldo N. Oliveira Jr.
Abstract:
The control of molecular architecture inherent in some experimental methods to produce nanostructured films has had great impact on devices of various types, including sensors and biosensors. The self-assembly monolayers (SAMs) and the electrostatic layer-by-layer (LbL) techniques, for example, are now routinely used to produce tailored architectures for biosensing where biomolecules are immobilized with long-lasting preserved activity. Enzymes, antigens, antibodies, peptides and many other molecules serve as the molecular recognition elements for detecting an equally wide variety of analytes. The principles of detection are also varied, including electrochemical methods, fluorescence spectroscopy and impedance spectroscopy. In this presentation an overview will be provided of biosensors made with nanostructured films to detect antibodies associated with tropical diseases and HIV, in addition to detection of analytes of medical interest such as cholesterol and triglycerides. Because large amounts of data are generated in the biosensing experiments, use has been made of computational and statistical methods to optimize performance. Multidimensional projection techniques such as Sammon´s mapping have been shown more efficient than traditional multivariate statistical analysis in identifying small concentrations of anti-HIV antibodies and for distinguishing between blood serum samples of animals infected with two tropical diseases, namely Chagas´ disease and Leishmaniasis. Optimization of biosensing may include a combination of another information visualization method, the Parallel Coordinate technique, with artificial intelligence methods in order to identify the most suitable frequencies for reaching higher sensitivity using impedance spectroscopy. Also discussed will be the possible convergence of technologies, through which machine learning and other computational methods may be used to treat data from biosensors within an expert system for clinical diagnosis.Keywords: clinical diagnosis, information visualization, nanostructured films, layer-by-layer technique
Procedia PDF Downloads 32826286 Prediction of Solidification Behavior of Al Alloy in a Cube Mold Cavity
Authors: N. P. Yadav, Deepti Verma
Abstract:
This paper focuses on the mathematical modeling for solidification of Al alloy in a cube mould cavity to study the solidification behavior of casting process. The parametric investigation of solidification process inside the cavity was performed by using computational solidification/melting model coupled with Volume of fluid (VOF) model. The implicit filling algorithm is used in this study to understand the overall process from the filling stage to solidification in a model metal casting process. The model is validated with past studied at same conditions. The solidification process are analyzed by including the effect of pouring velocity and temperature of liquid metal, effect of wall temperature as well natural convection from the wall and geometry of the cavity. These studies show the possibility of various defects during solidification process.Keywords: buoyancy driven flow, natural convection driven flow, residual flow, secondary flow, volume of fluid
Procedia PDF Downloads 41326285 The Effects of Plantation Size and Internal Transport on Energy Efficiency of Biofuel Production
Authors: Olga Orynycz, Andrzej Wasiak
Abstract:
Mathematical model describing energetic efficiency (defined as a ratio of energy obtained in the form of biofuel to the sum of energy inputs necessary to facilitate production) of agricultural subsystem as a function of technological parameters was developed. Production technology is characterized by parameters of machinery, topological characteristics of the plantation as well as transportation routes inside and outside of plantation. The relationship between the energetic efficiency of agricultural and industrial subsystems is also derived. Due to the assumed large area of the individual field, the operations last for several days increasing inter-fields routes because of several returns. The total distance driven outside of the fields is, however, small as compared to the distance driven inside of the fields. This results in small energy consumption during inter-fields transport that, however, causes a substantial decrease of the energetic effectiveness of the whole system.Keywords: biofuel, energetic efficiency, EROEI, mathematical modelling, production system
Procedia PDF Downloads 33926284 Classification of Potential Biomarkers in Breast Cancer Using Artificial Intelligence Algorithms and Anthropometric Datasets
Authors: Aref Aasi, Sahar Ebrahimi Bajgani, Erfan Aasi
Abstract:
Breast cancer (BC) continues to be the most frequent cancer in females and causes the highest number of cancer-related deaths in women worldwide. Inspired by recent advances in studying the relationship between different patient attributes and features and the disease, in this paper, we have tried to investigate the different classification methods for better diagnosis of BC in the early stages. In this regard, datasets from the University Hospital Centre of Coimbra were chosen, and different machine learning (ML)-based and neural network (NN) classifiers have been studied. For this purpose, we have selected favorable features among the nine provided attributes from the clinical dataset by using a random forest algorithm. This dataset consists of both healthy controls and BC patients, and it was noted that glucose, BMI, resistin, and age have the most importance, respectively. Moreover, we have analyzed these features with various ML-based classifier methods, including Decision Tree (DT), K-Nearest Neighbors (KNN), eXtreme Gradient Boosting (XGBoost), Logistic Regression (LR), Naive Bayes (NB), and Support Vector Machine (SVM) along with NN-based Multi-Layer Perceptron (MLP) classifier. The results revealed that among different techniques, the SVM and MLP classifiers have the most accuracy, with amounts of 96% and 92%, respectively. These results divulged that the adopted procedure could be used effectively for the classification of cancer cells, and also it encourages further experimental investigations with more collected data for other types of cancers.Keywords: breast cancer, diagnosis, machine learning, biomarker classification, neural network
Procedia PDF Downloads 12626283 AI Software Algorithms for Drivers Monitoring within Vehicles Traffic - SiaMOTO
Authors: Ioan Corneliu Salisteanu, Valentin Dogaru Ulieru, Mihaita Nicolae Ardeleanu, Alin Pohoata, Bogdan Salisteanu, Stefan Broscareanu
Abstract:
Creating a personalized statistic for an individual within the population using IT systems, based on the searches and intercepted spheres of interest they manifest, is just one 'atom' of the artificial intelligence analysis network. However, having the ability to generate statistics based on individual data intercepted from large demographic areas leads to reasoning like that issued by a human mind with global strategic ambitions. The DiaMOTO device is a technical sensory system that allows the interception of car events caused by a driver, positioning them in time and space. The device's connection to the vehicle allows the creation of a source of data whose analysis can create psychological, behavioural profiles of the drivers involved. The SiaMOTO system collects data from many vehicles equipped with DiaMOTO, driven by many different drivers with a unique fingerprint in their approach to driving. In this paper, we aimed to explain the software infrastructure of the SiaMOTO system, a system designed to monitor and improve driver driving behaviour, as well as the criteria and algorithms underlying the intelligent analysis process.Keywords: artificial intelligence, data processing, driver behaviour, driver monitoring, SiaMOTO
Procedia PDF Downloads 7326282 Light Car Assisted by PV Panels
Authors: Soufiane Benoumhani, Nadia Saifi, Boubekeur Dokkar, Mohamed Cherif Benzid
Abstract:
This work presents the design and simulation of electric equipment for a hybrid solar vehicle. The new drive train of this vehicle is a parallel hybrid system which means a vehicle driven by a great percentage of an internal combustion engine with 49.35 kW as maximal power and electric motor only as assistance when is needed. This assistance is carried out on the rear axle by a single electric motor of 7.22 kW as nominal power. The motor is driven by 12 batteries connecting in series, which are charged by three PV panels (300 W) installed on the roof and hood of the vehicle. The individual components are modeled and simulated by using the Matlab Simulink environment. The whole system is examined under different load conditions. The reduction of CO₂ emission is obtained by reducing fuel consumption. With the use of this hybrid system, fuel consumption can be reduced from 6.74 kg/h to 5.56 kg/h when the electric motor works at 100 % of its power. The net benefit of the system reaches 1.18 kg/h as fuel reduction at high values of power and torque.Keywords: light car, hybrid system, PV panel, electric motor
Procedia PDF Downloads 11526281 A Qualitative Study of Parents' Recommendations for Improving the Notification Process and Communication between Health Professionals and Families for New Diagnosis of Cystic Fibrosis
Authors: Mohammad S. Razai, Jan Williams, Rachel Nestel, Dermot Dalton
Abstract:
Purpose: This descriptive qualitative study aimed to obtain parents recommendations for improving the notification process and communication of positive newborn screening result for cystic fibrosis (CF). Methods: Thematic analysis of semi-structured open-ended interviews with 11 parents of 7 children with confirmed diagnosis of CF between 2 months — 2 years of age. Results: Parents preferred face to face disclosure of positive NBS results by a pediatrician with CF professional qualification. They trusted a pediatrician more than any other professional in providing accurate, credible and comprehensive information about the diagnosis and its implications. Parents recommended that health professionals be knowledgeable and provide clear, succinct and understandable information. Providers should also explore parents concerns and acknowledge feelings and emotions. Most parents reported that they preferred to be notified immediately as soon as the results were available. Several parents preferred to be told once the diagnosis was certain. Most parents regarded open access to CF team as the most significant part of care coordination. In addition to health professionals, most parents used internet as an important source of information, interaction and exchange of experiences. Most parents also used social networking sites such as Facebook groups and smart phone apps. Conclusion: This study provides significant new evidence from parental perspective in emphasizing the pivotal role of good communication skills deployed by a knowledgeable CF specialist in person. Parents use of social media and internet has replaced some traditional methods of information exchange and may reduce the need for professional input for newly diagnosed CF patients.Keywords: care coordination, cystic fibrosis, newborn screening, notification process, parental preferences, professional-paren communication
Procedia PDF Downloads 39526280 Enhancing Temporal Extrapolation of Wind Speed Using a Hybrid Technique: A Case Study in West Coast of Denmark
Authors: B. Elshafei, X. Mao
Abstract:
The demand for renewable energy is significantly increasing, major investments are being supplied to the wind power generation industry as a leading source of clean energy. The wind energy sector is entirely dependable and driven by the prediction of wind speed, which by the nature of wind is very stochastic and widely random. This s0tudy employs deep multi-fidelity Gaussian process regression, used to predict wind speeds for medium term time horizons. Data of the RUNE experiment in the west coast of Denmark were provided by the Technical University of Denmark, which represent the wind speed across the study area from the period between December 2015 and March 2016. The study aims to investigate the effect of pre-processing the data by denoising the signal using empirical wavelet transform (EWT) and engaging the vector components of wind speed to increase the number of input data layers for data fusion using deep multi-fidelity Gaussian process regression (GPR). The outcomes were compared using root mean square error (RMSE) and the results demonstrated a significant increase in the accuracy of predictions which demonstrated that using vector components of the wind speed as additional predictors exhibits more accurate predictions than strategies that ignore them, reflecting the importance of the inclusion of all sub data and pre-processing signals for wind speed forecasting models.Keywords: data fusion, Gaussian process regression, signal denoise, temporal extrapolation
Procedia PDF Downloads 13126279 A Grounded Theory on Marist Spirituality/Charism from the Perspective of the Lay Marists in the Philippines
Authors: Nino M. Pizarro
Abstract:
To the author’s knowledge, despite the written documents about Marist spirituality/charism, nothing has been done concerning a clear theoretical framework that highlights Marist spirituality/charism from the perspective or lived experience of the lay Marists of St. Marcellin Champagnat. The participants of the study are the lay Marist - educators who are from Marist Schools in the Philippines. Since the study would like to find out the respondents’ own concepts and meanings about Marist spirituality/charism, qualitative methodology is considered the approach to be used in the study. In particular, the study will use the qualitative methods of Barney Glaser. The theory will be generated systematically from data collection, coding and analyzing through memoing, theoretical sampling, sorting and writing and using the constant comparative method. The data collection method that will be employed in this grounded theory research is the in-depth interview that is semi-structured and participant driven. Data collection will be done through snowball sampling that is purposive. The study is considering to come up with a theoretical framework that will help the lay Marists to deepen their understanding of the Marist spirituality/charism and their vocation as lay partners of the Marist Brothers of the Schools.Keywords: grounded theory, Lay Marists, lived experience, Marist spirituality/charism
Procedia PDF Downloads 30126278 Managing the Cloud Procurement Process: Findings from a Case Study
Authors: Andreas Jede, Frank Teuteberg
Abstract:
Cloud computing (CC) has already gained overall appreciation in research and practice. Whereas the willingness to integrate cloud services in various IT environments is still unbroken, the previous CC procurement processes run mostly in an unorganized and non-standardized way. In practice, a sufficiently specific, yet applicable business process for the important acquisition phase is often lacking. And research does not appropriately remedy this deficiency yet. Therefore, this paper introduces a field-tested approach for CC procurement. Based on an extensive literature review and augmented by expert interviews, we designed a model that is validated and further refined through an in-depth real-life case study. For the detailed process description, we apply the event-driven process chain notation (EPC). The gained valuable insights into the case study may help CC research to shift to a more socio-technical area. For practice, next to giving useful organizational instructions we will provide extended checklists and lessons learned.Keywords: cloud procurement process, IT-organization, event-driven process chain, in-depth case study
Procedia PDF Downloads 38726277 Application of Data Driven Based Models as Early Warning Tools of High Stream Flow Events and Floods
Authors: Mohammed Seyam, Faridah Othman, Ahmed El-Shafie
Abstract:
The early warning of high stream flow events (HSF) and floods is an important aspect in the management of surface water and rivers systems. This process can be performed using either process-based models or data driven-based models such as artificial intelligence (AI) techniques. The main goal of this study is to develop efficient AI-based model for predicting the real-time hourly stream flow (Q) and apply it as early warning tool of HSF and floods in the downstream area of the Selangor River basin, taken here as a paradigm of humid tropical rivers in Southeast Asia. The performance of AI-based models has been improved through the integration of the lag time (Lt) estimation in the modelling process. A total of 8753 patterns of Q, water level, and rainfall hourly records representing one-year period (2011) were utilized in the modelling process. Six hydrological scenarios have been arranged through hypothetical cases of input variables to investigate how the changes in RF intensity in upstream stations can lead formation of floods. The initial SF was changed for each scenario in order to include wide range of hydrological situations in this study. The performance evaluation of the developed AI-based model shows that high correlation coefficient (R) between the observed and predicted Q is achieved. The AI-based model has been successfully employed in early warning throughout the advance detection of the hydrological conditions that could lead to formations of floods and HSF, where represented by three levels of severity (i.e., alert, warning, and danger). Based on the results of the scenarios, reaching the danger level in the downstream area required high RF intensity in at least two upstream areas. According to results of applications, it can be concluded that AI-based models are beneficial tools to the local authorities for flood control and awareness.Keywords: floods, stream flow, hydrological modelling, hydrology, artificial intelligence
Procedia PDF Downloads 24326276 Urinary Exosome miR-30c-5p as a Biomarker for Early-Stage Clear Cell Renal Cell Carcinoma
Authors: Shangqing Song, Bin Xu, Yajun Cheng, Zhong Wang
Abstract:
miRNAs derived from exosomes exist in a body fluid such as urine were regarded as potential biomarkers for various human cancers diagnosis and prognosis, as mature miRNAs can be steadily preserved by exosomes. However, its potential value in clear cell renal cell carcinoma (ccRCC) diagnosis and prognosis remains unclear. In the present study, differentially expressed miRNAs from urinal exosomes were identified by next-generation sequencing (NGS) technology. The 16 differentially expressed miRNAs were identified between ccRCC patients and healthy donors. To explore the specific diagnosis biomarker of ccRCC, we validated these urinary exosomes from 70 early-stage renal cancer patients, 30 healthy people and other urinary system cancers, including 30 early-stage prostate cancer patients and 30 early-stage bladder cancer patients by qRT-PCR. The results showed that urinary exosome miR-30c-5p could be stably amplified and meanwhile the expression of miR-30c-5p has no significant difference between other urinary system cancers and healthy control, however, expression level of miR-30c-5p in urinary exosomal of ccRCC patients was lower than healthy people and receiver operation characterization (ROC) curve showed that the area under the curve (AUC) values was 0.8192 (95% confidence interval was 0.7388-0.8996, P= 0.0000). In addition, up-regulating miR-30c-5p expression could inhibit renal cell carcinoma cells growth. Lastly, HSP5A was found as a direct target gene of miR-30c-5p. HSP5A depletion reversed the promoting effect of ccRCC growth casued by miR-30c-5p inhibitor, respectively. In conclusion, this study demonstrated that urinary exosomal miR-30c-5p is readily accessible as diagnosis biomarker of early-stage ccRCC, and miR-30c-5p might modulate the expression of HSPA5, which correlated with the progression of ccRCC.Keywords: clear cell renal cell carcinoma, exosome, HSP5A, miR-30c-5p
Procedia PDF Downloads 25326275 Comparison between Transient Elastography (FibroScan) and Liver Biopsy for Diagnosis of Hepatic Fibrosis in Chronic Hepatitis C Genotype 4
Authors: Gamal Shiha, Seham Seif, Shahera Etreby, Khaled Zalata, Waleed Samir
Abstract:
Background: Transient Elastography (TE; FibroScan®) is a non-invasive technique to assess liver fibrosis. Aim: To compare TE and liver biopsy in hepatitis C virus (HCV) patients, genotype IV and evaluate the effect of steatosis and schistosomiasis on FibroScan. Methods: The fibrosis stage (METAVIR Score) TE, was assessed in 519 patients. The diagnostic performance of FibroScan is assessed by calculating the area under the receiver operating characteristic curves (AUROCs). Results: The cut-off value of ≥ F2 was 8.55 kPa, ≥ F3 was 10.2 kPa and cirrhosis = F4 was 16.3 kPa. The positive predictive value and negative predictive value were 70.1% and 81.7% for the diagnosis of ≥ F2, 62.6% and 96.22% for F ≥ 3, and 27.7% and 100% for F4. No significant difference between schistosomiasis, steatosis degree and FibroScan measurements. Conclusion: Fibroscan could accurately predict liver fibrosis.Keywords: chronic hepatitis C, FibroScan, liver biopsy, liver fibrosis
Procedia PDF Downloads 40226274 Identifying Autism Spectrum Disorder Using Optimization-Based Clustering
Authors: Sharifah Mousli, Sona Taheri, Jiayuan He
Abstract:
Autism spectrum disorder (ASD) is a complex developmental condition involving persistent difficulties with social communication, restricted interests, and repetitive behavior. The challenges associated with ASD can interfere with an affected individual’s ability to function in social, academic, and employment settings. Although there is no effective medication known to treat ASD, to our best knowledge, early intervention can significantly improve an affected individual’s overall development. Hence, an accurate diagnosis of ASD at an early phase is essential. The use of machine learning approaches improves and speeds up the diagnosis of ASD. In this paper, we focus on the application of unsupervised clustering methods in ASD as a large volume of ASD data generated through hospitals, therapy centers, and mobile applications has no pre-existing labels. We conduct a comparative analysis using seven clustering approaches such as K-means, agglomerative hierarchical, model-based, fuzzy-C-means, affinity propagation, self organizing maps, linear vector quantisation – as well as the recently developed optimization-based clustering (COMSEP-Clust) approach. We evaluate the performances of the clustering methods extensively on real-world ASD datasets encompassing different age groups: toddlers, children, adolescents, and adults. Our experimental results suggest that the COMSEP-Clust approach outperforms the other seven methods in recognizing ASD with well-separated clusters.Keywords: autism spectrum disorder, clustering, optimization, unsupervised machine learning
Procedia PDF Downloads 10626273 Big Data Analytics and Public Policy: A Study in Rural India
Authors: Vasantha Gouri Prathapagiri
Abstract:
Innovations in ICT sector facilitate qualitative life style for citizens across the globe. Countries that facilitate usage of new techniques in ICT, i.e., big data analytics find it easier to fulfil the needs of their citizens. Big data is characterised by its volume, variety, and speed. Analytics involves its processing in a cost effective way in order to draw conclusion for their useful application. Big data also involves into the field of machine learning, artificial intelligence all leading to accuracy in data presentation useful for public policy making. Hence using data analytics in public policy making is a proper way to march towards all round development of any country. The data driven insights can help the government to take important strategic decisions with regard to socio-economic development of her country. Developed nations like UK and USA are already far ahead on the path of digitization with the support of Big Data analytics. India is a huge country and is currently on the path of massive digitization being realised through Digital India Mission. Internet connection per household is on the rise every year. This transforms into a massive data set that has the potential to improvise the public services delivery system into an effective service mechanism for Indian citizens. In fact, when compared to developed nations, this capacity is being underutilized in India. This is particularly true for administrative system in rural areas. The present paper focuses on the need for big data analytics adaptation in Indian rural administration and its contribution towards development of the country on a faster pace. Results of the research focussed on the need for increasing awareness and serious capacity building of the government personnel working for rural development with regard to big data analytics and its utility for development of the country. Multiple public policies are framed and implemented for rural development yet the results are not as effective as they should be. Big data has a major role to play in this context as can assist in improving both policy making and implementation aiming at all round development of the country.Keywords: Digital India Mission, public service delivery system, public policy, Indian administration
Procedia PDF Downloads 15226272 Data Analytics of Electronic Medical Records Shows an Age-Related Differences in Diagnosis of Coronary Artery Disease
Authors: Maryam Panahiazar, Andrew M. Bishara, Yorick Chern, Roohallah Alizadehsani, Dexter Hadleye, Ramin E. Beygui
Abstract:
Early detection plays a crucial role in enhancing the outcome for a patient with coronary artery disease (CAD). We utilized a big data analytics platform on ~23,000 patients with CAD from a total of 960,129 UCSF patients in 8 years. We traced the patients from their first encounter with a physician to diagnose and treat CAD. Characteristics such as demographic information, comorbidities, vital, lab tests, medications, and procedures are included. There are statistically significant gender-based differences in patients younger than 60 years old from the time of the first physician encounter to coronary artery bypass grafting (CABG) with a p-value=0.03. There are no significant differences between the patients between 60 and 80 years old (p-value=0.8) and older than 80 (p-value=0.4) with a 95% confidence interval. This recognition would affect significant changes in the guideline for referral of the patients for diagnostic tests expeditiously to improve the outcome by avoiding the delay in treatment.Keywords: electronic medical records, coronary artery disease, data analytics, young women
Procedia PDF Downloads 14326271 Graph Neural Network-Based Classification for Disease Prediction in Health Care Heterogeneous Data Structures of Electronic Health Record
Authors: Raghavi C. Janaswamy
Abstract:
In the healthcare sector, heterogenous data elements such as patients, diagnosis, symptoms, conditions, observation text from physician notes, and prescriptions form the essentials of the Electronic Health Record (EHR). The data in the form of clear text and images are stored or processed in a relational format in most systems. However, the intrinsic structure restrictions and complex joins of relational databases limit the widespread utility. In this regard, the design and development of realistic mapping and deep connections as real-time objects offer unparallel advantages. Herein, a graph neural network-based classification of EHR data has been developed. The patient conditions have been predicted as a node classification task using a graph-based open source EHR data, Synthea Database, stored in Tigergraph. The Synthea DB dataset is leveraged due to its closer representation of the real-time data and being voluminous. The graph model is built from the EHR heterogeneous data using python modules, namely, pyTigerGraph to get nodes and edges from the Tigergraph database, PyTorch to tensorize the nodes and edges, PyTorch-Geometric (PyG) to train the Graph Neural Network (GNN) and adopt the self-supervised learning techniques with the AutoEncoders to generate the node embeddings and eventually perform the node classifications using the node embeddings. The model predicts patient conditions ranging from common to rare situations. The outcome is deemed to open up opportunities for data querying toward better predictions and accuracy.Keywords: electronic health record, graph neural network, heterogeneous data, prediction
Procedia PDF Downloads 8126270 Software Assessment Using Ant Colony Optimization Algorithm
Authors: Saad M. Darwish
Abstract:
Recently, software quality issues have come to be seen as important subject as we see an enormous growth of agencies involved in software industries. However,these agencies cannot guarantee the quality of their products, thus leaving users in uncertainties. Software certification is the extension of quality by means that quality needs to be measured prior to certification granting process. This research participates in solving the problem of software assessment by proposing a model for assessment and certification of software product that uses a fuzzy inference engine to integrate both of process–driven and application-driven quality assurance strategies. The key idea of the on hand model is to improve the compactness and the interpretability of the model’s fuzzy rules via employing an ant colony optimization algorithm (ACO), which tries to find good rules description by dint of compound rules initially expressed with traditional single rules. The model has been tested by case study and the results have demonstrated feasibility and practicability of the model in a real environment.Keywords: optimization technique, quality assurance, software certification model, software assessment
Procedia PDF Downloads 479