Search results for: evolution algorithm

Authors: Jui-Chien Hsieh

Abstract:

Background:12-lead electrocardiography(ECG) is one of frequently-used tools to detect atrial fibrillation (AF), which might degenerate into life-threaten stroke, in clinical Practice. Based on this study, the AF detection by the clinically-used 12-lead ECG device has only 0.73~0.77 positive predictive value (ppv). Objective: It is on great demand to develop a new algorithm to improve the precision of AF detection using 12-lead ECG. Due to the progress on artificial intelligence (AI), we develop an ECG deep model that has the ability to recognize AF patterns and reduce false-positive errors. Methods: In this study, (1) 570-sample 12-lead ECG reports whose computer interpretation by the ECG device was AF were collected as the training dataset. The ECG reports were interpreted by 2 senior cardiologists, and confirmed that the precision of AF detection by the ECG device is 0.73.; (2) 88 12-lead ECG reports whose computer interpretation generated by the ECG device was AF were used as test dataset. Cardiologist confirmed that 68 cases of 88 reports were AF, and others were not AF. The precision of AF detection by ECG device is about 0.77; (3) A parallel 4-layer 1 dimensional convolutional neural network (CNN) was developed to identify AF based on limb-lead ECGs and chest-lead ECGs. Results: The results indicated that this model has better performance on AF detection than traditional computer interpretation of the ECG device in 88 test samples with 0.94 ppv, 0.98 sensitivity, 0.80 specificity. Conclusions: As compared to the clinical ECG device, this AI ECG model promotes the precision of AF detection from 0.77 to 0.94, and can generate impacts on clinical applications.

Keywords: 12-lead ECG, atrial fibrillation, deep learning, convolutional neural network

Procedia PDF Downloads 100

Authors: Ying Han, Weirong Chen, Qi Li

Abstract:

An energy management method based on equivalent hydrogen consumption minimum strategy is proposed in this paper aiming at the direct-current (DC) microgrid consisting of photovoltaic cells, fuel cells, energy storage devices, converters and DC loads. The rational allocation of fuel cells and battery devices is achieved by adopting equivalent minimum hydrogen consumption strategy with the full use of power generated by photovoltaic cells. Considering the balance of the battery’s state of charge (SOC), the optimal power of the battery under different SOC conditions is obtained and the reference output power of the fuel cell is calculated. And then a droop control method based on time-varying droop coefficient is proposed to realize the automatic charge and discharge control of the battery, balance the system power and maintain the bus voltage. The proposed control strategy is verified by RT-LAB hardware-in-the-loop simulation platform. The simulation results show that the designed control algorithm can realize the rational allocation of DC micro-grid energy and improve the stability of system.

Keywords: DC microgrid, equivalent minimum hydrogen consumption strategy, energy management, time-varying droop coefficient, droop control

Procedia PDF Downloads 287

Authors: Reza Alikhani

Abstract:

This research focuses on the establishment of horizontal cooperation among companies to enhance their operational efficiency and competitiveness. The study proposes an approach to horizontal collaboration, called coalition configuration, which involves partnering companies sharing distribution centers in a network design problem. The paper investigates which coalition should be formed in each distribution center to minimize the total cost of the network. Moreover, potential uncertainties, such as operational and disruption risks, are considered during the collaborative design phase. To address this problem, a two-stage robust optimization model for collaborative distribution network design under surging demand and facility disruptions is presented, along with a column-and-constraint generation algorithm to obtain exact solutions tailored to the proposed formulation. Extensive numerical experiments are conducted to analyze solutions obtained by the model in various scenarios, including decisions ranging from fully centralized to fully decentralized settings, collaborative versus non-collaborative approaches, and different amounts of uncertainty budgets. The results show that the coalition formation mechanism proposes some solutions that are competitive with the savings of the grand coalition. The research also highlights that collaboration increases network flexibility and resilience while reducing costs associated with demand and capacity uncertainties.

Keywords: logistics, warehouse sharing, robust facility location, collaboration for resilience

Procedia PDF Downloads 50

Authors: Loai AbdAllah, Mahmoud Kaiyal

Abstract:

Missing values in real-world datasets are a common problem. Many algorithms were developed to deal with this problem, most of them replace the missing values with a fixed value that was computed based on the observed values. In our work, we used a distance function based on Bhattacharyya distance to measure the distance between objects with missing values. Bhattacharyya distance, which measures the similarity of two probability distributions. The proposed distance distinguishes between known and unknown values. Where the distance between two known values is the Mahalanobis distance. When, on the other hand, one of them is missing the distance is computed based on the distribution of the known values, for the coordinate that contains the missing value. This method was integrated with Wikaya, a digital health company developing a platform that helps to improve prevention of chronic diseases such as diabetes and cancer. In order for Wikaya’s recommendation system to work distance between users need to be measured. Since there are missing values in the collected data, there is a need to develop a distance function distances between incomplete users profiles. To evaluate the accuracy of the proposed distance function in reflecting the actual similarity between different objects, when some of them contain missing values, we integrated it within the framework of k nearest neighbors (kNN) classifier, since its computation is based only on the similarity between objects. To validate this, we ran the algorithm over diabetes and breast cancer datasets, standard benchmark datasets from the UCI repository. Our experiments show that kNN classifier using our proposed distance function outperforms the kNN using other existing methods.

Keywords: missing values, incomplete data, distance, incomplete diabetes data

Procedia PDF Downloads 203

Authors: Muhtasim Shafi Kader, Fizar Ahmed, Annesha Acharjee

Abstract:

Machine learning and data mining are crucial in health care, as well as medical information and detection. Machine learning approaches are now being utilized to improve awareness of a variety of critical health issues, including diabetes detection, neuron cell tumor diagnosis, COVID 19 identification, and so on. Parkinson’s disease is basically a disease for our senior citizens in Bangladesh. Parkinson's Disease indications often seem progressive and get worst with time. People got affected trouble walking and communicating with the condition advances. Patients can also have psychological and social vagaries, nap problems, hopelessness, reminiscence loss, and weariness. Parkinson's disease can happen in both men and women. Though men are affected by the illness at a proportion that is around partial of them are women. In this research, we have to get out the accurate ML algorithm to find out the disease with a predictable dataset and the model of the following machine learning classifiers. Therefore, nine ML classifiers are secondhand to portion study to use machine learning approaches like as follows, Naive Bayes, Adaptive Boosting, Bagging Classifier, Decision Tree Classifier, Random Forest classifier, XBG Classifier, K Nearest Neighbor Classifier, Support Vector Machine Classifier, and Gradient Boosting Classifier are used.

Keywords: naive bayes, adaptive boosting, bagging classifier, decision tree classifier, random forest classifier, XBG classifier, k nearest neighbor classifier, support vector classifier, gradient boosting classifier

Procedia PDF Downloads 115

Authors: Ahmed E. Hodaib, Mohamed A. Hashem

Abstract:

In engineering applications, a design has to be as fully perfect as possible in some defined case. The designer has to overcome many challenges in order to reach the optimal solution to a specific problem. This process is called optimization. Generally, there is always a function called “objective function” that is required to be maximized or minimized by choosing input parameters called “degrees of freedom” within an allowed domain called “search space” and computing the values of the objective function for these input values. It becomes more complex when we have more than one objective for our design. As an example for Multi-Objective Optimization Problem (MOP): A structural design that aims to minimize weight and maximize strength. In such case, the Pareto Optimal Frontier (POF) is used, which is a curve plotting two objective functions for the best cases. At this point, a designer should make a decision to choose the point on the curve. Engineers use algorithms or iterative methods for optimization. In this paper, we will discuss the Evolutionary Algorithms (EA) which are widely used with Multi-objective Optimization Problems due to their robustness, simplicity, suitability to be coupled and to be parallelized. Evolutionary algorithms are developed to guarantee the convergence to an optimal solution. An EA uses mechanisms inspired by Darwinian evolution principles. Technically, they belong to the family of trial and error problem solvers and can be considered global optimization methods with a stochastic optimization character. The optimization is initialized by picking random solutions from the search space and then the solution progresses towards the optimal point by using operators such as Selection, Combination, Cross-over and/or Mutation. These operators are applied to the old solutions “parents” so that new sets of design variables called “children” appear. The process is repeated until the optimal solution to the problem is reached. Reliable and robust computational fluid dynamics solvers are nowadays commonly utilized in the design and analyses of various engineering systems, such as aircraft, turbo-machinery, and auto-motives. Coupling of Computational Fluid Dynamics “CFD” and Multi-Objective Evolutionary Algorithms “MOEA” has become substantial in aerospace engineering applications, such as in aerodynamic shape optimization and advanced turbo-machinery design.

Keywords: mathematical optimization, multi-objective evolutionary algorithms "MOEA", computational fluid dynamics "CFD", aerodynamic shape optimization

Procedia PDF Downloads 242

Authors: Panupong Makvichian

Abstract:

Global Navigation Satellite System (GNSS) is nowadays a common technology that improves navigation functions in our life. Additionally, GNSS is also being employed on behalf of an accurate atmospheric sensor these times. Meteorology is a practical application of GNSS, which is unnoticeable in the background of people’s life. GNSS Precise Point Positioning (PPP) is a positioning method that requires data from a single dual-frequency receiver and precise information about satellite positions and satellite clocks. In addition, careful attention to mitigate various error sources is required. All the above data are combined in a sophisticated mathematical algorithm. At this point, the research is going to demonstrate how GNSS and PPP method is capable to provide high-precision estimates, such as 3D positions or Zenith tropospheric delays (ZTDs). ZTDs combined with pressure and temperature information allows us to estimate the water vapor in the atmosphere as precipitable water vapor (PWV). If the process is replicated for a network of GNSS sensors, we can create thematic maps that allow extract water content information in any location within the network area. All of the above are possible thanks to the advances in GNSS data processing. Therefore, we are able to use GNSS data for climatic trend analysis and acquisition of the further knowledge about the atmospheric water content.

Keywords: GNSS, precise point positioning, Zenith tropospheric delays, precipitable water vapor

Procedia PDF Downloads 180

Authors: Juhee Lee, Yongjun Lee

Abstract:

In designing a low-energy-consuming buildings, the heat transfer through a large glass or wall becomes critical. Multiple layers of the window glasses and walls are employed for the high insulation. The gravity driven air flow between window glasses or wall layers is a natural heat convection phenomenon being a key of the heat transfer. For the first step of the natural heat transfer analysis, in this study the development and application of a finite volume method for the numerical computation of viscous incompressible flows is presented. It will become a part of the natural convection analysis with high-order scheme, multi-grid method, and dual-time step in the future. A finite volume method based on a fully-implicit second-order is used to discretize and solve the fluid flow on unstructured grids composed of arbitrary-shaped cells. The integrations of the governing equation are discretised in the finite volume manner using a collocated arrangement of variables. The convergence of the SIMPLE segregated algorithm for the solution of the coupled nonlinear algebraic equations is accelerated by using a sparse matrix solver such as BiCGSTAB. The method used in the present study is verified by applying it to some flows for which either the numerical solution is known or the solution can be obtained using another numerical technique available in the other researches. The accuracy of the method is assessed through the grid refinement.

Keywords: finite volume method, fluid flow, laminar flow, unstructured grid

Procedia PDF Downloads 267

Authors: Hao Wang, Shengchun Wang, Weidong Wang

Abstract:

On the influence of train vibration and environmental noise on the measurement of track wear, we proposed a method for automatic extraction of circular arc on the inner or outer side of the rail waist and achieved the high-precision registration of rail profile. Firstly, a polynomial fitting method based on truncated residual histogram was proposed to find the optimal fitting curve of the profile and reduce the influence of noise on profile curve fitting. Then, based on the curvature distribution characteristics of the fitting curve, the interval search algorithm based on dynamic window’s maximum curvature entropy was proposed to realize the automatic segmentation of small circular arc. At last, we fit two circle centers as matching reference points based on small circular arcs on both sides and realized the alignment from the measured profile to the standard designed profile. The static experimental results show that the mean and standard deviation of the method are controlled within 0.01mm with small measurement errors and high repeatability. The dynamic test also verified the repeatability of the method in the train-running environment, and the dynamic measurement deviation of rail wear is within 0.2mm with high repeatability.

Keywords: curvature entropy, profile registration, rail wear, structured light, train-running

Procedia PDF Downloads 243

Authors: Muhammad Ali

Abstract:

Cyber-attacks and anomaly detection on the Internet of Things (IoT) infrastructure is emerging concern in the domain of data-driven intrusion. Rapidly increasing IoT risk is now making headlines around the world. denial of service, malicious control, data type probing, malicious operation, DDos, scan, spying, and wrong setup are attacks and anomalies that can affect an IoT system failure. Everyone talks about cyber security, connectivity, smart devices, and real-time data extraction. IoT devices expose a wide variety of new cyber security attack vectors in network traffic. For further than IoT development, and mainly for smart and IoT applications, there is a necessity for intelligent processing and analysis of data. So, our approach is too secure. We train several machine learning models that have been compared to accurately predicting attacks and anomalies on IoT systems, considering IoT applications, with ANOVA-based feature selection with fewer prediction models to evaluate network traffic to help prevent IoT devices. The machine learning (ML) algorithms that have been used here are KNN, SVM, NB, D.T., and R.F., with the most satisfactory test accuracy with fast detection. The evaluation of ML metrics includes precision, recall, F1 score, FPR, NPV, G.M., MCC, and AUC & ROC. The Random Forest algorithm achieved the best results with less prediction time, with an accuracy of 99.98%.

Keywords: machine learning, analysis of variance, Internet of Thing, network security, intrusion detection

Procedia PDF Downloads 101

Authors: Sagri Sharma

Abstract:

Analysis of diseases integrating multi-factors increases the complexity of the problem and therefore, development of frameworks for the analysis of diseases is an issue that is currently a topic of intense research. Due to the inter-dependence of the various parameters, the use of traditional methodologies has not been very effective. Consequently, newer methodologies are being sought to deal with the problem. Supervised Learning Algorithms are commonly used for performing the prediction on previously unseen data. These algorithms are commonly used for applications in fields ranging from image analysis to protein structure and function prediction and they get trained using a known dataset to come up with a predictor model that generates reasonable predictions for the response to new data. Gene expression profiles generated by DNA analysis experiments can be quite complex since these experiments can involve hypotheses involving entire genomes. The application of well-known machine learning algorithm - Support Vector Machine - to analyze the expression levels of thousands of genes simultaneously in a timely, automated and cost effective way is thus used. The objectives to undertake the presented work are development of a methodology to identify genes relevant to Hepatocellular Carcinoma (HCC) from gene expression dataset utilizing supervised learning algorithms and statistical evaluations along with development of a predictive framework that can perform classification tasks on new, unseen data.

Keywords: artificial intelligence, biomarker, gene expression datasets, hepatocellular carcinoma, machine learning, supervised learning algorithms, support vector machine

Procedia PDF Downloads 414

Authors: Ahmad Shahin, Walid Moudani, Ali Bekraki

Abstract:

This research aims at presenting a predictive data mining model to handle an accurate diagnosis of acute appendicitis with patients for the purpose of maximizing the health service quality, minimizing morbidity/mortality, and reducing cost. However, acute appendicitis is the most common disease which requires timely accurate diagnosis and needs surgical intervention. Although the treatment of acute appendicitis is simple and straightforward, its diagnosis is still difficult because no single sign, symptom, laboratory or image examination accurately confirms the diagnosis of acute appendicitis in all cases. This contributes in increasing morbidity and negative appendectomy. In this study, the authors propose to generate an accurate model in prediction of patients with acute appendicitis which is based, firstly, on the segmentation technique associated to ABC algorithm to segment the patients; secondly, on applying fuzzy logic to process the massive volume of heterogeneous and noisy data (age, sex, fever, white blood cell, neutrophilia, CRP, urine, ultrasound, CT, appendectomy, etc.) in order to express knowledge and analyze the relationships among data in a comprehensive manner; and thirdly, on applying dynamic programming technique to reduce the number of data attributes. The proposed model is evaluated based on a set of benchmark techniques and even on a set of benchmark classification problems of osteoporosis, diabetes and heart obtained from the UCI data and other data sources.

Keywords: healthcare management, acute appendicitis, data mining, classification, decision tree

Procedia PDF Downloads 333

Authors: Kateryna Nykytchenko

Abstract:

Modern fiction and non-fiction writers commonly use their own lexical and stylistic devices to capture a reader’s attention and bring certain thoughts and feelings to his reader. Among such devices is the appearance of one of the neologic notions – individual author’s formations: occasionalisms or nonce words. To a significant extent, the host of examples of new words occurs in chick lit genre which has experienced exponential growth in recent years. Chick Lit is a new-millennial postfeminist fiction which focuses primarily on twenty- to thirtysomething middle-class women. It brings into focus the image of 'a new woman' of the 21st century who is always fallible, funny. This paper aims to investigate different types of occasional word-formation which reflect cognitive mechanisms of conveying women’s perception of the world. Chick lit novels of Irish author Marian Keyes present genuinely innovative mixture of forms, both literary and nonliterary which is displayed in different types of occasional word-formation processes such as blending, compounding, creative respelling, etc. Crossing existing mental and linguistic boundaries, adopting herself to new and overlapping linguistic spaces, chick lit author creates new words which demonstrate the result of development and progress of language and the relationship between language, thought and new reality, ultimately resulting in hybrid word-formation (e.g. affixation or pseudoborrowing). Moreover, this article attempts to present the main characteristics of chick-lit fiction genre with the help of the Marian Keyes’s novels and their influence on occasionalisms. There has been a lack of research concerning cognitive nature of occasionalisms. The current paper intends to account for occasional word-formation as a set of interconnected cognitive mechanisms, operations and procedures meld together to create a new word. The results of the generalized analysis solidify arguments that the kind of new knowledge an occasionalism manifests is inextricably linked with cognitive procedure underlying it, which results in corresponding type of word-formation processes. In addition, the findings of the study reveal that the necessity of creating occasionalisms in postmodern fiction novels arises from the need to write in a new way keeping up with a perpetually developing world, and thus the evolution of the speaker herself and her perception of the world.

Keywords: Chick Lit, occasionalism, occasional word-formation, cognitive linguistics

Procedia PDF Downloads 164

Authors: Firdaous Zair, Zoubir Elfelsoufi, Mohammed Fourka

Abstract:

The allocation of resources is an issue that is needed on the tactical and operational strategic plan. This work considers the allocation of resources in the case of pure players, manufacturers and Click & Mortars that have launched online sales. The aim is to improve the level of customer satisfaction and maintaining the benefits of e-retailer and of its cooperators and reducing costs and risks. Our contribution is a decision support system and tool for improving the allocation of resources in logistics chains e-commerce B2C context. We first modeled the B2C chain with all operations that integrates and possible scenarios since online retailers offer a wide selection of personalized service. The personalized services that online shopping companies offer to the clients can be embodied in many aspects, such as the customizations of payment, the distribution methods, and after-sales service choices. In addition, every aspect of customized service has several modes. At that time, we analyzed the optimization problems of supply chain resource allocation in customized online shopping service mode, which is different from the supply chain resource allocation under traditional manufacturing or service circumstances. Then we realized an optimization model and algorithm for the development based on the analysis of the allocation of the B2C supply chain resources. It is a multi-objective optimization that considers the collaboration of resources in operations, time and costs but also the risks and the quality of services as well as dynamic and uncertain characters related to the request.

Keywords: e-commerce, supply chain, B2C, optimisation, resource allocation

Procedia PDF Downloads 253

Authors: Bilge Ozel

Abstract:

Cities are high-complex living organisms and are subjects to continuous transformations produced by the stress that derives from changing conditions. Today the metropolises are seen like “development engines” of the countries and accordingly they become the centre of better living conditions that encourages demographic growth which constitutes the main reason of the changes. Indeed, the potential for economic advancement of the cities directly represents the economic status of their countries. The term of “resilience”, which sees the changes as natural processes and represents the flexibility and adaptability of the systems in the face of changing conditions, becomes a key concept for the development of urban transformation policies. The term of “resilience” derives from the Latin word ‘resilire’, which means ‘bounce’, ‘jump back’, refers to the ability of a system to withstand shocks and still maintain the basic characteristics. A resilient system does not only survive the potential risks and threats but also takes advantage of the positive outcomes of the perturbations and ensures adaptation to the new external conditions. When this understanding is taken into the urban context - or rather “urban resilience” - it delineates the capacity of cities to anticipate upcoming shocks and changes without undergoing major alterations in its functional, physical, socio-economic systems. Undoubtedly, the issue of coordinating the urban systems in a “resilient” form is a multidisciplinary and complex process as the cities are multi-layered and dynamic structures. The concept of “urban transformation” is first launched in Europe just after World War II. It has been applied through different methods such as renovation, revitalization, improvement and gentrification. These methods have been in continuous advancement by acquiring new meanings and trends over years. With the effects of neoliberal policies in the 1980s, the concept of urban transformation has been associated with economic objectives. Subsequently this understanding has been improved over time and had new orientations such as providing more social justice and environmental sustainability. The aim of this research is to identify the most applied urban transformation methods in Turkey and its main reasons of being selected. Moreover, investigating the lacking and limiting points of the urban transformation policies in the context of “urban resilience” in a comparative way with European interventions. The emblematic examples, which symbolize the breaking points of the recent evolution of urban transformation concepts in Europe and Turkey, are chosen and reviewed in a critical way.

Keywords: resilience, urban dynamics, urban resilience, urban transformation

Procedia PDF Downloads 252

Authors: Bingchun Liu, Pei-Chann Chang, Natasha Huang, Dun Li

Abstract:

Machine Learning and Data Mining are the two important tools for extracting useful information and knowledge from large datasets. In machine learning, classification is a wildly used technique to predict qualitative variables and is generally preferred over regression from an operational point of view. Due to the enormous increase in air pollution in various countries especially China, Air Quality Classification has become one of the most important topics in air quality research and modelling. This study aims at introducing a hybrid classification model based on information theory and Support Vector Machine (SVM) using the air quality data of four cities in China namely Beijing, Guangzhou, Shanghai and Tianjin from Jan 1, 2014 to April 30, 2016. China's Ministry of Environmental Protection has classified the daily air quality into 6 levels namely Serious Pollution, Severe Pollution, Moderate Pollution, Light Pollution, Good and Excellent based on their respective Air Quality Index (AQI) values. Using the information theory, information gain (IG) is calculated and feature selection is done for both categorical features and continuous numeric features. Then SVM Machine Learning algorithm is implemented on the selected features with cross-validation. The final evaluation reveals that the IG and SVM hybrid model performs better than SVM (alone), Artificial Neural Network (ANN) and K-Nearest Neighbours (KNN) models in terms of accuracy as well as complexity.

Keywords: machine learning, air quality classification, air quality index, information gain, support vector machine, cross-validation

Procedia PDF Downloads 218

Authors: Huzaifa Bilal

Abstract:

Russian wheat aphid (Diuraphis noxia, Kurdjumov) is considered an economically important wheat (Triticum aestivum L.) pest worldwide and in South Africa. The RWA damages wheat plants and reduces annual yields by more than 10%. Even though pest management by pesticides and resistance breeding is an attractive option, chemicals can cause harm to the environment. Furthermore, the evolution of resistance-breaking aphid biotypes has out-paced the release of resistant cultivars. An alternative strategy to reduce the impact of aphid damage on plants, such as priming, which sensitizes plants to respond effectively to subsequent attacks, is necessary. In this study, wheat plants at the seedling and flag leaf stages were primed by salicylic acid and isolate representative of two races of the leaf rust pathogen Puccinia triticina Eriks. (Pt), before RWA (South African RWA biotypes 1 and 4) infestation. Randomized complete block design experiments were conducted in the greenhouse to study plant-pest interaction in primed and non-primed plants. Analysis of induced aphid damage indicated salicylic acid differentially primed wheat cultivars for increased resistance to the RWASA biotypes. At the seedling stage, all cultivars were primed for enhanced resistance to RWASA1, while at the flag leaf stage, only PAN 3111, SST 356 and Makalote were primed for increased resistance. The Puccinia triticina efficaciously primed wheat cultivars for excellent resistance to RWASA1 at the seedling and flag leaf stages. However, Pt failed to enhance the four Lesotho cultivars' resistance to RWASA4 at the seedling stage and PAN 3118 at the flag leaf stage. The induced responses at the seedling and flag leaf stages were positively correlated in all the treatments. Primed plants induced high activity of antioxidant enzymes like peroxidase, ascorbate peroxidase and superoxide dismutase. High antioxidant activity indicates activation of resistant responses in primed plants (primed by salicylic acid and Puccina triticina). Isolates of avirulent Pt races can be a worthy priming agent for improved resistance to RWA infestation. Further confirmation of the priming effects needs to be evaluated at the field trials to investigate its application efficiency.

Keywords: Russian wheat aphis, salicylic acid, puccina triticina, priming

Procedia PDF Downloads 189

Authors: Mohamed Al-Badrashiny, Abdelghani Bellaachia

Abstract:

This paper presents a classifier ensemble approach for predicting the survivability of the breast cancer patients using the latest database version of the Surveillance, Epidemiology, and End Results (SEER) Program of the National Cancer Institute. The system consists of two main components; features selection and classifier ensemble components. The features selection component divides the features in SEER database into four groups. After that it tries to find the most important features among the four groups that maximizes the weighted average F-score of a certain classification algorithm. The ensemble component uses three different classifiers, each of which models different set of features from SEER through the features selection module. On top of them, another classifier is used to give the final decision based on the output decisions and confidence scores from each of the underlying classifiers. Different classification algorithms have been examined; the best setup found is by using the decision tree, Bayesian network, and Na¨ıve Bayes algorithms for the underlying classifiers and Na¨ıve Bayes for the classifier ensemble step. The system outperforms all published systems to date when evaluated against the exact same data of SEER (period of 1973-2002). It gives 87.39% weighted average F-score compared to 85.82% and 81.34% of the other published systems. By increasing the data size to cover the whole database (period of 1973-2014), the overall weighted average F-score jumps to 92.4% on the held out unseen test set.

Keywords: classifier ensemble, breast cancer survivability, data mining, SEER

Procedia PDF Downloads 304

Authors: Hugh Battye

Abstract:

In recent years, Muslim identity in China has strengthened against the backdrop of a worldwide Islamic revival. One discussion arising from this has been focused around the Hui, an ethnicity created by the Communist government in the 1950s covering the Chinese speaking 'Sino-Muslims' as opposed to those with their own language. While the term Hui in Chinese has traditionally meant 'Muslim', the strengthening of Hui identity in recent decades has led to a debate among scholars as to whether this identity is primarily ethnically or religiously driven. This article looks at the case of a mixed ethnic community in rural Gansu Province, Central Northwest China, which not only contains the official Hui ethnicity but also members of the smaller Muslim Salar and Bonan minority groups. In analyzing the close interaction between these groups, the paper will argue that, despite government attempts to promote the Hui as an ethnicity within its modern ethnic paradigm, in rural Gansu and the general region, Hui is still essentially seen as a religious identity. Having provided an overview of the historical evolution of the Hui ethnonym in China and presented the views of some of the important scholars involved in the discussion, the paper will then offer its findings based on participant observation and survey work in Gansu. The results will show that, firstly, for the local Muslims, religious identity clearly dominates ethnic identity. On the ground, the term Hui continues to be used as a catch-all term for Muslims, whether they belong to the official 'Hui' nationality or not, and against this backdrop, the ethnic importance of being 'Hui', 'Bonan' or 'Salar' within the Muslim community itself is by contrast minimal. Secondly, however, this local Muslim solidarity is not at present pointing towards some kind of national pan-ethnic Islamic movement that could potentially set itself up in opposition to the Chinese government; rather it is better seen as part of an ongoing negotiation by local Muslims with the state in the context of its ascribed ethnic categories. The findings of this study in a region where many of the Muslims are more conservative in their beliefs is not necessarily replicated in other contexts, such as in urban areas and in eastern and southern China, and hence reification of the term Hui as one idea extending all across China should be avoided, whether in terms of a united religious 'ummah' or of a real or imagined 'ethnic group.' Rather, this localized case study seeks to demonstrate ways in which Muslims of rural Central Northwest China are 'being Hui,' as a contribution to the broader discussion on what it means to be Muslim and Chinese in the reform era.

Keywords: China, ethnicity, Hui, identity, Muslims

Procedia PDF Downloads 107

Authors: Laura M. Hovsepyan, Gayane S. Ghazaryan, Hasmik V. Zanginyan

Abstract:

Hypertension (HD) is the most common cardiovascular pathology that causes disability and mortality in the working population. Most often, heart failure (HF), which is based on myocardial remodeling, leads to death in hypertension. Recently, endothelial dysfunction (EDF) or a violation of the functional state of the vascular endothelium has been assigned a significant role in the structural changes in the myocardium and the occurrence of heart failure in patients with hypertension. It has now been established that tissues affected by inflammation form increased amounts of superoxide radical and NO, which play a significant role in the development and pathogenesis of various pathologies. They mediate inflammation, modify proteins and damage nucleic acids. The aim of this work was to study the processes of oxidative modification of proteins (OMP) and the production of nitric oxide in hypertension. In the experimental work, the blood of 30 donors and 33 patients with hypertension was used. For the quantitative determination of OMP products, the based on the reaction of the interaction of oxidized amino acid residues of proteins and 2,4-dinitrophenylhydrazine (DNPH) with the formation of 2,4-dinitrophenylhydrazones, the amount of which was determined spectrophotometrically. The optical density of the formed carbonyl derivatives of dinitrophenylhydrazones was recorded at different wavelengths: 356 nm - aliphatic ketone dinitrophenylhydrazones (KDNPH) of neutral character; 370 nm - aliphatic aldehyde dinirophenylhydrazones (ADNPH) of neutral character; 430 nm - aliphatic KDNFG of the main character; 530 nm - basic aliphatic ADNPH. Nitric oxide was determined by photometry using Grace's solution. Adsorption was measured on a Thermo Scientific Evolution 201 SF at a wavelength of 546 nm. Thus, the results of the studies showed that in patients with arterial hypertension, an increased level of nitric oxide in the blood serum is observed, and there is also a tendency to an increase in the intensity of oxidative modification of proteins at a wavelength of 270 nm and 363 nm, which indicates a statistically significant increase in aliphatic aldehyde and ketone dinitrophenylhydrazones. The increase in the intensity of oxidative modification of blood plasma proteins in the studied patients, revealed by us, actually reflects the general direction of free radical processes and, in particular, the oxidation of proteins throughout the body. A decrease in the activity of the antioxidant system also leads to a violation of protein metabolism. The most important consequence of the oxidative modification of proteins is the inactivation of enzymes.

Keywords: hypertension (HD), oxidative modification of proteins (OMP), nitric oxide (NO), oxidative stress

Procedia PDF Downloads 80

Authors: Gheorghe Braniste

Abstract:

Gender gap has always been in dispute when comparing records and has been a major factor influencing best performances in various sports. Consequently, our study registers the evolution of the difference between men's and women’s best performances within either cyclic or acyclic sports, considering the fact that the training sessions of high performance athletes prove both similarities and differences in long-term adaptation of their body to stress and effort in breaking limits and records. Firstly, for a correct interpretation of the data and tables included in this paper, we must point out that the intense muscular activity has a considerable impact on the structural organization of the organs and systems of the performer's body through the mechanism of motor-visceral reflexes, forming a high working capacity suitable for intense muscular activity. The opportunity to obtaine high sports results during the official competitions is due, on the one hand, to the genetic characteristics of the athlete's body, and on the other hand, to the fact that playing professional sports leaves its mark on the vital morphological and functional parameters. The aim of our research is to study the landmarking differences between male and female athletes and their physical development, together with their growing capacity to stand up to the functional training during the competitive period of their annual training cycle. In order to evaluate the physical development of the athletes, the data of the anthropometric screenings obtained at the Olympic Training Center of the selected teams of the Republic of Moldova were interpreted and rated. During the study of physical development in terms of body height and weight, vital capacity, thoracic excursion, maximum force (Fmax), dynamometry of the hand and back, a further evaluation of the physical development indices that allow an evaluation of complex physical development were registered. The interdependence of the results obtained in performance sports with the morphological and functional particularities of the athletes' body is firmly determined and cannot be disputed. Nevertheless, registered data proved that with the increase of the training capacity, the morphological and functional abilities of the female body increase and, in some respects, approach and even slightly surpass the men in certain sports.

Keywords: physical development, indices, parameters, active body weight, morphological maturity, physical performance

Procedia PDF Downloads 99

Authors: Oluwabiyi Adeola Ayodele

Abstract:

This study analysed the Policy and general issues that have arisen over time in Nigeria’ Cashless banking environment as a result of the lack of a Legal framework on Electronic banking in Nigeria. It undertook an in-depth study of the cashless banking system. It discussed the evolution, growth and development of cashless banking in Nigeria; It revealed the expected benefits of the cashless banking system; It appraised regulatory issues and other prevalent problems on cashless banking in Nigeria; and made appropriate recommendations where necessary. The study relied on primary and secondary sources of information. The primary sources included the Constitution of the Federal Republic of Nigeria, Statutes, Conventions and Judicial decisions, while the secondary sources included Books, Journals Articles, Newspapers and Internet Materials. The study revealed that cashless banking has been adopted in Nigeria but still at the developing stage. It revealed that there is no law for the regulation of cashless banking in Nigeria, what Nigeria relies on for regulation is the Central Bank of Nigeria’s Cashless Policy, 2014. The Banks and Other Financial Institutions Act Chapter B3, LFN, 2004 of Nigeria lack provision to accommodate issues on Internet banking. However, under the general principles of legality in criminal law, and by the provisions of the Nigerian Constitution, a person can only be punished for conducts that have been defined to be criminal by written laws with the penalties specifically stated in the law. Although Nigeria has potent laws for the regulation of paper banking, these laws cannot be substituted for paperless transactions. This is because the issues involved in both transactions vary. The study also revealed that the absence of law in the cashless banking environment in Nigeria will subject consumers to endless risks. This study revealed that the creation of banking markets via the Internet relies on both available technologies and appropriate laws and regulations. It revealed however that Law of some of the countries considered on cashless banking has taken care of most of the legal issues and other problems prevalent in the cashless banking environment. The study also revealed some other problems prevalent in the Nigerian cashless banking environment. The study concluded that for Nigeria to find solutions to the legal issues raised in its cashless banking environment and other problems of cashless banking, it should have a viable legal Frame work for internet banking. The study concluded that the Central Bank of Nigeria’s Policy on Cashless banking is not potent enough to tackle the challenges posed to cashless banking in Nigeria because policies only have a persuasive effect and not a binding effect. There is, therefore, a need for appropriate Laws for the regulation of cashless Banking in Nigeria. The study also concluded that there is a need to create more awareness of the system among Nigerians and solve infrastructural problems like prevalent power outage which often have been creating internet network problem.

Keywords: cashless-banking, Nigeria, policies, laws

Procedia PDF Downloads 475

Authors: Abhishek Ranka

Abstract:

Rock-cut Architecture is a manifestation of human endurance in constructing magnificent structures by sculpting and cutting entire hills. Cave Architecture in India form an important part of rock-cut development and is among the most prolific examples of rock-cut architecture in the world. There are more than 1500 rock-cut caves in various regions of India. Among them mostly are located in western India, more particularly in the state of Maharashtra. Some of the rock-cut caves are located in the central region of India, which is presently known as Malawa (Madhya Pradesh). The region is dominated by the vidhyachal hill ranges toward the west, dotted with the coarse laterite rock. Dhamnar Caves have been excavated in the central region of Mandsaur Dist. With a combination of shared sacred faiths. The earliest rock-cut activity began in the north, in Bihar, where caves were excavated in the Barabar and the Nagarjuni hills during the Mauryan period (3rd century BCE). The rock-cut activity then shifts to the central part of India in Madhya Pradesh, where the caves at Dhamnar, Bagh, Udayagiri, Poldungar, etc. excavated between 3rdto 9ᵗʰ CE. The rock-cut excavation continued to flourish in Madhya Pradesh till 10ᵗʰ century CE, simultaneously with monolithic Hindu temples. Dhamnar caves fall into four architectural typologies: the Lena caves, Chaitya caves, Viharas & Lena-Chaityagriha caves. The Buddhist rock-cutting activity in central India is divisible into two phases. In the first phase (2ndBCE-3rd CE), the Buddha image is conspicuously absent. After a lapse of about three centuries, activity begins again, and the Buddha images this time are carved. The former group belongs to the Hinayana (Lesser Vehicle) phase and the latter to the Mahayana (Greater Vehicle). Dhamnar caves has an elaborate facades, pillar capitals, and many more creative sculptures in various postures. These caves were excavated against the background of invigorating trade activities and varied socio-religious or Socio Cultural contexts. These caves also highlights the wealthy and varied patronage provided by the dynasties of the past. This paper speaks about the appraisal of the rock cut mechanisms, design strategies, and approaches while promoting a scope for further research in conservation practices. Rock-cut sites, with their physical setting and various functional spaces as a sustainable habitat for centuries, has a heritage footprint with a researchquotient.

Keywords: rock-cut architecture, buddhism, hinduism, Iconography, and architectural typologies, Jainism

Procedia PDF Downloads 127

Authors: Mohamad Ammar Ayass, Natalya Griko, Victor Pashkov, Wanying Cao, Kevin Zhu, Jin Zhang, Lina Abi Mosleh

Abstract:

Respiratory syndrome coronavirus 2 (SARS-CoV-2) is the causative agent for coronavirus disease 2019 (COVID-19). Early evidence pointed at the angiotensin-converting enzyme 2 (ACE-2) expressed on the epithelial cells of the lung as the main entry point of SARS-CoV-2 into the cells. The viral entry is mediated by the binding of the Receptor Binding Domain (RBD) of the spike protein that is expressed on the surface of the virus to the ACE-2 receptor. As the number of SARS-CoV-2 variants continues to increase, mutations arising in the RBD of SARS-CoV-2 may lead to the ineffectiveness of RBD targeted neutralizing antibodies. To address this limitation, the objective of this study is to develop a combination of aptamers that target different regions of the RBD, preventing the binding of the spike protein to ACE-2 receptor and subsequent viral entry and replication. A safe and innovative biomedical tool was developed to inhibit viral infection and reduce the harms of COVID-19. In the present study, DNA aptamers were developed against a recombinant trimer S protein using the Systematic Evolution of Ligands by Exponential enrichment (SELEX). Negative selection was introduced at round number 7 to select for aptamers that bind specifically to the RBD domain. A series of 9 aptamers (ADI2010, ADI2011, ADI201L, ADI203L, ADI205L, ADIR68, ADIR74, ADIR80, ADIR83) were selected and characterized with high binding affinity and specificity to the RBD of the spike protein. Aptamers (ADI25, ADI2009, ADI203L) were able to bind and pull down endogenous spike protein expressed on the surface of SARS-CoV-2 virus in COVID-19 positive patient samples and determined by liquid chromatography- tandem mass spectrometry analysis (LC-MS/MS). LC-MS/MS data confirmed that aptamers can bind to the RBD of the spike protein. Furthermore, results indicated that the combination of the 9 best aptamers inhibited the binding of the purified trimer spike protein to the ACE-2 receptor found on the surface of Vero E6 cells. In the same experiment, the combined aptamers displayed a better neutralizing effect than antibodies. The data suggests that the selected aptamers could be used in therapy to neutralize the effect of the SARS-CoV-2 virus by inhibiting the interaction between the RBD and ACE-2 receptor, preventing viral entry into target cells and therefore blocking viral replication.

Keywords: aptamer, ACE-2 receptor, binding inhibitor, COVID-19, spike protein, SARS-CoV-2, treatment

Procedia PDF Downloads 174

Authors: Claes Gunnarsson, Karin Fröding, Nina Hasche

Abstract:

Innovation is a necessity for the evolution of societies and it is also a driving force in human life that leverages value creation among cross-sector participants in various network arrangements. Social innovations can be characterized as the creation and implementation of a new solution to a social problem, which is more effective and sustainable than existing solutions in terms of improvement of society’s conditions and in particular social inclusion processes. However, barriers exist which may restrict the potential of social innovations to live up to its promise as a societal welfare promoting driving force. The literature points at difficulties in tackling social problems primarily related to problem complexity, access to networks, and lack of financial muscles. Further research is warranted at detailed at detail clarification of these barriers, also connected to recognition of the interplay between institutional logics on the development of cross-sector collaborations in networks and the organizing processes to achieve innovation barrier break-through. There is also a need to further elaborate how obstacles that spur a difference between the actual and desired state of innovative value creating service systems can be overcome. The purpose of this paper is to illustrate barriers to social innovations, based on qualitative content analysis of 36 dialogue-based seminars (i.e. research circles) with nine Swedish focus groups including more than 90 individuals representing civil society organizations, private business, municipal offices, and politicians; and analyze patterns that reveal constituents of barriers to social innovations. The paper draws on central aspects of innovation barriers as discussed in the literature and analyze barriers basically related to internal/external and tangible/intangible characteristics. The findings of this study are that existing institutional structures highly influence the transformative potential of social innovations, as well as networking conditions in terms of building a competence-propelled strategy, which serves as an offspring for overcoming barriers of competence extension. Both theoretical and practical knowledge will contribute to how policy-makers and SI-practitioners can facilitate and support social innovation processes to be contextually adapted and implemented across areas and sectors.

Keywords: barriers, research circles, social innovation, service systems

Procedia PDF Downloads 238

Authors: Qing Zhang, Jiachen Nie, Yujia Wen, Guanyuan Kou, Peng Yu, Kun Xia, Qin Yang, Li Ding

Abstract:

BACKGROUND: A facility layout problem (FLP) is an NP-complete (non-deterministic polynomial) problem, which is hard to obtain an exact optimal solution. FLP has been widely studied in various limited spaces and workflows. For example, cafeterias with many types of equipment for troops cause chaotic processes when dining. OBJECTIVE: This article tried to optimize the layout of troops’ cafeteria and to improve the overall efficiency of the dining process. METHODS: First, the original cafeteria layout design scheme was analyzed from an ergonomic perspective and two new design schemes were generated. Next, three facility layout models were designed, and further simulation was applied to compare the total time and density of troops between each scheme. Last, an experiment of the dining process with video observation and analysis verified the simulation results. RESULTS: In a simulation, the dining time under the second new layout is shortened by 2.25% and 1.89% (p<0.0001, p=0.0001) compared with the other two layouts, while troops-flow density and interference both greatly reduced in the two new layouts. In the experiment, process completing time and the number of interference reduced as well, which verified corresponding simulation results. CONCLUSIONS: Our two new layout schemes are tested to be optimal by a series of simulation and space experiments. In future research, similar approaches could be applied when taking layout-design algorithm calculation into consideration.

Keywords: layout optimization, dining efficiency, troops’ cafeteria, anylogic simulation, field experiment

Procedia PDF Downloads 126

Authors: Ajai Singh

Abstract:

Simulation of hydrological processes at the watershed outlet through modelling approach is essential for proper planning and implementation of appropriate soil conservation measures in Damodar Barakar catchment, Hazaribagh, India where soil erosion is a dominant problem. This study quantifies the parametric uncertainty involved in simulation of stream flow using Soil and Water Assessment Tool (SWAT), a watershed scale model and Radial Basis Neural Network (RBNN), an artificial neural network model. Both the models were calibrated and validated based on measured stream flow and quantification of the uncertainty in SWAT model output was assessed using ‘‘Sequential Uncertainty Fitting Algorithm’’ (SUFI-2). Though both the model predicted satisfactorily, but RBNN model performed better than SWAT with R2 and NSE values of 0.92 and 0.92 during training, and 0.71 and 0.70 during validation period, respectively. Comparison of the results of the two models also indicates a wider prediction interval for the results of the SWAT model. The values of P-factor related to each model shows that the percentage of observed stream flow values bracketed by the 95PPU in the RBNN model as 91% is higher than the P-factor in SWAT as 87%. In other words the RBNN model estimates the stream flow values more accurately and with less uncertainty. It could be stated that RBNN model based on simple input could be used for estimation of monthly stream flow, missing data, and testing the accuracy and performance of other models.

Keywords: SWAT, RBNN, SUFI 2, bootstrap technique, stream flow, simulation

Procedia PDF Downloads 342

Authors: Marilou Cadatal-Raduban, Minh Hong Pham, Duong Van Pham, Tu Nguyen Xuan, Mui Viet Luong, Kohei Yamanoi, Toshihiko Shimizu, Nobuhiko Sarukura, Hung Dai Nguyen

Abstract:

There is a great deal of interest in developing all-solid-state tunable ultrashort pulsed lasers emitting in the ultraviolet (UV) region for applications such as micromachining, investigation of charge carrier relaxation in conductors, and probing of ultrafast chemical processes. However, direct short-pulse generation is not as straight forward in solid-state gain media as it is for near-IR tunable solid-state lasers such as Ti:sapphire due to the difficulty of obtaining continuous wave laser operation, which is required for Kerr lens mode-locking schemes utilizing spatial or temporal Kerr type nonlinearity. In this work, the transient cavity method, which was reported to generate ultrashort laser pulses in dye lasers, is extended to a solid-state gain medium. Ce:LiCAF was chosen among the rare-earth-doped fluoride laser crystals emitting in the UV region because of its broad tunability (from 280 to 325 nm) and enough bandwidth to generate 3-fs pulses, sufficiently large effective gain cross section (6.0 x10⁻¹⁸ cm²) favorable for oscillators, and a high saturation fluence (115 mJ/cm²). Numerical simulations are performed to investigate the spectro-temporal evolution of the broadband UV laser emission from Ce:LiCAF, represented as a system of two homogeneous broadened singlet states, by solving the rate equations extended to multiple wavelengths. The goal is to find the appropriate cavity length and Q-factor to achieve the optimal photon cavity decay time and pumping energy for resonator transients that will lead to ps UV laser emission from a Ce:LiCAF crystal pumped by the fourth harmonics (266nm) of a Nd:YAG laser. Results show that a single ps pulse can be generated from a 1-mm, 1 mol% Ce³⁺-doped LiCAF crystal using an output coupler with 10% reflectivity (low-Q) and an oscillator cavity that is 2-mm long (short cavity). This technique can be extended to other fluoride-based solid-state laser gain media.

Keywords: rare-earth-doped fluoride gain medium, transient cavity, ultrashort laser, ultraviolet laser

Procedia PDF Downloads 339

Authors: Rhea Kapoor

Abstract:

Fractal dimension provides a way to characterize non-geometric shapes like those found in nature. The purpose of this research is to estimate Minkowski fractal dimension of human lung images for early detection of lung cancer. Lung cancer is the leading cause of death among all types of cancer and an early histopathological analysis will help reduce deaths primarily due to late diagnosis. A Python application program, PathoPy2.0, was developed for analyzing medical images in pixelated format and estimating Minkowski fractal dimension using a new box-counting algorithm that allows windowing of images for more accurate calculation in the suspected areas of cancerous growth. Benchmark geometric fractals were used to validate the accuracy of the program and changes in fractal dimension of lung images to indicate the presence of issues in the lung. The accuracy of the program for the benchmark examples was between 93-99% of known values of the fractal dimensions. Fractal dimension values were then calculated for lung images, from National Cancer Institute, taken over time to correctly detect the presence of cancerous growth. For example, as the fractal dimension for a given lung increased from 1.19 to 1.27 due to cancerous growth, it represents a significant change in fractal dimension which lies between 1 and 2 for 2-D images. Based on the results obtained on many lung test cases, it was concluded that fractal dimension of human lungs can be used to diagnose lung cancer early. The ideas behind PathoPy2.0 can also be applied to study patterns in the electrical activity of the human brain and DNA matching.

Keywords: fractals, histopathological analysis, image processing, lung cancer, Minkowski dimension

Procedia PDF Downloads 153

Authors: Simon Arunga, Teddy Kwaga, Rita Kageni, Michael Gichangi, Nyawira Mwangi, Fred Kagwa, Rogers Mwavu, Amos Baryashaba, Luis F. Nakayama, Katharine Morley, Michael Morley, Leo A. Celi, Jessica Haberer, Celestino Obua

Abstract:

Purpose: The main aim for creating the Multimodal Database of Retinal Images for Africa (MoDRIA) was to provide a publicly available repository of retinal images for responsible researchers to conduct algorithm development in a bid to curb the challenges of ophthalmic artificial intelligence (AI) in Africa. Methods: Data and retina images were ethically sourced from sites in Uganda and Kenya. Data on medical history, visual acuity, ocular examination, blood pressure, and blood sugar were collected. Retina images were captured using fundus cameras (Foru3-nethra and Canon CR-Mark-1). Images were stored on a secure online database. Results: The database consists of 7,859 retinal images in portable network graphics format from 1,988 participants. Images from patients with human immunodeficiency virus were 18.9%, 18.2% of images were from hypertensive patients, 12.8% from diabetic patients, and the rest from normal’ participants. Conclusion: Publicly available data repositories are a valuable asset in the development of AI technology. Therefore, is a need for the expansion of MoDRIA so as to provide larger datasets that are more representative of Sub-Saharan data.

Keywords: retina images, MoDRIA, image repository, African database

Procedia PDF Downloads 98