Search results for: computer virus classification

Authors: Nikita Katyal, Shaurya Uppal

Abstract:

This paper tackles the significant challenge of accurately classifying customers within a retailer’s customer base. Accurate classification is essential for developing targeted marketing strategies that effectively engage this important demographic. To address this issue, we propose a method that utilizes Large Language Models (LLMs). By employing LLMs, we analyze the metadata associated with product purchases derived from historical data to identify key product categories that act as distinguishing factors. These categories, such as baby food, eldercare products, or family-sized packages, offer valuable insights into the likely household composition of customers, including families with babies, families with kids/teenagers, families with pets, households caring for elders, or mixed households. We segment high-confidence customers into distinct categories by integrating historical purchase behavior with LLM-powered product classification. This paper asserts that life stage segmentation can significantly enhance e-commerce businesses’ ability to target the appropriate customers with tailored products and campaigns, thereby augmenting sales and improving customer retention. Additionally, the paper details the data sources, model architecture, and evaluation metrics employed for the segmentation task.

Keywords: LLMs, segmentation, product tags, fine-tuning, target segments, marketing communication

Procedia PDF Downloads 21

Authors: Gajendra Kumar Mourya, Dinesh Bhatia, Akash Handique, Sunita Warjri, Syed Achaab Amir

Abstract:

Nowadays, Medical imaging has become an integral part of modern healthcare. Abdominal CT images are an invaluable mean for abdominal organ investigation and have been widely studied in the recent years. Diagnosis of liver pathologies is one of the major areas of current interests in the field of medical image processing and is still an open problem. To deeply study and diagnose the liver, segmentation of liver is done to identify which part of the liver is mostly affected. Manual segmentation of the liver in CT images is time-consuming and suffers from inter- and intra-observer differences. However, automatic or semi-automatic computer aided segmentation of the Liver is a challenging task due to inter-patient Liver shape and size variability. In this paper, we present a technique for automatic segmenting the liver from CT images using Random Forest Classifier. Random forests or random decision forests are an ensemble learning method for classification that operate by constructing a multitude of decision trees at training time and outputting the class that is the mode of the classes of the individual trees. After comparing with various other techniques, it was found that Random Forest Classifier provide a better segmentation results with respect to accuracy and speed. We have done the validation of our results using various techniques and it shows above 89% accuracy in all the cases.

Keywords: CT images, image validation, random forest, segmentation

Procedia PDF Downloads 311

Authors: Yeliz Karaca, Carlo Cattani

Abstract:

This study focuses on the local Holder exponent as a measure of the function regularity for time series related to finance data. In this study, the attributes of the finance dataset belonging to 13 countries (India, China, Japan, Sweden, France, Germany, Italy, Australia, Mexico, United Kingdom, Argentina, Brazil, USA) located in 5 different continents (Asia, Europe, Australia, North America and South America) have been examined.These countries are the ones mostly affected by the attributes with regard to financial development, covering a period from 2012 to 2017. Our study is concerned with the most important attributes that have impact on the development of finance for the countries identified. Our method is comprised of the following stages: (a) among the multi fractal methods and Brownian motion Holder regularity functions (polynomial, exponential), significant and self-similar attributes have been identified (b) The significant and self-similar attributes have been applied to the Artificial Neuronal Network (ANN) algorithms (Feed Forward Back Propagation (FFBP) and Cascade Forward Back Propagation (CFBP)) (c) the outcomes of classification accuracy have been compared concerning the attributes that have impact on the attributes which affect the countries’ financial development. This study has enabled to reveal, through the application of ANN algorithms, how the most significant attributes are identified within the relevant dataset via the Holder functions (polynomial and exponential function).

Keywords: artificial neural networks, finance data, Holder regularity, multifractals

Procedia PDF Downloads 245

Authors: Jutta Ransmayr

Abstract:

The digital age has long arrived at Austrian schools, so both society and educationalists demand that digital means should be integrated accordingly to day-to-day school routines. Therefore, the Austrian school-leaving exam (A-levels) can now be written either by hand or by using a computer. However, the choice of writing medium (pen and paper or computer) for written examination papers, which are considered 'high-stakes' exams, raises a number of questions that have not yet been adequately investigated and answered until recently, such as: What effects do the different conditions of text production in the written German A-levels have on the component of normative linguistic accuracy? How do the spelling skills of German A-level papers written with a pen differ from those that the students wrote on the computer? And how is the teacher's assessment related to this? Which practical desiderata for German didactics can be derived from this? In a trilateral pilot project of the Austrian Center for Digital Humanities (ACDH) of the Austrian Academy of Sciences and the University of Vienna in cooperation with the Austrian Ministry of Education and the Council for German Orthography, these questions were investigated. A representative Austrian learner corpus, consisting of around 530 German A-level papers from all over Austria (pen and computer written), was set up in order to subject it to a quantitative (corpus-linguistic and statistical) and qualitative investigation with regard to the spelling and punctuation performance of the high school graduates and the differences between pen- and computer-written papers and their assessments. Relevant studies are currently available mainly from the Anglophone world. These have shown that writing on the computer increases the motivation to write, has positive effects on the length of the text, and, in some cases, also on the quality of the text. Depending on the writing situation and other technical aids, better results in terms of spelling and punctuation could also be found in the computer-written texts as compared to the handwritten ones. Studies also point towards a tendency among teachers to rate handwritten texts better than computer-written texts. In this paper, the first comparable results from the German-speaking area are to be presented. Research results have shown that, on the one hand, there are significant differences between handwritten and computer-written work with regard to performance in orthography and punctuation. On the other hand, the corpus linguistic investigation and the subsequent statistical analysis made it clear that not only the teachers' assessments of the students’ spelling performance vary enormously but also the overall assessments of the exam papers – the factor of the production medium (pen and paper or computer) also seems to play a decisive role.

Keywords: exam paper assessment, pen and paper or computer, learner corpora, linguistics

Procedia PDF Downloads 168

Authors: Shigenori Togashi, Kei Takenaka

Abstract:

We developed new processes which can collect and detect rapidly airborne pathogens such as the avian flu virus for the pandemic prevention. The fluorescence antibody technique is known as one of high-sensitive detection methods for viruses, but this needs up to a few hours to bind sufficient fluorescence dyes to viruses for detection. In this paper, we developed a mist-labeling can detect substitution viruses in a short time to improve the binding rate of fluorescent dyes and substitution viruses by the micro reaction process. Moreover, we developed the rapid detection system with the above 'mist labeling'. The detection system set with a sampling bag collecting patient’s breath and a cartridge can detect automatically pathogens within 10 minutes.

Keywords: viruses, sampler, mist, detection, fluorescent dyes, microreaction

Procedia PDF Downloads 473

Authors: Sushma Ghogale

Abstract:

With a surge in user-generated content or feedback or reviews on the internet, it has become possible and important to know consumers' opinions about products and services. This data is important for both potential customers and businesses providing the services. Data from social media is attracting significant attention and has become the most prominent channel of expressing an unregulated opinion. Prospective customers look for reviews from experienced customers before deciding to buy a product or service. Several websites provide a platform for users to post their feedback for the provider and potential customers. However, the biggest challenge in analyzing such data is in extracting latent features and providing term-level analysis of the data. This paper proposes an approach to use topic modeling to classify the reviews into topics and conduct sentiment analysis to mine the opinions. This approach can analyse and classify latent topics mentioned by reviewers on business sites or review sites, or social media using topic modeling to identify the importance of each topic. It is followed by sentiment analysis to assess the satisfaction level of each topic. This approach provides a classification of hotel reviews using multiple machine learning techniques and comparing different classifiers to mine the opinions of user reviews through sentiment analysis. This experiment concludes that Multinomial Naïve Bayes classifier produces higher accuracy than other classifiers.

Keywords: latent Dirichlet allocation, topic modeling, text classification, sentiment analysis

Procedia PDF Downloads 96

Authors: Muhammad Faheem Khakhi, Jian Yu Wang, Salman Muhammad, Muhammad Faisal Shabir

Abstract:

Population growth and Chinese two-child policy will boost pharmaceutical market, and it will continue to maintain the growth for a period of time in the future, the traditional pharmacy dispensary has been unable to meet the growing medical needs of the peoples. Under the strong support of the national policy, the automatic transformation of traditional pharmacies is the inclination of the Times, the new type of intelligent pharmacy system will continue to promote the development of the pharmaceutical industry. Under this background, based on PLC control, the paper proposed an intelligent storage and automatic drug delivery system; complete design of the lower computer's control system and the host computer's software system has been present. The system can be applied to dispensing work for Chinese herbal medicinal and Western medicines. Firstly, the essential of intelligent control system for pharmacy is discussed. After the analysis of the requirements, the overall scheme of the system design is presented. Secondly, introduces the software and hardware design of the lower computer's control system, including the selection of PLC and the selection of motion control system, the problem of the human-computer interaction module and the communication between PC and PLC solves, the program design and development of the PLC control system is completed. The design of the upper computer software management system is described in detail. By analyzing of E-R diagram, built the establish data, the communication protocol between systems is customize, C++ Builder is adopted to realize interface module, supply module, main control module, etc. The paper also gives the implementations of the multi-threaded system and communication method. Lastly, each module of the lower computer control system is tested. Then, after building a test environment, the function test of the upper computer software management system is completed. On this basis, the entire control system accepts the overall test.

Keywords: automatic pharmacy, PLC, control system, management system, communication

Procedia PDF Downloads 307

Authors: Zegrar Ahmed, Ghabi Mohamed

Abstract:

The degradation of arid and semi-arid ecosystems in Algeria has become a palpable fact that only hinders progress and rural development. In these exceptionally fragile environments, the decline of vegetation is done according to an alarming increase and wind erosion dominates. The ecosystem is subjected to a long hot dry season and low annual average rainfall. The urgency of the fight against desertification is imposed by the very nature of the process that tends to self-accelerate, resulting when human intervention is not forthcoming the irreversibility situations, preventing any possibility of restoration state of these zones. These phenomena have led to different degradation processes, such as the destruction of vegetation, soil erosion, and deterioration of the physical environment. In this study, the work is mainly based on the criteria for classification and identification of physical parameters for spatial analysis and multi-sources to determine the vulnerability of major steppe formations and their impact on desertification. we used Landsat data with two different dates March 2010 and November 2014 in order to determine the changes in land cover, sand moving and land degradation for the diagnosis of the desertification Phenomenon. The application, through specific processes, including the supervised classification was used to characterize the main steppe formations. An analysis of the vulnerability of plant communities was conducted to assign weights and identify areas most susceptible to desertification. Vegetation indices are used to characterize the steppe formations to determine changes in land use.

Keywords: remote sensing, SIG, ecosystem, degradation, desertification

Procedia PDF Downloads 337

Authors: Chang Liang, Weizhi Gong, Yan Zhang

Abstract:

Purpose: Hepatocellular carcinoma (HCC) is a malignant tumor with a high mortality rate and poor prognosis worldwide. Murine double minute 2 (MDM2) regulates the tumor suppressor p53, increasing cancer risk and accelerating tumor progression. Speckle-type POX virus and zinc finger protein (SPOP), a key of subunit of Cullin-Ring E3 ligase, inhibits tumor genesis and progression by the ubiquitination of its downstream substrates. This study aimed to clarify whether SPOP and MDM2 are mutually regulated in HCC and the correlation between SPOP and MDM2 and the prognosis of HCC patients. Methods: First, the expression of SPOP and MDM2 in HCC tissues were detected by TCGA database. Then, 53 paired samples of HCC tumor and adjacent tissues were collected to evaluate the expression of SPOP and MDM2 using immunohistochemistry. Chi-square test or Fisher’s exact test were used to analyze the relationship between clinicopathological features and the expression levels of SPOP and MDM2. In addition, Kaplan‒Meier curve analysis and log-rank test were used to investigate the effects of SPOP and MDM2 on the survival of HCC patients. Last, the Multivariate Cox proportional risk regression model analyzed whether the different expression levels of SPOP and MDM2 were independent risk factors for the prognosis of HCC patients. Results: Bioinformatics analysis revealed the low expression of SPOP and high expression of MDM2 were related to worse prognosis of HCC patients. The relationship between the expression of SPOP and MDM2 and tumor stem-like features showed an opposite trend. The immunohistochemistry showed the expression of SPOP protein was significantly downregulated while MDM2 protein significantly upregulated in HCC tissue compared to that in para-cancerous tissue. Tumors with low SPOP expression were related to worse T stage and Barcelona Clinic Liver Cancer (BCLC) stage, but tumors with high MDM2 expression were related to worse T stage, M stage, and BCLC stage. Kaplan–Meier curves showed HCC patients with high SPOP expression and low MDM2 expression had better survival than those with low SPOP expression and high MDM2 expression (P < 0.05). A multivariate Cox proportional risk regression model confirmed that a high MDM2 expression level was an independent risk factor for poor prognosis in HCC patients (P <0.05). Conclusion: The expression of SPOP protein was significantly downregulated, while the expression of MDM2 significantly upregulated in HCC. The low expression of SPOP and high expression. of MDM2 were associated with malignant progression and poor prognosis of HCC patients, indicating a potential therapeutic target for HCC patients.

Keywords: hepatocellular carcinoma, murine double minute 2, speckle-type POX virus and zinc finger protein, ubiquitination

Procedia PDF Downloads 142

Authors: Steven G. Sclan

Abstract:

Background: Since December 2019, the world has been afflicted by the spread of the Severe Acute Respiratory Syndrome-Corona Virus-2 (SARS-CoV-2), which is responsible for the condition referred to as Covid-19. The illness has had a cataclysmic impact on the political, social, economic, and overall well-being of the population of the entire globe. While Covid-19 has had a substantial universal fatality impact, it may have an even greater effect on the socioeconomic, medical well-being, and healthcare planning for remaining societies. Significance: As these numbers illustrate, many more persons survive the infection than die from it, and many of those patients have noted ongoing, persistent symptoms after successfully enduring the acute phase of the illness. Recognition and understanding of these symptoms are crucial for developing and arranging efficacious models of care for all patients (whether or not having been hospitalized) surviving acute covid illness and plagued by post-acute symptoms. Furthermore, regarding Covid infection in children (< 18 y/o), although it may be that Covid “+” children are not major vectors of infective transmission, it now appears that many more children than initially thought are carrying the virus without accompanying obvious symptomatic expression. It seems reasonable to wonder whether viral effects occur in children – those children who are Covid “+” and now asymptomatic – and if, over time, they might also experience similar symptoms. An even more significant question is whether Covid “+” asymptomatic children might manifest increased multiple health problems as they grow – i.e., developmental complications (e.g., physical/medical, metabolic, neurobehavioral, etc.) – in comparison to children who had been consistently Covid “ - ” during the pandemic. Topics Addressed and Theoretical Importance: This review is important because of the description of both quantitative and qualitative methods for clinical and biomedical research. Topics reviewed will consider the importance of well-designed, comprehensive (i.e., quantitative and qualitative methods) longitudinal studies of Post Covid-19 symptoms in both adults and children. Also reviewed will be general characteristics of longitudinal studies and a presentation of a model for a proposed study. Also discussed will be the benefit of longitudinal studies for the development of efficacious interventions and for the establishment of cogent, practical, and efficacious community healthcare service planning for post-acute covid patients. Conclusion: Results of multi-dimensional, longitudinal studies will have important theoretical implications. These studies will help to improve our understanding of the pathophysiology of long COVID and will aid in the identification of potential targets for treatment. Such studies can also provide valuable insights into the long-term impact of COVID-19 on public health and socioeconomics.

Keywords: COVID-19, post-COVID-19, long COVID, longitudinal research, quantitative research, qualitative research

Procedia PDF Downloads 59

Authors: Kwaku Damoah

Abstract:

This paper presents a methodology and software application (App) designed to empower users in accessing, retrieving, and comparatively exploring data within the hierarchical network framework of the Government Finance Statistics (GFS) system. It explores the ease of navigating the GFS system and identifies the gaps filled by the new methodology and App. The GFS, embodies a complex Hierarchical Network Classification (HNC) structure, encapsulating institutional units, revenues, expenses, assets, liabilities, and economic activities. Navigating this structure demands specialized knowledge, experience, and skill, posing a significant challenge for effective analytics and fiscal policy decision-making. Many professionals encounter difficulties deciphering these classifications, hindering confident utilization of the system. This accessibility barrier obstructs a vast number of professionals, students, policymakers, and the public from leveraging the abundant data and information within the GFS. Leveraging R programming language, Data Science Analytics and Machine Learning, an efficient methodology enabling users to access, navigate, and conduct exploratory comparisons was developed. The machine learning Fiscal Analytics App (FLOWZZ) democratizes access to advanced analytics through its user-friendly interface, breaking down expertise barriers.

Keywords: data science, data wrangling, drilldown analytics, government finance statistics, hierarchical network classification, machine learning, web application.

Procedia PDF Downloads 69

Authors: Waseem Akram, Hafiz Azhar Ali Khan

Abstract:

Unplanned urbanization together with change in life from simple to more technologically advanced style with flow of rural masses to urban areas has played a vital role in pilling loads of solid wastes in our environment. The cities and towns have expanded beyond boundaries. Even the uncontrolled population expansion has caused the overall environmental burden. Thus, today the indifference remains as one of the biggest trash that has come up due to the non-responsive behavior of the people. Everyday huge amount of solid waste is thrown in the streets, on the roads, parks, and in all those places that are frequently and often visited by the human beings. This behavior based response in many countries of the world has led to serious health concerns and environmental issues. Over 80% of our products that are sold in the market are packed in plastic bags. None of the bags are later recycled but simply become a permanent environment concern that flies, choke lines or are burnt and release toxic gases in the environment or form dumps of heaps. Lack of classification of the daily waste generated from houses and other places lead to worst clogging of the sewerage lines and formation of ponding areas which ultimately favor vector borne disease and sometimes become a cause of transmission of polio virus. Solid waste heaps were checked at different places of the cities. All of the wastes on visual assessments were classified into plastic bags, papers, broken plastic pots, clay pots, steel boxes, wrappers etc. All solid waste dumping sites in the cities and wastes that were thrown outside of the trash containers usually contained wrappers, plastic bags, and unconsumed food products. Insect populations seen in these sites included the house flies, bugs, cockroaches and mosquito larvae breeding in water filled wrappers, containers or plastic bags. The population of the mosquitoes, cockroaches and houseflies were relatively very high in dumping sites close to human population. This population has been associated with cases like dengue, malaria, dysentery, gastro and also to skin allergies during the monsoon and summer season. Thus, dumping of the huge amount of solid wastes in and near the residential areas results into serious environmental concerns, bad smell circulation, and health related issues. In some places, the same waste is burnt to get rid of mosquitoes through smoke which ultimately releases toxic material in the atmosphere. Therefore, a proper environmental strategy is needed to minimize environmental burden and promote concepts of recycled products and thus, reduce the disease burden.

Keywords: solid waste accumulation, disease burden, mosquitoes, vector borne diseases

Procedia PDF Downloads 277

Authors: Agih Ukuru Agih

Abstract:

This work is an appraisal of the application and applicability of computer system to financial management in improving the speed, performance, accuracy, and efficiency of the College of Education, Oju. The computerization of financial management, which is a recent development that has authentic and dedicated balancing of accounting records, would be of enormous benefits to the college. The core objective of this project is to recommend the software that typically matches a computerized institution, making for improved service, reduced fraud, mishandled funds, and financial records in the College of Education, Oju. Considering major globalization impacts in computerized financial management of the college, the study recommends among other things that the College of Education, Oju should endeavor to be positive towards computerized financial management in the institution.

Keywords: computer system, balancing, accounting records, computerized financial management

Procedia PDF Downloads 392

Authors: Vishwajit Ghatge, David Looper

Abstract:

Over the last few decades, oilfield service rolling equipment has significantly increased in weight, primarily because of emissions regulations, which require larger/heavier engines, larger cooling systems, and emissions after-treatment systems, in some cases, etc. Larger engines cause more vibration and shock loads, leading to failure of electronics and control systems. If the vibrating frequency of the engine matches the system frequency, high resonance is observed on structural parts and mounts. One such existing automated control equipment system comprising wire rope mounts used for mounting computers was designed approximately 12 years ago. This includes the use of an industrial- grade computer to control the system operation. The original computer had a smaller, lighter enclosure. After a few years, a newer computer version was introduced, which was 10 lbm heavier. Some failures of internal computer parts have been documented for cases in which the old mounts were used. Because of the added weight, there is a possibility of having the two brackets impact each other under off-road conditions, which causes a high shock input to the computer parts. This added failure mode requires validating the existing mount design to suit the new heavy-weight computer. This paper discusses the modal finite element method (FEM) analysis and experimental modal analysis conducted to study the effects of vibration on the wire rope mounts and the computer. The existing mount was modelled in ANSYS software, and resultant mode shapes and frequencies were obtained. The experimental modal analysis was conducted, and actual frequency responses were observed and recorded. Results clearly revealed that at resonance frequency, the brackets were colliding and potentially causing damage to computer parts. To solve this issue, spring mounts of different stiffness were modeled in ANSYS software, and the resonant frequency was determined. Increasing the stiffness of the system increased the resonant frequency zone away from the frequency window at which the engine showed heavy vibrations or resonance. After multiple iterations in ANSYS software, the stiffness of the spring mount was finalized, which was again experimentally validated.

Keywords: experimental modal analysis, FEM Modal Analysis, frequency, modal analysis, resonance, vibration

Procedia PDF Downloads 320

Authors: Anitha Muralidhara, Victor Engelen, Christophe Len, Pascal Pandard, Guy Marlair

Abstract:

Production of bio-based chemicals and materials from lignocellulosic biomass is gaining tremendous importance in advanced bio-refineries while aiming towards progressive replacement of petroleum based chemicals in transportation fuels and commodity polymers. One such attempt has resulted in the production of key furan derivatives (FD) such as furfural, HMF, MMF etc., via acid catalyzed dehydration (ACD) of C6 and C5 sugars, which are further converted into key chemicals or intermediates (such as Furandicarboxylic acid, Furfuryl alcohol etc.,). In subsequent processes, many high potential FD are produced, that can be converted into high added value polymers or high energy density biofuels. During ACD, an unavoidable polyfuranic byproduct is generated which is called humins. The family of FD is very large with varying chemical structures and diverse physicochemical properties. Accordingly, the associated risk profiles may largely vary. Hazardous Material (Haz-mat) classification systems such as GHS (CLP in the EU) and the UN TDG Model Regulations for transport of dangerous goods are one of the preliminary requirements for all chemicals for their appropriate classification, labelling, packaging, safe storage, and transportation. Considering the growing application routes of FD, it becomes important to notice the limited access to safety related information (safety data sheets available only for famous compounds such as HMF, furfural etc.,) in these internationally recognized haz-mat classification systems. However, these classifications do not necessarily provide information about the extent of risk involved when the chemical is used in any specific application. Factors such as thermal stability, speed of combustion, chemical incompatibilities, etc., can equally influence the safety profile of a compound, that are clearly out of the scope of any haz-mat classification system. Irrespective of the bio-based origin, FD has so far received inconsistent remarks concerning their toxicity profiles. With such inconsistencies, there is a fear that, a large family of FD may also follow extreme judgmental scenarios like ionic liquids, by ranking some compounds as extremely thermally stable, non-flammable, etc., Unless clarified, these messages could lead to misleading judgements while ranking the chemical based on its hazard rating. Safety is a key aspect in any sustainable biorefinery operation/facility, which is often underscored or neglected. To fill up these existing data gaps and to address ambiguities and discrepancies, the current study focuses on giving preliminary insights on safety assessment of FD and their potential targeted by-products. With the available information in the literature and obtained experimental results, physicochemical safety, environmental safety as well as (a scenario based) fire safety profiles of key FD, as well as side streams such as humins and levulinic acid, will be considered. With this, the study focuses on defining patterns and trends that gives coherent safety related information for existing and newly synthesized FD in the market for better functionality and sustainable applications.

Keywords: furanics, humins, safety, thermal and fire hazard, toxicity

Procedia PDF Downloads 164

Authors: Dmitriy Babenko, Sergey Yegorov, Ilya Korshukov, Aidana Sultanbekova, Valentina Barkhanskaya, Tatiana Bashirova, Yerzhan Zhunusov, Yevgeniya Li, Viktoriya Parakhina, Svetlana Kolesnichenko, Yeldar Baiken, Aruzhan Pralieva, Zhibek Zhumadilova, Matthew S. Miller, Gonzalo H. Hortelano, Anar Turmuhambetova, Antonella E. Chesca, Irina Kadyrova

Abstract:

Introduction: The rapidly evolving COVID-19 pandemic, along with the re-emergence of pathogens causing acute respiratory infections (ARI), has necessitated the development of novel diagnostic tools to differentiate various causes of ARI. MALDI-MS, due to its wide usage and affordability, has been proposed as a potential instrument for diagnosing SARS-CoV-2 versus non-SARS-CoV-2 ARI. The aim of this study was to investigate the potential of MALDI-MS in conjunction with a machine learning model to accurately distinguish between symptomatic infections caused by SARS-CoV-2 and non-SARS-CoV-2 during both the early and later phases of the pandemic. Furthermore, this study aimed to analyze mass spectrometry (MS) data obtained from nasal swabs of healthy individuals. Methods: We gathered mass spectra from 252 samples, comprising 108 SARS-CoV-2-positive samples obtained in 2020 (Covid 2020), 7 SARS-CoV- 2-positive samples obtained in 2023 (Covid 2023), 71 samples from symptomatic individuals without SARS-CoV-2 (Control non-Covid ARVI), and 66 samples from healthy individuals (Control healthy). All the samples were subjected to RT-PCR testing. For data analysis, we employed the caret R package to train and test seven machine-learning algorithms: C5.0, KNN, NB, RF, SVM-L, SVM-R, and XGBoost. We conducted a training process using a five-fold (outer) nested repeated (five times) ten-fold (inner) cross-validation with a randomized stratified splitting approach. Results: In this study, we utilized the Covid 2020 dataset as a case group and the non-Covid ARVI dataset as a control group to train and test various machine learning (ML) models. Among these models, XGBoost and SVM-R demonstrated the highest performance, with accuracy values of 0.97 [0.93, 0.97] and 0.95 [0.95; 0.97], specificity values of 0.86 [0.71; 0.93] and 0.86 [0.79; 0.87], and sensitivity values of 0.984 [0.984; 1.000] and 1.000 [0.968; 1.000], respectively. When examining the Covid 2023 dataset, the Naive Bayes model achieved the highest classification accuracy of 43%, while XGBoost and SVM-R achieved accuracies of 14%. For the healthy control dataset, the accuracy of the models ranged from 0.27 [0.24; 0.32] for k-nearest neighbors to 0.44 [0.41; 0.45] for the Support Vector Machine with a radial basis function kernel. Conclusion: Therefore, ML models trained on MALDI MS of nasopharyngeal swabs obtained from patients with Covid during the initial phase of the pandemic, as well as symptomatic non-Covid individuals, showed excellent classification performance, which aligns with the results of previous studies. However, when applied to swabs from healthy individuals and a limited sample of patients with Covid in the late phase of the pandemic, ML models exhibited lower classification accuracy.

Keywords: SARS-CoV-2, MALDI-TOF MS, ML models, nasopharyngeal swabs, classification

Procedia PDF Downloads 106

Authors: RAM PAL SINGH, VIKASH CHAUDHARY, MONIKA VERMA

Abstract:

In this paper, we proposed the implementation of optimization based Extreme Learning Machine (ELM) for watermarking of B-channel of color image in discrete wavelet transform (DWT) domain. ELM, a regularization algorithm, works based on generalized single-hidden-layer feed-forward neural networks (SLFNs). However, hidden layer parameters, generally called feature mapping in context of ELM need not to be tuned every time. This paper shows the embedding and extraction processes of watermark with the help of ELM and results are compared with already used machine learning models for watermarking.Here, a cover image is divide into suitable numbers of non-overlapping blocks of required size and DWT is applied to each block to be transformed in low frequency sub-band domain. Basically, ELM gives a unified leaning platform with a feature mapping, that is, mapping between hidden layer and output layer of SLFNs, is tried for watermark embedding and extraction purpose in a cover image. Although ELM has widespread application right from binary classification, multiclass classification to regression and function estimation etc. Unlike SVM based algorithm which achieve suboptimal solution with high computational complexity, ELM can provide better generalization performance results with very small complexity. Efficacy of optimization method based ELM algorithm is measured by using quantitative and qualitative parameters on a watermarked image even though image is subjected to different types of geometrical and conventional attacks.

Keywords: BER, DWT, extreme leaning machine (ELM), PSNR

Procedia PDF Downloads 310

Authors: Kajal Zarei

Abstract:

Supply chain management is becoming an increasingly important issue in many businesses today. In such circumstances, a number of reasons such as management deficiency in different segments of the supply chain, lack of streamlined processes, resistance to change the current systems and technologies, and lack of advanced information system have paved the ground to ask for innovative research studies. To this end, information technology (IT) is becoming a major driver to overcome the supply chain limitations and deficiencies. The emergence of IT has provided an excellent opportunity for redefining the supply chain to be more effective and competitive. This paper has investigated the IT impact on two-digit industry codes in the International Standard Industrial Classification (ISIC) that are operating in four groups of the supply chains. Firstly, the primary fields of the supply chain were investigated, and then paired comparisons of different industry parts were accomplished. Using experts' ideas and Analytical Hierarchy Process (AHP), the status of industrial activities in Kurdistan Province in Iran was determined. The results revealed that manufacturing and inventory fields have been more important compared to other fields of the supply chain. In addition, IT has had greater impact on food and beverage industry, chemical industry, wood industry, wood products, and production of basic metals. The results indicated the need to IT awareness in supply chain management; in other words, IT applications needed to be developed for the identified industries.

Keywords: supply chain, information technology, analytical hierarchy process, two-digit codes, international standard industrial classification

Procedia PDF Downloads 279

Authors: Meruyert Serik, Nassipzhan Duisegaliyeva, Danara Tleumagambetova, Madina Ermaganbetova

Abstract:

This research paper explores the process of creating a proctoring system by evaluating the implementation of practical face recognition algorithms. Students of educational programs reviewed the research work "6B01511-Computer Science", "7M01511-Computer Science", "7M01525- STEM Education," and "8D01511-Computer Science" of Eurasian National University named after L.N. Gumilyov. As an outcome, a proctoring system will be created, enabling the conduction of tests and ensuring academic integrity checks within the system. Due to the correct operation of the system, test works are carried out. The result of the creation of the proctoring system will be the basis for the automation of the informational, educational portal developed by machine learning.

Keywords: artificial intelligence, education portal, face recognition, machine learning, proctoring

Procedia PDF Downloads 123

Authors: Sergio Alejandro Cuevas, Catherine Etchebest, Fernando Luis Barroso Da Silva

Abstract:

The flavivirus genus has several organisms responsible for generating various diseases in humans. Special in Brazil, Zika (ZIKV), Dengue (DENV) and Yellow Fever (YFV) viruses have raised great health concerns due to the high number of cases affecting the area during the last years. Diagnostic is still a difficult issue since the clinical symptoms are highly similar. The understanding of their common structural/dynamical and biomolecular interactions features and differences might suggest alternative strategies towards differential serological diagnostics and therapeutic intervention. Due to their immunogenicity, the primary focus of this study was on the ZIKV, DENV and YFV non-structural proteins 1 (NS1) protein. By means of computational studies, we calculated the main physical chemical properties of this protein from different strains that are directly responsible for the biomolecular interactions and, therefore, can be related to the differential infectivity of the strains. We also mapped the electrostatic differences at both the sequence and structural levels for the strains from Uganda to Brazil that could suggest possible molecular mechanisms for the increase of the virulence of ZIKV. It is interesting to note that despite the small changes in the protein sequence due to the high sequence identity among the studied strains, the electrostatic properties are strongly impacted by the pH which also impact on their biomolecular interactions with partners and, consequently, the molecular viral biology. African and Asian strains are distinguishable. Exploring the interfaces used by NS1 to self-associate in different oligomeric states, and to interact with membranes and the antibody, we could map the strategy used by the ZIKV during its evolutionary process. This indicates possible molecular mechanisms that can explain the different immunological response. By the comparison with the known antibody structure available for the West Nile virus, we demonstrated that the antibody would have difficulties to neutralize the NS1 from the Brazilian strain. The present study also opens up perspectives to computationally design high specificity antibodies.

Keywords: zika, biomolecular interactions, electrostatic interactions, molecular mechanisms

Procedia PDF Downloads 132

Authors: Mahdi Bazarganigilani

Abstract:

Computer-aided diagnosis (CAD) systems can play crucial roles in diagnosing crucial diseases such as breast cancer at the earliest. In this paper, a CAD system for the diagnosis of breast cancer was introduced and evaluated. This CAD system was developed by using spatio-temporal analysis of data on a set of consecutive thermographic images by employing wavelet transformation. By using this analysis, a very accurate machine learning model using random forest was obtained. The final results showed a promising accuracy of 91% in terms of the F1 measure indicator among 200 patients' sample data. The CAD system was further extended to obtain a detailed analysis of the effect of smaller sub-areas of each breast on the occurrence of cancer.

Keywords: computer-aided diagnosis systems, thermographic analysis, spatio-temporal analysis, image processing, machine learning

Procedia PDF Downloads 209

Authors: B. S. Muddukrishna, Karthik Aithal, Aravind Pai

Abstract:

Introduction: Preparation of binary cocrystals of Etraverine (ETR) by using Tartaric Acid (TAR) as a conformer was the main focus of this study. Etravirine is a Class IV drug, as per the BCS classification system. Methods: Cocrystals were prepared by slow evaporation technique. A mixture of total 500mg of ETR: TAR was weighed in molar ratios of 1:1 (371.72mg of ETR and 128.27mg of TAR). Saturated solution of Etravirine was prepared in Acetone: Methanol (50:50) mixture in which tartaric acid is dissolved by sonication and then this solution was stirred using a magnetic stirrer until the solvent got evaporated. Shimadzu FTIR – 8300 system was used to acquire the FTIR spectra of the cocrystals prepared. Shimadzu thermal analyzer was used to achieve DSC measurements. X-ray diffractometer was used to obtain the X-ray powder diffraction pattern. Shake flask method was used to determine the equilibrium dynamic solubility of pure, physical mixture and cocrystals of ETR. USP buffer (pH 6.8) containing 1% of Tween 80 was used as the medium. The pure, physical mixture and the optimized cocrystal of ETR were accurately weighed sufficient to maintain the sink condition and were filled in hard gelatine capsules (size 4). Electrolab-Tablet Dissolution tester using basket apparatus at a rotational speed of 50 rpm and USP phosphate buffer (900 mL, pH = 6.8, 37 ˚C) + 1% Tween80 as a media, was used to carry out dissolution. Shimadzu LC-10 series chromatographic system was used to perform the analysis with PDA detector. An Hypersil BDS C18 (150mm ×4.6 mm ×5 µm) column was used for separation with mobile phase comprising of a mixture of ace¬tonitrile and phosphate buffer 20mM, pH 3.2 in the ratio 60:40 v/v. The flow rate was 1.0mL/min and column temperature was set to 30°C. The detection was carried out at 304 nm for ETR. Results and discussions: The cocrystals were subjected to various solid state characterization and the results confirmed the formation of cocrystals. The C=O stretching vibration (1741cm-1) in tartaric acid was disappeared in the cocrystal and the peak broadening of primary amine indicates hydrogen bond formation. The difference in the melting point of cocrystals when compared to pure Etravirine (265 °C) indicates interaction between the drug and the coformer which proves that first ordered transformation i.e. melting endotherm has disappeared. The difference in 2θ values of pure drug and cocrystals indicates the interaction between the drug and the coformer. Dynamic solubility and dissolution studies were also conducted by shake flask method and USP apparatus one respectively and 3.6 fold increase in the dynamic solubility were observed and in-vitro dissolution study shows four fold increase in the solubility for the ETR: TAR (1:1) cocrystals. The ETR: TAR (1:1) cocrystals shows improved solubility and dissolution as compared to the pure drug which was clearly showed by solid state characterization and dissolution studies.

Keywords: dynamic solubility, Etraverine, in vitro dissolution, slurry method

Procedia PDF Downloads 354

Authors: David Jurado, Carlos Ávila

Abstract:

Detection of early signs of breast cancer development is crucial to quickly diagnose the disease and to define adequate treatment to increase the survival probability of the patient. Computer Aided Detection systems (CADs), along with modern data techniques such as Machine Learning (ML) and Neural Networks (NN), have shown an overall improvement in digital mammography cancer diagnosis, reducing the false positive and false negative rates becoming important tools for the diagnostic evaluations performed by specialized radiologists. However, ML and NN-based algorithms rely on datasets that might bring issues to the segmentation tasks. In the present work, an automatic segmentation and detection algorithm is described. This algorithm uses image processing techniques along with the Hough transform to automatically identify microcalcifications that are highly correlated with breast cancer development in the early stages. Along with image processing, automatic segmentation of high-contrast objects is done using edge extraction and circle Hough transform. This provides the geometrical features needed for an automatic mask design which extracts statistical features of the regions of interest. The results shown in this study prove the potential of this tool for further diagnostics and classification of mammographic images due to the low sensitivity to noisy images and low contrast mammographies.

Keywords: breast cancer, segmentation, X-ray imaging, hough transform, image analysis

Procedia PDF Downloads 82

Authors: M. C. O. Ezeibe, F. I. O. Ezeibe

Abstract:

Reasons viral diseases (including AI, HIV/AIDS, and COVID-19), tumors (including Cancers and Prostrate enlargement), and antimicrobial-resistant infections (AMR) are difficult to cure are features of the pathogens which normal cells do not have or need (biomedical markers) have not been identified; medicines that can counter the markers have not been invented; strategies and mechanisms for their treatments have not been developed. When cells become abnormal, they acquire negative electrical charges, and viruses are either positively charged or negatively charged, while normal cells remain neutral (without electrical charges). So, opposite charges' electrostatic attraction is a treatment mechanism for viral diseases and tumors. Medicines that have positive electrical charges would mop abnormal (infected and tumor) cells and DNA viruses (negatively charged), while negatively charged medicines would mop RNA viruses (positively charged). Molecules of Aluminum-magnesium silicate [AMS: Al₂Mg₃ (SiO₄)₃], an approved medicine and pharmaceutical stabilizing agent, consist of nanoparticles which have both positive electrically charged ends and negative electrically charged ends. The very small size (0.96 nm) of the nanoparticles allows them to reach all cells in every organ. By stabilizing antimicrobials, AMS reduces the rate at which the body metabolizes them so that they remain at high concentrations for extended periods. When drugs remain at high concentrations for longer periods, their efficacies improve. Again, nanoparticles enhance the delivery of medicines to effect targets. Both remaining at high concentrations for longer periods and better delivery to effect targets improve efficacy and make lower doses achieve desired effects so that side effects of medicines are reduced to allow the immunity of patients to be enhanced. Silicates also enhance the immune responses of treated patients. Improving antimicrobial efficacies and enhancing patients` immunity terminate infections so that none remains that could develop resistance. Some countries do not have natural deposits of AMS, but they may have Aluminum silicate (AS: Al₄ (SiO₄)₃) and Magnesium silicate (MS: Mg₂SiO₄), which are also approved medicines. So, AS and MS were used to formulate an AMS-brand, named Medicinal synthetic AMS {Al₄ (SiO₄)₃ + 3Mg₂SiO₄ → 2Al₂Mg₃ (SiO₄)₃}. To overcome the challenge of AMS, AS, and MS being un-absorbable, Dextrose monohydrate is incorporated in MSAMS-formulations for the simple sugar to convey the electrically charged nanoparticles into blood circulation by the principle of active transport so that MSAMS-antimicrobial formulations function systemically. In vitro, MSAMS reduced (P≤0.05) titers of viruses, including Avian influenza virus and HIV. When used to treat virus-infected animals, it cured Newcastle disease and Infectious bursa disease of chickens, Parvovirus disease of dogs, and Peste des petits ruminants disease of sheep and goats. A number of HIV/AIDS patients treated with it have been reported to become HIV-negative (antibody and antigen). COVID-19 patients are also reported to recover and test virus negative when treated with MSAMS. PSA titers of prostate cancer/enlargement patients normalize (≤4) following treatment with MSAMS. MSAMS has also potentiated ampicillin trihydrate, sulfadimidin, cotrimoxazole, piparazine citrate and chloroquine phosphate to achieve ≥ 95 % infection-load reductions (AMR-prevention). At 75 % of doses of ampicillin, cotrimoxazole, and streptomycin, supporting MSAMS-formulations' treatments with antioxidants led to the termination of even already resistant infections.

Keywords: electrical charges, viruses, abnormal cells, aluminum-magnesium silicate

Procedia PDF Downloads 62

Authors: Kamakshaiah Kolli, R. Seshadri

Abstract:

Water is a key resource in all economic activities ranging from agriculture to industry. Only a tiny fraction of the planet's abundant water is available to us as fresh water. Assessment of water quality has always been paramount in the field of environmental quality management. It is the foundation for health, hygiene, progress and prosperity. With ever increasing pressure of human population, there is severe stress on water resources. Therefore efficient water management is essential to civil society for betterment of quality of life. The present study emphasizes on the groundwater quality, sources of ground water contamination, variation of groundwater quality and its spatial distribution. The bases for groundwater quality assessment are groundwater bodies and representative monitoring network enabling determination of chemical status of groundwater body. For this study, water samples were collected from various areas of the entire corporation area of Guntur. Water is required for all living organisms of which 1.7% is available as ground water. Water has no calories or any nutrients, but essential for various metabolic activities in our body. Chemical and physical parameters can be tested for identifying the portability of ground water. Electrical conductivity, pH, alkalinity, Total Alkalinity, TDS, Calcium, Magnesium, Sodium, Potassium, Chloride, and Sulphate of the ground water from Guntur district: Different areas of the District were analyzed. Our aim is to check, if the ground water from the above areas are potable or not. As multivariate are present, Data mining technique using JRIP rules was employed for classifying the ground water.

Keywords: groundwater, water quality standards, potability, data mining, JRIP, PCA, classification

Procedia PDF Downloads 428

Authors: Manal Hassan Abdel Aziz, Fatma Mohamed Magdy Badr El Dine, Nourhan Mohamed Mohamed Saeed

Abstract:

Establishing association between lip print patterns and those of fingerprints as well as blood groups is of fundamental importance in the forensic identification domain. The first aim of the current study was to determine the prevalent types of ABO blood groups, lip prints and fingerprints patterns in both studied populations. Secondly, to analyze any relation found between the different print patterns and the blood groups, which would be valuable in identification purposes. The present study was conducted on 60 healthy volunteers, (30 males and 30 females) from each of the studied population. Lip prints and fingerprints were obtained and classified according to Tsuchihashi's classification and Michael Kuchen’s classification, respectively. The results show that the ulnar loop was the most frequent among both populations. Blood group A was the most frequent among Egyptians, while blood groups O and B were the predominant among Malaysians. Significant relations were observed between lip print patterns and fingerprint (in the second quadrant for Egyptian males and the first one for Malaysian). For Malaysian females, a statistically significant association was proved in the fourth quadrant. Regarding the blood groups, 89.5% of ulnar loops were significantly related to blood group A among Egyptian males. The results proved an association between the fingerprint pattern and the lip prints, as well as between the ABO blood group and the pattern of fingerprints. However, further researches with larger sample sizes need to be directed to approve the current results.

Keywords: ABO, cheiloscopy, dactylography, Egyptians, Malaysians

Procedia PDF Downloads 217

Authors: Daniel Todorov, Anton Hinkov, Petya Angelova, Kalina Shishkova, Venelin Tsvetkov, Stoyan Shishkov

Abstract:

Human herpes viruses (HHV) are ubiquitous pathogens with a pandemic spread across the globe. HHV type 1 is the main causative agent of cold sores and fever blisters around the mouth and on the face, whereas HHV type 2 is generally responsible for genital herpes outbreaks. The treatment of both viruses is more or less successful with antivirals from the nucleoside analogues group. Their wide application increasingly leads to the emergence of resistant mutants In the past, medicinal plants have been used to treat a number of infectious and non-infectious diseases. Their diversity and ability to produce the vast variety of secondary metabolites according to the characteristics of the environment give them the potential to help us in our warfare with viral infections. The variable chemical characteristics and complex composition is an advantage in the treatment of herpes since the emergence of resistant mutants is significantly complicated. The screening process is difficult due to the lack of standardization. That is why it is especially important to follow the mechanism of antiviral action of plants. On the one hand, it may be expected to interact with its compounds, resulting in enhanced antiviral effects, and the most appropriate environmental conditions can be chosen to maximize the amount of active secondary metabolites. During our study, we followed the activity of various plant extracts on the viral replication cycle as well as their effect on the extracellular virion. We obtained our results following the logical sequence of the experimental settings - determining the cytotoxicity of the extracts, evaluating the overall effect on viral replication and extracellular virion.During our research, we have screened a variety of plant extracts for their antiviral activity against both virus replication and the virion itself. We investigated the effect of the extracts on the individual stages of the viral replication cycle - viral adsorption, penetration and the effect on replication depending on the time of addition. If there are positive results in the later experiments, we had studied the activity over viral adsorption, penetration and the effect of replication according to the time of addition. Our results indicate that some of the extracts from the Lamium album have several targets. The first stages of the viral life cycle are most affected. Several of our active antiviral agents have shown an effect on extracellular virion and adsorption and penetration processes. Our research over the last decade has shown several curative antiviral plants - some of which are from the Lamiacea family. The rich set of active ingredients of the plants in this family makes them a good source of antiviral preparation.

Keywords: human herpes virus, antiviral activity, Lamium album, Nepeta nuda

Procedia PDF Downloads 153

Authors: Marinella Majorano, Rachele Ferrari, Tamara Bastianello

Abstract:

The recent technological advance allows for applying innovative and multimedia screen-based assessment tools to test children's language and early literacy skills, monitor their growth over the preschool years, and test their readiness for primary school. Several are the advantages that a computer-based assessment tool offers with respect to paper-based tools. Firstly, computer-based tools which provide the use of games, videos, and audio may be more motivating and engaging for children, especially for those with language difficulties. Secondly, computer-based assessments are generally less time-consuming than traditional paper-based assessments: this makes them less demanding for children and provides clinicians and researchers, but also teachers, with the opportunity to test children multiple times over the same school year and, thus, to monitor their language growth more systematically. Finally, while paper-based tools require offline coding, computer-based tools sometimes allow obtaining automatically calculated scores, thus producing less subjective evaluations of the assessed skills and provide immediate feedback. Nonetheless, using computer-based assessment tools to test meta-phonological and language skills in children is not yet common practice in Italy. The present contribution aims to estimate the internal consistency of a computer-based assessment (i.e., the Simo-syl assessment). Sixty-three Italian pre-schoolers aged between 4;10 and 5;9 years were tested at the beginning of the last year of the preschool through paper-based standardised tools in their lexical (Peabody Picture Vocabulary Test), morpho-syntactical (Grammar Repetition Test for Children), meta-phonological (Meta-Phonological skills Evaluation test), and phono-articulatory skills (non-word repetition). The same children were tested through Simo-syl assessment on their phonological and meta-phonological skills (e.g., recognise syllables and vowels and read syllables and words). The internal consistency of the computer-based tool was acceptable (Cronbach's alpha = .799). Children's scores obtained in the paper-based assessment and scores obtained in each task of the computer-based assessment were correlated. Significant and positive correlations emerged between all the tasks of the computer-based assessment and the scores obtained in the CMF (r = .287 - .311, p < .05) and in the correct sentences in the RCGB (r = .360 - .481, p < .01); non-word repetition standardised test significantly correlates with the reading tasks only (r = .329 - .350, p < .05). Further tasks should be included in the current version of Simo-syl to have a comprehensive and multi-dimensional approach when assessing children. However, such a tool represents a good chance for the teachers to early identifying language-related problems even in the school environment.

Keywords: assessment, computer-based, early identification, language-related skills

Procedia PDF Downloads 181

Authors: Jigg Pelayo, Ricardo Villar, Einstine Opiso

Abstract:

The rampant and unintended spread of urban areas resulted in increasing artificial component features in the land cover types of the countryside and bringing forth the urban heat island (UHI). This paved the way to wide range of negative influences on the human health and environment which commonly relates to air pollution, drought, higher energy demand, and water shortage. Land cover type also plays a relevant role in the process of understanding the interaction between ground surfaces with the local temperature. At the moment, the depiction of the land surface temperature (LST) at city/municipality scale particularly in certain areas of Misamis Oriental, Philippines is inadequate as support to efficient mitigations and adaptations of the surface urban heat island (SUHI). Thus, this study purposely attempts to provide application on the Landsat 8 satellite data and low density Light Detection and Ranging (LiDAR) products in mapping out quality automated LST model and crop-level land cover classification in a local scale, through theoretical and algorithm based approach utilizing the principle of data analysis subjected to multi-dimensional image object model. The paper also aims to explore the relationship between the derived LST and land cover classification. The results of the presented model showed the ability of comprehensive data analysis and GIS functionalities with the integration of object-based image analysis (OBIA) approach on automating complex maps production processes with considerable efficiency and high accuracy. The findings may potentially lead to expanded investigation of temporal dynamics of land surface UHI. It is worthwhile to note that the environmental significance of these interactions through combined application of remote sensing, geographic information tools, mathematical morphology and data analysis can provide microclimate perception, awareness and improved decision-making for land use planning and characterization at local and neighborhood scale. As a result, it can aid in facilitating problem identification, support mitigations and adaptations more efficiently.

Keywords: LiDAR, OBIA, remote sensing, local scale

Procedia PDF Downloads 281

Authors: Jairson Barbosa Rodrigues, Paulo Romero Martins Maciel, Germano Crispim Vasconcelos

Abstract:

This paper presents an investigation of the performance impacts regarding the variation of five factors (input data size, node number, cores, memory, and disks) when applying a distributed implementation of Naïve Bayes for text classification of a large Corpus on the Spark big data processing framework. Problem: The algorithm's performance depends on multiple factors, and knowing before-hand the effects of each factor becomes especially critical as hardware is priced by time slice in cloud environments. Objectives: To explain the functional relationship between factors and performance and to develop linear predictor models for time and cost. Methods: the solid statistical principles of Design of Experiments (DoE), particularly the randomized two-level fractional factorial design with replications. This research involved 48 real clusters with different hardware arrangements. The metrics were analyzed using linear models for screening, ranking, and measurement of each factor's impact. Results: Our findings include prediction models and show some non-intuitive results about the small influence of cores and the neutrality of memory and disks on total execution time, and the non-significant impact of data input scale on costs, although notably impacts the execution time.

Keywords: big data, design of experiments, distributed machine learning, natural language processing, spark

Procedia PDF Downloads 118