Search results for: clustering

Authors: Saeid Haghjoo, Ebrahim Reyhani, Fahimeh Kolahdouz

Abstract:

The present study aimed to evaluate the understanding of the students in Tehran universities (Iran) about the numerical representation of the average rate of change based on the Structure of Observed Learning Outcomes (SOLO). In the present descriptive-survey research, the statistical population included undergraduate students (basic sciences and engineering) in the universities of Tehran. The samples were 604 students selected by random multi-stage clustering. The measurement tool was a task whose face and content validity was confirmed by math and mathematics education professors. Using Cronbach's Alpha criterion, the reliability coefficient of the task was obtained 0.95, which verified its reliability. The collected data were analyzed by descriptive statistics and inferential statistics (chi-squared and independent t-tests) under SPSS-24 software. According to the SOLO model in the prestructural, unistructural, and multistructural levels, basic science students had a higher percentage of understanding than that of engineering students, although the outcome was inverse at the relational level. However, there was no significant difference in the average understanding of both groups. The results indicated that students failed to have a proper understanding of the numerical representation of the average rate of change, in addition to missconceptions when using physics formulas in solving the problem. In addition, multiple solutions were derived along with their dominant methods during the qualitative analysis. The current research proposed to focus on the context problems with approximate calculations and numerical representation, using software and connection common relations between math and physics in the teaching process of teachers and professors.

Keywords: average rate of change, context problems, derivative, numerical representation, SOLO taxonomy

Procedia PDF Downloads 93

Authors: Meimei Shi

Abstract:

Objectives: The identification of endangered species, especially simultaneous detection of multiple species in complex samples, plays a critical role in alleged wildlife crime incidents and prevents illegal trade. This study was to develop a multi-locus DNA metabarcoding method for endangered animal species identification. Methods: Several pairs of universal primers were designed according to the mitochondria conserved gene regions. Experimental mixtures were artificially prepared by mixing well-defined species, including endangered species, e.g., forest musk, bear, tiger, pangolin, and sika deer. The artificial samples were prepared with 1-16 well-characterized species at 1% to 100% DNA concentrations. After multiplex-PCR amplification and parameter modification, the amplified products were analyzed by capillary electrophoresis and used for NGS library preparation. The DNA metabarcoding was carried out based on Illumina MiSeq amplicon sequencing. The data was processed with quality trimming, reads filtering, and OTU clustering; representative sequences were blasted using BLASTn. Results: According to the parameter modification and multiplex-PCR amplification results, five primer sets targeting COI, Cytb, 12S, and 16S, respectively, were selected as the NGS library amplification primer panel. High-throughput sequencing data analysis showed that the established multi-locus DNA metabarcoding method was sensitive and could accurately identify all species in artificial mixtures, including endangered animal species Moschus berezovskii, Ursus thibetanus, Panthera tigris, Manis pentadactyla, Cervus nippon at 1% (DNA concentration). In conclusion, the established species identification method provides technical support for customs and forensic scientists to prevent the illegal trade of endangered animals and their products.

Keywords: DNA metabarcoding, endangered animal species, mitochondria nucleic acid, multi-locus

Procedia PDF Downloads 140

Authors: Donatella Giuliani

Abstract:

In this research, we propose an unsupervised grayscale image segmentation method based on a combination of the Firefly Algorithm and the Gaussian Mixture Model. Firstly, the Firefly Algorithm has been applied in a histogram-based research of cluster means. The Firefly Algorithm is a stochastic global optimization technique, centered on the flashing characteristics of fireflies. In this context it has been performed to determine the number of clusters and the related cluster means in a histogram-based segmentation approach. Successively these means are used in the initialization step for the parameter estimation of a Gaussian Mixture Model. The parametric probability density function of a Gaussian Mixture Model is represented as a weighted sum of Gaussian component densities, whose parameters are evaluated applying the iterative Expectation-Maximization technique. The coefficients of the linear super-position of Gaussians can be thought as prior probabilities of each component. Applying the Bayes rule, the posterior probabilities of the grayscale intensities have been evaluated, therefore their maxima are used to assign each pixel to the clusters, according to their gray-level values. The proposed approach appears fairly solid and reliable when applied even to complex grayscale images. The validation has been performed by using different standard measures, more precisely: the Root Mean Square Error (RMSE), the Structural Content (SC), the Normalized Correlation Coefficient (NK) and the Davies-Bouldin (DB) index. The achieved results have strongly confirmed the robustness of this gray scale segmentation method based on a metaheuristic algorithm. Another noteworthy advantage of this methodology is due to the use of maxima of responsibilities for the pixel assignment that implies a consistent reduction of the computational costs.

Keywords: clustering images, firefly algorithm, Gaussian mixture model, meta heuristic algorithm, image segmentation

Procedia PDF Downloads 217

Authors: P. Karthick, K. Mahesh

Abstract:

Video has become an increasingly significant component of our digital everyday contact. With the advancement of greater contents and shows of the resolution, its significant volume poses serious obstacles to the objective of receiving, distributing, compressing, and revealing video content of high quality. In this paper, we propose the primary beginning to complete a deep video compression model that jointly upgrades all video compression components. The video compression method involves splitting the video into frames, comparing the images using convolutional neural networks (CNN) to remove duplicates, repeating the single image instead of the duplicate images by recognizing and detecting minute changes using generative adversarial network (GAN) and recorded with long short-term memory (LSTM). Instead of the complete image, the small changes generated using GAN are substituted, which helps in frame level compression. Pixel wise comparison is performed using K-nearest neighbours (KNN) over the frame, clustered with K-means, and singular value decomposition (SVD) is applied for each and every frame in the video for all three color channels [Red, Green, Blue] to decrease the dimension of the utility matrix [R, G, B] by extracting its latent factors. Video frames are packed with parameters with the aid of a codec and converted to video format, and the results are compared with the original video. Repeated experiments on several videos with different sizes, duration, frames per second (FPS), and quality results demonstrate a significant resampling rate. On average, the result produced had approximately a 10% deviation in quality and more than 50% in size when compared with the original video.

Keywords: video compression, K-means clustering, convolutional neural network, generative adversarial network, singular value decomposition, pixel visualization, stochastic gradient descent, frame per second extraction, RGB channel extraction, self-detection and deciding system

Procedia PDF Downloads 188

Authors: Arsalan Ansari, Muhammad Dawood Idrees, Maria Hafeez

Abstract:

Use of mobile phones has been increasing considerably over the past decade. Currently, it is one of the main sources of communication and information. Initially, mobile phones were limited to calls and messages, but with the advent of new technology smart phones were being used for many other purposes including video games. Despite of positive outcomes, addiction to video games on mobile phone has become a leading cause of psychological and physiological problems among many people. Several researchers examined the different aspects of behavior addiction with the use of different scales. Objective of this study is to examine any distinction between mobile game addicted and non-addicted players with the use of electroencephalography (EEG), based upon psycho-physiological indicators. The mobile players were asked to play a mobile game and EEG signals were recorded by BIOPAC equipment with AcqKnowledge as data acquisition software. Electrodes were places, following the 10-20 system. EEG was recorded at sampling rate of 200 samples/sec (12,000samples/min). EEG recordings were obtained from the frontal (Fp1, Fp2), parietal (P3, P4), and occipital (O1, O2) lobes of the brain. The frontal lobe is associated with behavioral control, personality, and emotions. The parietal lobe is involved in perception, understanding logic, and arithmetic. The occipital lobe plays a role in visual tasks. For this study, a 60 second time window was chosen for analysis. Preliminary analysis of the signals was carried out with Acqknowledge software of BIOPAC Systems. From the survey based on CGS manual study 2010, it was concluded that five participants out of fifteen were in addictive category. This was used as prior information to group the addicted and non-addicted by physiological analysis. Statistical analysis showed that by applying clustering analysis technique authors were able to categorize the addicted and non-addicted players specifically on theta frequency range of occipital area.

Keywords: mobile game, addiction, psycho-physiology, EEG analysis

Procedia PDF Downloads 167

Authors: Enrique Claver Cortés, Bartolomé Marco Lajara, Eduardo Sánchez García, Pedro Seva Larrosa, Encarnación Manresa Marhuenda, Lorena Ruiz Fernández, Esther Poveda Pareja

Abstract:

In recent decades, the analysis of the effects of clustering as an essential factor for the development of innovations and the competitiveness of enterprises has raised great interest in different areas. Nowadays, companies have access to almost all tangible and intangible resources located and/or developed in any country in the world. However, despite the obvious advantages that this situation entails for companies, their geographical location has shown itself, increasingly clearly, to be a fundamental factor that positively influences their innovative performance and competitiveness. Industrial clusters could represent a unique level of analysis, positioned between the individual company and the industry, which makes them an ideal unit of analysis to determine the effects derived from company membership of a cluster. Also, the absorptive capacity (hereinafter 'AC') can mediate the process of innovation development by companies located in a cluster. The transformation and exploitation of knowledge could have a mediating effect between knowledge acquisition and innovative performance. The main objective of this work is to determine the key factors that affect the degree of generation and use of knowledge from the environment by companies and, consequently, their innovative performance and competitiveness. The elements analyzed are the companies' membership of a cluster and the AC. To this end, 30 most relevant papers published on this subject in the "Web of Science" database have been reviewed. Our findings show that, within a cluster, the knowledge coming from the companies' environment can significantly influence their innovative performance and competitiveness, although in this relationship, the degree of access and exploitation of the companies to this knowledge plays a fundamental role, which depends on a series of elements both internal and external to the company.

Keywords: absorptive capacity, clusters, innovation, knowledge

Procedia PDF Downloads 132

Authors: Chang-Fa Liu, Yi-Ting Wang, Yuan Liu, Hai-Feng Wei, Lei Fang, Jin Li

Abstract:

Heavy metals in sediments can cause adverse ecological effects while it exceeds a given criteria. The present study investigated sediment environmental quality, pollutant enrichment, ecological risk, and source identification for copper, cadmium, lead, zinc, mercury, and arsenic in the sediments collected from tidal flat marsh of Shuangtai estuary, China. The arithmetic mean integrated pollution index, geometric mean integrated pollution index, fuzzy integrated pollution index, and principal component score were used to characterize sediment environmental quality; fuzzy similarity and geo-accumulation Index were used to evaluate pollutant enrichment; correlation matrix, principal component analysis, and cluster analysis were used to identify source of pollution; environmental risk index and potential ecological risk index were used to assess ecological risk. The environmental qualities of sediment are classified to very low degree of contamination or low contamination. The similar order to element background of soil in the Liaohe plain is region of Sanjiaozhou, Honghaitan, Sandaogou, Xiaohe by pollutant enrichment analysis. The source identification indicates that correlations are significantly among metals except between copper and cadmium. Cadmium, lead, zinc, mercury, and arsenic will be clustered in the same clustering as the first principal component. Copper will be clustered as second principal component. The environmental risk assessment level will be scaled to no risk in the studied area. The order of potential ecological risk is As > Cd > Hg > Cu > Pb > Zn.

Keywords: ecological risk assessment, heavy metals, sediment, marsh, Shuangtai estuary

Procedia PDF Downloads 349

Authors: Garima Anand, Rupam Kapoor

Abstract:

Alternaria leaf spot caused by Alternaria carthami is one of the most devastating diseases of safflower. It has resulted in huge losses in crop production and cultivation leading to a fall out of India’s rank as the leading producer of safflower in the world. Understanding the diversity of any pathogen is essential for its management and for the development of disease control strategies. The diversity of A. carthami was therefore analysed on the basis of biochemical, pathogenicity and genetic lines using ISSR markers. Collections and isolations of 95 isolates of A. carthami were made from major safflower producing states of India. Virulence was analysed to evaluate the pathogenic potential of these isolates. The isolates from Bijapur, Dharwad districts (Karnataka), and Parbhani and Solapur districts (Maharashtra) were found to be highly virulent. The virulence assays showed low virulence levels (42%) for the largest part of the population. Biochemical characterization to assess aggressiveness of these isolates was done by estimating the activity of cell wall degrading enzymes where isolates from districts Dharwad, Bijapur of Karnataka and districts Parbhani and Latur of Maharashtra were found to be most aggressive. Genetic diversity among isolates of A. carthami was determined using eighteen ISSR markers. Distance analysis using neighbour joining method and PCoA analysis of the ISSR profiles divided the isolates into three sub-populations. The most virulent isolates clustered in one group in the dendrogram. The study provided no evidence for geographical clustering indicating that isolates are randomly spread across the states, signifying the high potential of the fungus to adapt to diverse regions. The study can, therefore, aid in the breeding and deployment of A. carthami resistant safflower varieties and in the management of Alternaria leaf spot disease.

Keywords: alternaria leaf spot, genetic diversity, pathogenic potential, virulence

Procedia PDF Downloads 255

Authors: Nur Sahver Uslu, Ali̇ Hakan Büyüklü

Abstract:

Maintenance, Repair, and Overhaul (MRO) costs are significant in the aviation industry. On the other hand, companies that provide MRO services to the aviation industry but are not dominant in the sector, need to determine the right strategies for sustainable profitability in a competitive environment. This study examined the operational real data of a small medium enterprise (SME) MRO company where analytical methods are not widely applied. The company's customers were divided into two categories: airline companies and non-airline companies, and the variables that best explained profitability were analyzed with Logistic Regression for each category and the results were compared. First, data reduction was applied to the transformed variables that went through the data cleaning and preparation stages, and the variables to be included in the model were decided. The misclassification rates for the logistic regression results concerning both customer categories are similar, indicating consistent model performance across different segments. Less profit margin is obtained from airline customers, which can be explained by the variables part description, time to quotation (TTQ), turnaround time (TAT), manager, part cost, and labour cost. The higher profit margin obtained from non-airline customers is explained only by the variables part description, part cost, and labour cost. Based on the two models, it can be stated that it is significantly more challenging for the MRO company, which is the subject of our study, to achieve profitability from Airline customers. While operational processes and organizational structure also affect the profit from airline customers, only the type of parts and costs determine the profit for non-airlines.

Keywords: aircraft, aircraft components, aviation, data analytics, data science, gini index, maintenance, repair, and overhaul, MRO, logistic regression, profit, variable clustering, variable reduction

Procedia PDF Downloads 35

Authors: Kamil Jonski

Abstract:

Last year vividly demonstrated, that populism and political instability can endanger democratic institutions in countries regarded as democratic transition champions (Poland) or cornerstones of liberal order (UK, US). So called ‘illiberal democracy’ is winning hearts and minds of voters, keen to believe that rule of strongman is a viable alternative to perceived decay of western values and institutions. These developments pose a serious threat to the democratic institutions (including rule of law), proven critical for both personal freedom and economic development. Although scholars proposed some structural explanations of the illiberal wave (notably focusing on inequality, stagnant incomes and drawbacks of globalization), they seem to have little predictive value. Indeed, events like Trump’s victory, Brexit or Polish shift towards populist nationalism always came as a surprise. Intriguingly, in the case of US election, simple rules like ‘Bread and Peace model’ gauged prospects of Trump’s victory better than pundits and pollsters. This paper attempts to compile set of indicators, in order to gauge various democracies’ vulnerability to populism, instability and pursuance of ‘illiberal’ projects. Among them, it identifies the gap between consensus assessment of institutional performance (as measured by WGI indicators) and citizens’ subjective assessment (survey based confidence in institutions). Plotting these variables against each other, reveals three clusters of countries – ‘predictable’ (good institutions and high confidence, poor institutions and low confidence), ‘blind’ (poor institutions, high confidence e.g. Uzbekistan or Azerbaijan) and ‘disillusioned’ (good institutions, low confidence e.g. Spain, Chile, Poland and US). It seems that this clustering – carried out separately for various institutions (like legislature, executive and courts) and blended with economic indicators like inequality and living standards (using PCA) – offers reasonably good watchlist of countries, that should ‘expect the unexpected’.

Keywords: illiberal democracy, populism, political instability, political risk measurement

Procedia PDF Downloads 204

Authors: Shivam Yadav, Neelam Atri

Abstract:

Cyanobacteria are photoautotrophic prokaryotes able to grow in diverse ecological habitats, originated 2.5 - 3.5 billion years ago and brought oxygenic photosynthesis. Since then superoxide dismutases (SODs) acquired great significance due to their ability to catalyze detoxification of byproducts of oxygenic photosynthesis, i.e. superoxide radicals. Sequence information from several cyanobacterial genomes offers a unique opportunity to conduct a comprehensive comparative analysis of the superoxide dismutases family. In the present study, we extracted information regarding SODs from species of sequenced cyanobacteria and investigated their diversity, conservation, domain structure, and evolution. 144 putative SOD homologues were identified. SODs are present in all cyanobacterial species reflecting their significant role in survival. However, their distribution varies, fewer in unicellular marine strains whereas abundant in filamentous nitrogen-fixing cyanobacteria. Motifs and invariant amino acids typical in eukaryotic SODs were conserved well in these proteins. These SODs were classified into three major families according to their domain structures. Interestingly, they lack additional domains as found in proteins of other family. Phylogenetic relationships correspond well with phylogenies based on 16S rRNA and clustering occurs on the basis of structural characteristics such as domain organization. Similar conserved motifs and amino acids indicate that cyanobacterial SODs make use of a similar catalytic mechanism as eukaryotic SODs. Gene gain-and-loss is insignificant during SOD evolution as evidenced by absence of additional domain. This study has not only examined an overall background of sequence-structure-function interactions for the SOD gene family but also revealed variation among SOD distribution based on ecophysiological and morphological characters.

Keywords: comparative genomics, cyanobacteria, phylogeny, superoxide dismutases

Procedia PDF Downloads 133

Authors: Leng Jian-Wei, Wang Lai-Jun, Li Ye

Abstract:

In order to measure and analyze the transportation situation within the counties of Shaanxi province over a certain period of time and to promote the province's future transportation planning and development, this paper proposes a reasonable layout plan and compares model rationality. The study uses entropy weight method to measure the transportation advantages of 107 counties in Shaanxi province from three dimensions: road network density, trunk line influence and location advantage in 2013 and 2021, and applies spatial autocorrelation analysis method to analyze the spatial layout and development trend of county-level transportation, and conducts ordinary least square (OLS)regression on transportation impact factors and other influencing factors. The paper also compares the regression fitting degree of the Geographically weighted regression(GWR) model and the OLS model. The results show that spatially, the transportation advantages of Shaanxi province generally show a decreasing trend from the Weihe Plain to the surrounding areas and mainly exhibit high-high clustering phenomenon. Temporally, transportation advantages show an overall upward trend, and the phenomenon of spatial imbalance gradually decreases. People's travel demands have changed to some extent, and the demand for rapid transportation has increased overall. The GWR model regression fitting degree of transportation advantages is 0.74, which is higher than the OLS regression model's fitting degree of 0.64. Based on the evolution of transportation advantages, it is predicted that this trend will continue for a period of time in the future. To improve the transportation advantages of Shaanxi province increasing the layout of rapid transportation can effectively enhance the transportation advantages of Shaanxi province. When analyzing spatial heterogeneity, geographic factors should be considered to establish a more reliable model

Keywords: traffic dominance, GWR model, spatial autocorrelation analysis, temporal and spatial evolution

Procedia PDF Downloads 89

Authors: Dagim Dessalegn Haile

Abstract:

This study investigated the interaction between the drivers' socio-demographic background information (age, gender, and driving experience) and the risky events score in the i-DREAMS platform. Further, the relationship between the participants' background driving behavior and the i-DREAMS platform behavioral output scores of risky events was also investigated. The i-DREAMS acronym stands for Smart Driver and Road Environment Assessment and Monitoring System. It is a European Union Horizon 2020 funded project consisting of 13 partners, researchers, and industry partners from 8 countries. A total of 25 Belgian car drivers (16 male and nine female) were considered for analysis. Drivers' ages were categorized into ages 18-25, 26-45, 46-65, and 65 and older. Drivers' driving experience was also categorized into four groups: 1-15, 16-30, 31-45, and 46-60 years. Drivers are classified into two clusters based on the recorded score for risky events during phase 1 (baseline) using risky events; acceleration, deceleration, speeding, tailgating, overtaking, and lane discipline. Agglomerative hierarchical clustering using SPSS shows Cluster 1 drivers are safer drivers, and Cluster 2 drivers are identified as risky drivers. The analysis result indicated no significant relationship between age groups, gender, and experience groups except for risky events like acceleration, tailgating, and overtaking in a few phases. This is mainly because the fewer participants create less variability of socio-demographic background groups. Repeated measure ANOVA shows that cluster 2 drivers improved more than cluster 1 drivers for tailgating, lane discipline, and speeding events. A positive relationship between background drivers' behavior and i-DREAMS platform behavioral output scores is observed. It implies that car drivers who in the questionnaire data indicate committing more risky driving behavior demonstrate more risky driver behavior in the i-DREAMS observed driving data.

Keywords: i-dreams, car drivers, socio-demographic background, risky events

Procedia PDF Downloads 70

Authors: Novee Lor C. Leyso, Maylin C. Palatino

Abstract:

Under-five malnutrition continues to persist in the Philippines, particularly in the island Province of Marinduque, with prevalence of some forms of malnutrition even worsening in recent years. Local spatial cluster detection provides a spatial perspective in understanding this phenomenon as key in analyzing patterns of geographic variation, identification of community-appropriate programs and interventions, and focused targeting on high-risk areas. Using data from a province-wide household-based census conducted in 2014–2016, this study aimed to determine and evaluate spatial clusters of under-five malnutrition, across the province and within each municipality at the individual level using household location. Malnutrition was defined as weight-for-age z-score that fall outside the 2 standard deviations from the median of the WHO reference population. The Kulldorff’s elliptical spatial scan statistic in binomial model was used to locate clusters with high-risk of malnutrition, while adjusting for age and membership to government conditional cash transfer program as proxy for socio-economic status. One large significant cluster of under-five malnutrition was found southwest of the province, in which living in these areas at least doubles the risk of malnutrition. Additionally, at least one significant cluster were identified within each municipality—mostly located along the coastal areas. All these indicate apparent geographical variations across and within municipalities in the province. There were also similarities and disparities in the patterns of risk of malnutrition in each cluster across municipalities, and even within municipality, suggesting underlying causes at work that warrants further investigation. Therefore, community-appropriate programs and interventions should be identified and should be focused on high-risk areas to maximize limited government resources. Further studies are also recommended to determine factors affecting variations in childhood malnutrition considering the evidence of spatial clustering found in this study.

Keywords: Binomial model, Kulldorff’s elliptical spatial scan statistic, Philippines, under-five malnutrition

Procedia PDF Downloads 141

Authors: Maad Kamal Al-Anni

Abstract:

This study is about an algorithmic dependence of Artificial Neural Network on Multilayer Perceptron (MPL) pertaining to the classification and clustering presentations for Mobile Adhoc Network vulnerabilities. Moreover, mobile ad hoc network (MANET) is ubiquitous intelligent internetworking devices in which it has the ability to detect their environment using an autonomous system of mobile nodes that are connected via wireless links. Security affairs are the most important subject in MANET due to the easy penetrative scenarios occurred in such an auto configuration network. One of the powerful techniques used for inspecting the network packets is Intrusion Detection System (IDS); in this article, we are going to show the effectiveness of artificial neural networks used as a machine learning along with stochastic approach (information gain) to classify the malicious behaviors in simulated network with respect to different IDS techniques. The monitoring agent is responsible for detection inference engine, the audit data is collected from collecting agent by simulating the node attack and contrasted outputs with normal behaviors of the framework, whenever. In the event that there is any deviation from the ordinary behaviors then the monitoring agent is considered this event as an attack , in this article we are going to demonstrate the  signature-based IDS approach in a MANET by implementing the back propagation algorithm over ensemble-based Traffic Table (TT), thus the signature of malicious behaviors or undesirable activities are often significantly prognosticated and efficiently figured out, by increasing the parametric set-up of Back propagation algorithm during the experimental results which empirically shown its effectiveness  for the ratio of detection index up to 98.6 percentage. Consequently it is proved in empirical results in this article, the performance matrices are also being included in this article with Xgraph screen show by different through puts like Packet Delivery Ratio (PDR), Through Put(TP), and Average Delay(AD).

Keywords: Intrusion Detection System (IDS), Mobile Adhoc Networks (MANET), Back Propagation Algorithm (BPA), Neural Networks (NN)

Procedia PDF Downloads 195

Authors: Vahid Ebrahimipour

Abstract:

Word representation and context meaning of text-based documents play an essential role in knowledge modeling. Business procedures written in natural language are meant to store technical and engineering information, management decision and operation experience during the production system life cycle. Context meaning representation is highly dependent upon word sense, lexical relativity, and sematic features of the argument. This paper proposes a method for lexical semantic analysis and context meaning representation of maintenance activity in a mass production system. Our approach constructs a straightforward lexical semantic approach to analyze facilitates semantic and syntactic features of context structure of maintenance report to facilitate translation, interpretation, and conversion of human-readable interpretation into computer-readable representation and understandable with less heterogeneity and ambiguity. The methodology will enable users to obtain a representation format that maximizes shareability and accessibility for multi-purpose usage. It provides a contextualized structure to obtain a generic context model that can be utilized during the system life cycle. At first, it employs a co-occurrence-based clustering framework to recognize a group of highly frequent contextual features that correspond to a maintenance report text. Then the keywords are identified for syntactic and semantic extraction analysis. The analysis exercises causality-driven logic of keywords’ senses to divulge the structural and meaning dependency relationships between the words in a context. The output is a word contextualized representation of maintenance activity accommodating computer-based representation and inference using OWL/RDF.

Keywords: lexical semantic analysis, metadata modeling, contextual meaning extraction, ontology modeling, knowledge representation

Procedia PDF Downloads 105

Authors: Hediyeh Talebi, Shokoofeh Ghiam, Changiz Eslahchi

Abstract:

Traditionally, Alzheimer’s disease research has focused on genes with significant fold changes, potentially neglecting subtle but biologically important alterations. Our study introduces an integrative approach that highlights genes crucial to underlying biological processes, regardless of their fold change magnitude. Alzheimer's Single-cell RNA-seq data related to the peripheral blood mononuclear cells (PBMC) was extracted from the Gene Expression Omnibus (GEO). After quality control, normalization, scaling, batch effect correction, and clustering, differentially expressed genes (DEGs) were identified with adjusted p-values less than 0.05. These DEGs were categorized based on cell-type, resulting in four datasets, each corresponding to a distinct cell type. To distinguish between cells from healthy individuals and those with Alzheimer's, an adversarial autoencoder with a classifier was employed. This allowed for the separation of healthy and diseased samples. To identify the most influential genes in this classification, the weight matrices in the network, which includes the encoder and classifier components, were multiplied, and focused on the top 20 genes. The analysis revealed that while some of these genes exhibit a high fold change, others do not. These genes, which may be overlooked by previous methods due to their low fold change, were shown to be significant in our study. The findings highlight the critical role of genes with subtle alterations in diagnosing Alzheimer's disease, a facet frequently overlooked by conventional methods. These genes demonstrate remarkable discriminatory power, underscoring the need to integrate biological relevance with statistical measures in gene prioritization. This integrative approach enhances our understanding of the molecular mechanisms in Alzheimer’s disease and provides a promising direction for identifying potential therapeutic targets.

Keywords: alzheimer's disease, single-cell RNA-seq, neural networks, blood biomarkers

Procedia PDF Downloads 67

Authors: Yu-Wen Huang, Yi-Cheng Chiang

Abstract:

With urban development, lots of buildings are built around the city. The buildings always affect the urban wind environment. The accelerative situation of wind caused of buildings often makes pedestrians uncomfortable, even causes the accidents and dangers. Factors influencing pedestrian level wind including atmospheric boundary layer, wind direction, wind velocity, planting, building volume, geometric shape of the buildings and adjacent interference effects, etc. Planting has many functions including scraping and slowing urban heat island effect, creating a good visual landscape, increasing urban green area and improve pedestrian level wind. On the other hand, urban square is an important space element supporting the entrance to buildings, city landmarks, and activity collections, etc. The appropriateness of urban square environment usually dominates its success. This research focuses on the effect of tree-planting on the wind environment of urban square. This research studied the square belt of Taichung City Hall. Taichung City Hall is a cuboid building with a large mass opening. The square belt connects the front square, the central opening and the back square. There is often wind draft on the square belt. This phenomenon decreases the activities on the squares. This research applies tree-planting to improve the wind environment and evaluate the effects of two types of planting configuration. The Computational Fluid Dynamics (CFD) simulation analysis and extensive field measurements are applied to explore the improve efficiency of planting configuration on wind environment. This research compares efficiencies of different kinds of planting configuration, including the clustering array configuration and the dispersion, and evaluates the efficiencies by the SET*.

Keywords: micro-climate, wind environment, planting configuration, comfortableness, computational fluid dynamics (CFD)

Procedia PDF Downloads 311

Authors: N. Casado-Sanz, B. Guirao

Abstract:

The population aged 65 and over is projected to double in the coming decades. Due to this increase, driver population is expected to grow and in the near future, all countries will be faced with population aging of varying intensity and in unique time frames. This is the greatest challenge facing industrialized nations and due to this fact, the study of the relationships of dependency between population aging and road safety is becoming increasingly relevant. Although the deterioration of driving skills in the elderly has been analyzed in depth, to our knowledge few research studies have focused on the road infrastructure and the mobility of this particular group of users. In Spain, crosstown roads have one of the highest fatality rates. These rural routes have a higher percentage of elderly people who are more dependent on driving due to the absence or limitations of urban public transportation. Analysing road safety in these routes is very complex because of the variety of the features, the dispersion of the data and the complete lack of related literature. The objective of this paper is to identify key factors that cause traffic accidents. The individuals under study were the accidents with killed or seriously injured in Spanish crosstown roads during the period 2006-2015. Latent cluster analysis was applied as a preliminary tool for segmentation of accidents, considering population aging as the main input among other socioeconomic indicators. Subsequently, a linear regression analysis was carried out to estimate the degree of dependence between the accident rate and the variables that define each group. The results show that segmenting the data is very interesting and provides further information. Additionally, the results revealed the clear influence of the aging variable in the clusters obtained. Other variables related to infrastructure and mobility levels, such as the crosstown roads layout and the traffic intensity aimed to be one of the key factors in the causality of road accidents.

Keywords: cluster analysis, population ageing, rural roads, road safety

Procedia PDF Downloads 113

Authors: Cristian Matti, Valerie Fowles, Eva Enyedi, Piotr Pogorzelski

Abstract:

The system mapping process can be defined as a knowledge service where a team of facilitators, experts and practitioners facilitate a guided conversation, enable the exchange of information and support an iterative curation process. System mapping processes rely on science-based tools to introduce and simplify a variety of components and concepts of socio-technical systems through metaphors while facilitating an interactive dialogue process to enable the design of co-created maps. System maps work then as “artifacts” to provide information and focus the conversation into specific areas around the defined challenge and related decision-making process. Knowledge management facilitates the curation of that data gathered during the system mapping sessions through practices of documentation and subsequent knowledge co-production for which common practices from data science are applied to identify new patterns, hidden insights, recurrent loops and unexpected elements. This study presents empirical evidence on the application of these techniques to explore mechanisms by which visual tools provide guiding principles to portray system components, key variables and types of data through the lens of climate change. In addition, data science facilitates the structuring of elements that allow the analysis of layers of information through affinity and clustering analysis and, therefore, develop simple indicators for supporting the decision-making process. This paper addresses methodological and empirical elements on the horizontal learning process that integrate system mapping through visual tools, interpretation, cognitive transformation and analysis. The process is designed to introduce practitioners to simple iterative and inclusive processes that create actionable knowledge and enable a shared understanding of the system in which they are embedded.

Keywords: indicators, knowledge management, system mapping, visual tools

Procedia PDF Downloads 195

Authors: Zimu Li, Zheng Wan

Abstract:

The Suez Canal plays an important role in global shipping networks and is one of the most frequently used waterways in the world. The 2021 canal obstruction by ship Ever Given in March 2021, however, completed blocked the Suez Canal for a week and caused significant disruption to world trade. Therefore, it is very important to quantitatively analyze the impact of the accident on the robustness of the global shipping network. However, the current research on maritime transportation networks is usually limited to local or small-scale networks in a certain region. Based on the complex network theory, this study establishes a global shipping complex network covering 2713 nodes and 137830 edges by using the real trajectory data of the global marine transport ship automatic identification system in 2018. At the same time, two attack modes, deliberate (Suez Canal Blocking) and random, are defined to calculate the changes in network node degree, eccentricity, clustering coefficient, network density, network isolated nodes, betweenness centrality, and closeness centrality under the two attack modes, and quantitatively analyze the actual impact of Suez Canal Blocking on the robustness of global shipping network. The results of the network robustness analysis show that Suez Canal blocking was more destructive to the shipping network than random attacks of the same scale. The network connectivity and accessibility decreased significantly, and the decline decreased with the distance between the port and the canal, showing the phenomenon of distance attenuation. This study further analyzes the impact of the blocking of the Suez Canal on Chinese ports and finds that the blocking of the Suez Canal significantly interferes withChina's shipping network and seriously affects China's normal trade activities. Finally, the impact of the global supply chain is analyzed, and it is found that blocking the canal will seriously damage the normal operation of the global supply chain.

Keywords: global shipping networks, ship AIS trajectory data, main channel, complex network, eigenvalue change

Procedia PDF Downloads 183

Authors: Nsikan Affiah, Kayode Osungbade, Williams Uzoma

Abstract:

Malaria remains one of the major killers of humans worldwide, threatening the lives of more than one-third of the world’s population. Some people refers it to; a disease of poverty because it contributes towards national poverty through its impact on foreign direct investment, tourism, labour productivity, and trade. At the micro level, it may cause poverty through spending on health care, income losses, and premature deaths. Unfortunately, malaria is a disease that affects both low-income household and its high-income counterpart, but low-income households are still at greater risk because significant part of the available monthly income is dedicated to various preventive and treatment measures. The objective of this study is to estimate direct and indirect cost of malaria treatment in households in a section of South-South Region (Akwa Ibom State) of Nigeria. A cross-sectional study of Six Hundred and Forty (640) heads of households or any adult representative of households in three local government areas of Akwa Ibom State, Nigeria from May 1-31, 2015 were ascertained through interviewer-administered questionnaire adapted from Nigerian Malaria Indicator Survey Report. The clustering technique was used to select 640 households with the help of Primary Health Care (PHC) house numbering system. Using exchange rate of 197 Naira/USD, result shows that direct cost of malaria treatment was 8,894.44 USD while the indirect cost of malaria treatment was 11,012.81 USD. Total cost of treatment made up of 44.7% direct cost and 55.3% indirect cost, with average direct cost of malaria treatment per household estimated at 20.6 USD and the average indirect cost of treatment per household estimated at 25.1 USD. Average total cost for each episode (888) of malaria was estimated at 22.4 USD. While at household level, the average total cost was estimated at 45.5 USD. From the average total cost, low-income households would spend 36% of monthly household income on treating malaria and the impact could be said to be catastrophic, compared to high-income households where only 1.2% of monthly household income is spent on malaria treatment. It could be concluded that the cost of malaria treatment is well beyond the means of households and given the reality of repeated bouts of malaria and its contribution to the impoverishment of households, there is a need for urgent action.

Keywords: direct cost, indirect cost, low income households, malaria

Procedia PDF Downloads 258

Authors: Faheem Shahzad Baloch, Muhammad Azhar Nadeem, Muhammad Amjad Nawaz, Ephrem Habyarimana, Gonul Comertpay, Tolga Karakoy, Rustu Hatipoglu, Mehmet Zahit Yeken, Vahdettin Ciftci

Abstract:

Turkey is considered a bridge between Europe, Asia, and Africa and possibly played an important role in the distribution of many crops including common bean. Hundreds of common bean landraces can be found in Turkey, particularly in farmers’ fields, and they consistently contribute to the overall production. To investigate the existing genetic diversity and hybridization events between the Andean and Mesoamerican gene pools in the Turkish common bean, 188 common bean accessions (182 landraces and 6 modern cultivars as controls) were collected from 19 different Turkish geographic regions. These accessions were characterized using phenotypic data (growth habit and seed weight), geographic provenance, 12557 high-quality whole-genome DArTseq markers, and 3767 novel DArTseq loci were also identified. The clustering algorithms resolved the Turkish common bean landrace germplasm into the two recognized gene pools, the Mesoamerican and Andean gene pools. Hybridization events were observed in both gene pools (14.36% of the accessions) but mostly in the Mesoamerican (7.97% of the accessions), and was low relative to previous European studies. The lower level of hybridization witnessed the existence of Turkish common bean germplasm in its original form as compared to Europe. Mesoamerican gene pool reflected a higher level of diversity, while the Andean gene pool was predominant (56.91% of the accessions), but genetically less diverse and phenotypically more pure, reflecting farmers greater preference for the Andean gene pool. We also found some genetically distinct landraces and overall, a meaningful level of genetic variability which can be used by the scientific community in breeding efforts to develop superior common bean strains.

Keywords: bean germplasm, DArTseq markers, genotyping by sequencing, Turkey, whole genome diversity

Procedia PDF Downloads 244

Authors: Miao Li, Mengyuan Xu

Abstract:

As a low-carbon travel mode, bicycling has drawn increasing political interest in the contemporary Chinese urban context, and the public sharing bikes have become the most popular ways of bike usage in China now. This research aims to explore the spatial-temporal relationship between sharing bike usage and different characteristics of the urban street built environment. In the research, street segments were used as the analytic unit of the street built environment defined by street intersections. The sharing bike usage data in the research include a total of 2.64 million samples that are the entire sharing bike distribution data recorded in two days in 2018 within a neighborhood of 185.4 hectares in the city of Wuhan, China. And these data are assigned to the 97 urban street segments in this area based on their geographic location. The built environment variables used in this research are categorized into three sections: 1) street design characteristics, such as street width, street greenery, types of bicycle lanes; 2) condition of other public transportation, such as the availability of metro station; 3) Street function characteristics that are described by the categories and density of the point of interest (POI) along the segments. Spatial Lag Models (SLM) were used in order to reveal the relationships of specific urban streets built environment characteristics and the likelihood of sharing bicycling usage in whole and different periods a day. The results show: 1) there is spatial autocorrelation among sharing bicycling usage of urban streets in case area in general, non-working day, working day and each period of a day, which presents a clustering pattern in the street space; 2) a statistically strong association between bike sharing usage and several different built environment characteristics such as POI density, types of bicycle lanes and street width; 3) the pattern that bike sharing usage is influenced by built environment characteristics depends on the period within a day. These findings could be useful for policymakers and urban designers to better understand the factors affecting bike sharing system and thus propose guidance and strategy for urban street planning and design in order to promote the use of sharing bikes.

Keywords: big data, sharing bike usage, spatial statistics, urban street built environment

Procedia PDF Downloads 146

Authors: Asif Zaman, Moinul Islam Zaber, Amin Ahsan Ali

Abstract:

In recent years of industrialization, the South Asian countries are being affected by air pollution due to a severe increase in fine particulate matter 2.5 (PM₂.₅). Among them, Bangladesh is one of the most polluting countries. In this paper, statistical analyses were conducted on the time series of PM₂.₅ from various districts in Bangladesh, mostly around Dhaka city. Research has been conducted on the dynamic interactions and relationships between PM₂.₅ concentrations in different zones. The study is conducted toward understanding the characteristics of PM₂.₅, such as spatial-temporal characterization, correlation of other contributors behind air pollution such as human activities, driving factors and environmental casualties. Clustering on the data gave an insight on the districts groups based on their AQI frequency as representative districts. Seasonality analysis on hourly and monthly frequency found higher concentration of fine particles in nighttime and winter season, respectively. Cross correlation analysis discovered a phenomenon of correlations among cities based on time-lagged series of air particle readings and visualization framework is developed for observing interaction in PM₂.₅ concentrations between cities. Significant time-lagged correlations were discovered between the PM₂.₅ time series in different city groups throughout the country by cross correlation analysis. Additionally, seasonal heatmaps depict that the pooled series correlations are less significant in warmer months, and among cities of greater geographic distance as well as time lag magnitude and direction of the best shifted correlated particulate matter time series among districts change seasonally. The geographic map visualization demonstrates spatial behaviour of air pollution among districts around Dhaka city and the significant effect of wind direction as the vital actor on correlated shifted time series. The visualization framework has multipurpose usage from gathering insight of general and seasonal air quality of Bangladesh to determining the pathway of regional transportation of air pollution.

Keywords: air quality, particles, cross correlation, seasonality

Procedia PDF Downloads 105

Authors: Lazhar Belkhiri, Ammar Tiri, Lotfi Mouni, Fatma Elhadj Lakouas

Abstract:

This research aims to present a surface water quality assessment of hydrochemical parameters in the Kebir Rhumel Basin, Algeria. The water quality index (WQI), Mann–Kendall (MK) test, and hierarchical cluster analysis (HCA) were used in oder to understand the spatio-temporal distribution of the surface water quality in the study area. Eleven hydrochemical parameters were measured monthly at eight stations from January 2016 to December 2020. The dominant cation in the surface water was found to be calcium, followed by sodium, and the dominant anion was sulfate, followed by chloride. In terms of WQI, a significant percentage of surface water samples at stations Ain Smara (AS), Beni Haroune (BH), Grarem (GR), and Sidi Khlifa (SK) exhibited poor water quality, with approximately 89.5%, 90.6%, 78.2%, and 62.7%, respectively, falling into this category. Mann–Kendall trend analysis revealed a significantly increasing trend in WQI values at stations Oued Boumerzoug (ON) and SK, indicating that the temporal variation of WQI in these stations is significant. Hierarchical clustering analysis classified the data into three clusters. The first cluster contained approximately 22% of the total number of months, the second cluster included about 30%, and the third cluster had the highest representation, approximately 48% of the total number of months. Within these clusters, certain stations exhibited higher WQI values. In the first cluster, stations GR and ON had the highest WQI values. In the second cluster, stations Oued Boumerzoug (OB) and SK showed the highest WQI values, while in the last cluster, stations AS, BH, El Milia (EM), and Hammam Grouz (HG) had the highest mean WQI values. Also, approximately 38%, 41%, and 38% of the total water samples in the first, second, and third clusters, respectively, were classified as having poor water quality. The findings of this study can serve as a scientific basis for decision-makers to formulate strategies for surface water quality restoration and management in the region.

Keywords: surface water, water quality index (WQI), Mann Kendall (MK) test, hierarchical cluster analysis (HCA), spatial-temporal distribution, Kebir Rhumel Basin

Procedia PDF Downloads 26

Authors: Sa’adu Mafara Abubakar, Muhammad Nuraddeen Danjuma, Adewole Tomiwa Adetunji, Richard Mundembe, Salisu Mohammed, Francis Bayo Lewu, Joseph I. Kiok

Abstract:

Pearl millet is the most drought tolerant of all domesticated cereals, is cultivated extensively to feed millions of people who mainly live in hash agroclimatic zones. It serves as a major source of food for more than 40 million smallholder farmers living in the marginal agricultural lands of Northern Nigeria. Pearl millet grain is more nutritious than other cereals like maize, is also a principal source of energy, protein, vitamins, and minerals for millions of poorest people in the regions where it is cultivated. Pearl millet has recorded relatively little research attention compared with other crops and no sufficient work has analyzed its genetic diversity in north-western Nigeria. Therefore, this study was undertaken with the objectives to analyze the genetic diversity of pearl millet accessions using SSR marker and to analyze the extent of evolutionary relationship among pearl millet accessions at the molecular level. The result of the present study confirmed diversity among accessions of pearl millet in the study area. Simple Sequence Repeats (SSR) markers were used for genetic analysis and evolutionary relationship of the accessions of pearl millet. To analyze the level of genetic diversity, 8 polymorphic SSR markers were used to screen 69 accessions collected based on three maturity periods. SSR markers result reveal relationships among the accessions in terms of genetic similarities, evolutionary and ancestral origin, it also reveals a total of 53 alleles recorded with 8 microsatellites and an average of 6.875 per microsatellite, the range was from 3 to 9 alleles in PSMP2248 and PSMP2080 respectively. Moreover, both the factorial analysis and the dendrogram of phylogeny tree grouping patterns and cluster analysis were almost in agreement with each other that diversity is not clustering according to geographical patterns but, according to similarity, the result showed maximum similarity among clusters with few numbers of accessions. It has been recommended that other molecular markers should be tested in the same study area.

Keywords: pearl millet, genetic diversity, simple sequence repeat (SSR)

Procedia PDF Downloads 270

Authors: Violet Justine Mtonga, Cecilia Diaz

Abstract:

this paper explores the prevalence of loyalty programs in the UK gambling industry and their association with unintended consequences and harm amongst program members. The use of loyalty programs within the UK gambling industry has risen significantly with over 40 million cards in circulation. Some research suggests that as of 2013-2014, nearly 95% of UK consumers have at least one loyalty card with 78% being members of two or more programs, and the average household possesses ‘22 loyalty programs’, nearly half of which tend to be used actively. The core design of loyalty programs is to create a relational ‘win-win’ approach where value is jointly created between the parties involved through repetitive engagement. However, main concern about the diffusion of gambling organisations’ loyalty programs amongst consumers, might be the use by the organisations within the gambling industry to over influence customer engagement and potentially cause unintended harm. To help understand the complex phenomena of the diffusions and adaptation of the use of loyalty programs in the gambling industry, and the potential unintended outcomes, this study is theoretically underpinned by the social exchange theory of relationships entrenched in the processes of social exchanges of resources, rewards, and costs for long-term interactions and mutual benefits. Qualitative data were collected via in-depth interviews from 14 customers and 12 employees within the UK land-based gambling firms. Data were analysed using a combination of thematic and clustering analysis to help reveal and discover the emerging themes regarding the use of loyalty cards for gambling companies and exploration of subgroups within the sample. The study’s results indicate that there are different unintended consequences and harm of loyalty program engagement and usage such as maladaptive gambling behaviours, risk of compulsiveness, and loyalty programs promoting gambling from home. Furthermore, there is a strong indication of a rite of passage among loyalty program members. There is also strong evidence to support other unfavorable behaviors such as amplified gambling habits and risk-taking practices. Additionally, in pursuit of rewards, loyalty program incentives effectuate overconsumption and heighten expenditure. Overall, the primary findings of this study show that loyalty programs in the gambling industry should be designed with an ethical perspective and practice.

Keywords: gambling, loyalty programs, social exchange theory, unintended harm

Procedia PDF Downloads 90

Authors: Hsin Lee, Hsuan Lee

Abstract:

Legal artificial intelligence (LegalAI) has been increasing applications within legal systems, propelled by advancements in natural language processing (NLP). Compared with general documents, legal case documents are typically long text sequences with intrinsic logical structures. Most existing language models have difficulty understanding the long-distance dependencies between different structures. Another unique challenge is that while the Judiciary of Taiwan has released legal judgments from various levels of courts over the years, there remains a significant obstacle in the lack of labeled datasets. This deficiency makes it difficult to train models with strong generalization capabilities, as well as accurately evaluate model performance. To date, models in Taiwan have yet to be specifically trained on judgment data. Given these challenges, this research proposes a Longformer-based pre-trained language model explicitly devised for retrieving similar judgments in Taiwanese legal documents. This model is trained on a self-constructed dataset, which this research has independently labeled to measure judgment similarities, thereby addressing a void left by the lack of an existing labeled dataset for Taiwanese judgments. This research adopts strategies such as early stopping and gradient clipping to prevent overfitting and manage gradient explosion, respectively, thereby enhancing the model's performance. The model in this research is evaluated using both the dataset and the Average Entropy of Offense-charged Clustering (AEOC) metric, which utilizes the notion of similar case scenarios within the same type of legal cases. Our experimental results illustrate our model's significant advancements in handling similarity comparisons within extensive legal judgments. By enabling more efficient retrieval and analysis of legal case documents, our model holds the potential to facilitate legal research, aid legal decision-making, and contribute to the further development of LegalAI in Taiwan.

Keywords: legal artificial intelligence, computation and language, language model, Taiwanese legal cases

Procedia PDF Downloads 73

Authors: Mane Darbinyan, Lusine Hayrapetyan, Elen Matevosyan

Abstract:

Artificial Intelligence in Education (AIED) has been created to help students get ready for the workforce, and over the past 25 years, it has grown significantly, offering a variety of technologies to support academic, institutional, and administrative services. However, this is still challenging, especially considering the labor market's rapid change. While choosing a career, people face various obstacles because they do not take into consideration their own preferences, which might lead to many other problems like shifting jobs, work stress, occupational infirmity, reduced productivity, and manual error. Besides preferences, people should properly evaluate their technical and non-technical skills, as well as their personalities. Professional counseling has become a difficult undertaking for counselors due to the wide range of career choices brought on by changing technological trends. It is necessary to close this gap by utilizing technology that makes sophisticated predictions about a person's career goals based on their personality. Hence, there is a need to create an automated model that would help in decision-making based on user inputs. Improving career guidance can be achieved by embedding machine learning into the career consulting ecosystem. There are various systems of career guidance that work based on the same logic, such as the classification of applicants, matching applications with appropriate departments or jobs, making predictions, and providing suitable recommendations. Methodologies like KNN, Neural Networks, K-means clustering, D-Tree, and many other advanced algorithms are applied in the fields of data and compute some data, which is helpful to predict the right careers. Besides helping users with their career choice, these systems provide numerous opportunities which are very useful while making this hard decision. They help the candidate to recognize where he/she specifically lacks sufficient skills so that the candidate can improve those skills. They are also capable to offer an e-learning platform, taking into account the user's lack of knowledge. Furthermore, users can be provided with details on a particular job, such as the abilities required to excel in that industry.

Keywords: career guidance system, machine learning, career prediction, predictive decision, data mining, technical and non-technical skills

Procedia PDF Downloads 81